{ "pages": { "adobe-pdf": { "meta": { "id": "adobe-pdf", "url": "https://developer.adobe.com/document-services/docs/overview/", "requested_url": "https://developer.adobe.com/document-services/docs/overview/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 12731 } }, "anchors": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2440, "chars": 9762, "content_recall": 0.9502, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9597, "f_coverage": 0.9597, "f_balanced": 0.9745, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2440, "chars": 9762, "content_recall": 0.9502, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9597, "f_coverage": 0.9597, "f_balanced": 0.9745, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2017, "chars": 8071, "content_recall": 0.8275, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8571, "f_coverage": 0.8571, "f_balanced": 0.9056, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2094, "chars": 8376, "content_recall": 0.9834, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9867, "f_coverage": 0.9867, "f_balanced": 0.9916, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2074, "chars": 8296, "content_recall": 0.9834, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9867, "f_coverage": 0.9867, "f_balanced": 0.9916, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2416, "chars": 9667, "content_recall": 0.9502, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9597, "f_coverage": 0.9597, "f_balanced": 0.9745, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2413, "chars": 9655, "content_recall": 0.9502, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9597, "f_coverage": 0.9597, "f_balanced": 0.9745, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2073, "chars": 8292, "content_recall": 0.9834, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9867, "f_coverage": 0.9867, "f_balanced": 0.9916, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2410, "chars": 9643, "content_recall": 0.9502, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9597, "f_coverage": 0.9597, "f_balanced": 0.9745, "anchor_diag": { "content_chars": 8822, "noise_chars": 0, "content_ngrams": 1084, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 73 }, "notes": "" } }, "scoreable": true }, "airflow-docs": { "meta": { "id": "airflow-docs", "url": "https://airflow.apache.org/docs/", "requested_url": "https://airflow.apache.org/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 67588 } }, "anchors": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 966, "chars": 3865, "content_recall": 0.8355, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8639, "f_coverage": 0.8639, "f_balanced": 0.9104, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 976, "chars": 3905, "content_recall": 0.838, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8661, "f_coverage": 0.8661, "f_balanced": 0.9119, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 801, "chars": 3204, "content_recall": 0.6684, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7159, "f_coverage": 0.7159, "f_balanced": 0.8012, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 797, "chars": 3190, "content_recall": 0.8715, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8945, "f_coverage": 0.8945, "f_balanced": 0.9313, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "readability": { "method": "readability", "tokens": 753, "chars": 3015, "content_recall": 0.91, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9267, "f_coverage": 0.9267, "f_balanced": 0.9529, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3487, "chars": 13951, "content_recall": 0.8355, "noise_retention": 0.507, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7335, "f_coverage": 0.7335, "f_balanced": 0.6201, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3596, "chars": 14384, "content_recall": 0.8355, "noise_retention": 0.507, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7335, "f_coverage": 0.7335, "f_balanced": 0.6201, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1276, "chars": 5107, "content_recall": 0.8997, "noise_retention": 0.8873, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3754, "f_coverage": 0.3754, "f_balanced": 0.2003, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3476, "chars": 13907, "content_recall": 0.8355, "noise_retention": 0.507, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7335, "f_coverage": 0.7335, "f_balanced": 0.6201, "anchor_diag": { "content_chars": 3142, "noise_chars": 833, "content_ngrams": 389, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" } }, "scoreable": true }, "alembic-docs": { "meta": { "id": "alembic-docs", "url": "https://alembic.sqlalchemy.org/en/latest/", "requested_url": "https://alembic.sqlalchemy.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 104395 } }, "anchors": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 137, "chars": 550, "content_recall": 0.008, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0099, "f_coverage": 0.0099, "f_balanced": 0.0158, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 161, "chars": 645, "content_recall": 0.008, "noise_retention": 0.1042, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0099, "f_coverage": 0.0099, "f_balanced": 0.0158, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 130, "chars": 520, "content_recall": 0.008, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0099, "f_coverage": 0.0099, "f_balanced": 0.0158, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2139, "chars": 8557, "content_recall": 0.8171, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8481, "f_coverage": 0.8481, "f_balanced": 0.8993, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" }, "readability": { "method": "readability", "tokens": 53, "chars": 214, "content_recall": 0.0149, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0186, "f_coverage": 0.0186, "f_balanced": 0.0294, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9692, "chars": 38770, "content_recall": 0.4911, "noise_retention": 0.0625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5427, "f_coverage": 0.5427, "f_balanced": 0.6445, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9978, "chars": 39913, "content_recall": 0.4891, "noise_retention": 0.0625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5408, "f_coverage": 0.5408, "f_balanced": 0.6428, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2347, "chars": 9388, "content_recall": 0.8171, "noise_retention": 0.8333, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4589, "f_coverage": 0.4589, "f_balanced": 0.2769, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9672, "chars": 38690, "content_recall": 0.4911, "noise_retention": 0.0625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5427, "f_coverage": 0.5427, "f_balanced": 0.6445, "anchor_diag": { "content_chars": 15748, "noise_chars": 485, "content_ngrams": 1006, "noise_ngrams": 48, "ambiguous_ngrams_removed": 6, "content_sentences": 69 }, "notes": "" } }, "scoreable": true }, "alibaba-cloud-docs": { "meta": { "id": "alibaba-cloud-docs", "url": "https://www.alibabacloud.com/help/en", "requested_url": "https://www.alibabacloud.com/help", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 17495 } }, "anchors": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 269, "chars": 1077, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 269, "chars": 1077, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 78, "chars": 313, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 196, "chars": 785, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" }, "readability": { "method": "readability", "tokens": 12, "chars": 48, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 494, "chars": 1977, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 256, "chars": 1024, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 207, "chars": 829, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 485, "chars": 1941, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 83, "noise_chars": 0, "content_ngrams": 4, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 2 }, "notes": "" } }, "scoreable": false }, "amplitude-docs": { "meta": { "id": "amplitude-docs", "url": "https://amplitude.com/docs", "requested_url": "https://www.docs.developers.amplitude.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 335202 } }, "anchors": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1034, "chars": 4139, "content_recall": 0.5969, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6493, "f_coverage": 0.6493, "f_balanced": 0.7476, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1070, "chars": 4280, "content_recall": 0.6278, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6783, "f_coverage": 0.6783, "f_balanced": 0.7713, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 811, "chars": 3247, "content_recall": 0.5369, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5917, "f_coverage": 0.5917, "f_balanced": 0.6987, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 540, "chars": 2162, "content_recall": 0.4322, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4876, "f_coverage": 0.4876, "f_balanced": 0.6036, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "readability": { "method": "readability", "tokens": 64, "chars": 259, "content_recall": 0.048, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0593, "f_coverage": 0.0593, "f_balanced": 0.0917, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2938, "chars": 11755, "content_recall": 0.6106, "noise_retention": 0.1404, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.361, "f_precision": 0.6482, "f_coverage": 0.6482, "f_balanced": 0.7141, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2998, "chars": 11993, "content_recall": 0.554, "noise_retention": 0.1404, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.001, "f_precision": 0.5964, "f_coverage": 0.5964, "f_balanced": 0.6738, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1434, "chars": 5739, "content_recall": 0.7942, "noise_retention": 0.8947, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.395, "f_precision": 0.344, "f_coverage": 0.344, "f_balanced": 0.1859, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2932, "chars": 11730, "content_recall": 0.6106, "noise_retention": 0.1404, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.364, "f_precision": 0.6482, "f_coverage": 0.6482, "f_balanced": 0.7141, "anchor_diag": { "content_chars": 4666, "noise_chars": 1032, "content_ngrams": 583, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" } }, "scoreable": true }, "ansible-docs": { "meta": { "id": "ansible-docs", "url": "https://docs.ansible.com/", "requested_url": "https://docs.ansible.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 23586 } }, "anchors": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 774, "chars": 3096, "content_recall": 0.6127, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6641, "f_coverage": 0.6641, "f_balanced": 0.7598, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 790, "chars": 3161, "content_recall": 0.6286, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.679, "f_coverage": 0.679, "f_balanced": 0.7719, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 622, "chars": 2489, "content_recall": 0.5746, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.628, "f_coverage": 0.628, "f_balanced": 0.7298, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 652, "chars": 2608, "content_recall": 0.6349, "noise_retention": 0.0811, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.534, "f_precision": 0.6768, "f_coverage": 0.6768, "f_balanced": 0.751, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" }, "readability": { "method": "readability", "tokens": 67, "chars": 269, "content_recall": 0.0698, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0858, "f_coverage": 0.0858, "f_balanced": 0.1306, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1795, "chars": 7182, "content_recall": 0.6984, "noise_retention": 0.2432, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.671, "f_precision": 0.7094, "f_coverage": 0.7094, "f_balanced": 0.7264, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1789, "chars": 7159, "content_recall": 0.6984, "noise_retention": 0.2432, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.677, "f_precision": 0.7094, "f_coverage": 0.7094, "f_balanced": 0.7264, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 970, "chars": 3882, "content_recall": 0.7206, "noise_retention": 0.7838, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.062, "f_precision": 0.4914, "f_coverage": 0.4914, "f_balanced": 0.3326, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1781, "chars": 7127, "content_recall": 0.6984, "noise_retention": 0.2432, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.684, "f_precision": 0.7094, "f_coverage": 0.7094, "f_balanced": 0.7264, "anchor_diag": { "content_chars": 2667, "noise_chars": 380, "content_ngrams": 315, "noise_ngrams": 37, "ambiguous_ngrams_removed": 8, "content_sentences": 27 }, "notes": "" } }, "scoreable": true }, "anthropic-docs": { "meta": { "id": "anthropic-docs", "url": "https://platform.claude.com/docs/en/home", "requested_url": "https://docs.anthropic.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 477269 } }, "anchors": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 625, "chars": 2501, "content_recall": 0.6767, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7235, "f_coverage": 0.7235, "f_balanced": 0.8072, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 649, "chars": 2598, "content_recall": 0.6767, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7235, "f_coverage": 0.7235, "f_balanced": 0.8072, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 395, "chars": 1583, "content_recall": 0.4138, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4687, "f_coverage": 0.4687, "f_balanced": 0.5854, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 303, "chars": 1213, "content_recall": 0.3793, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4331, "f_coverage": 0.4331, "f_balanced": 0.55, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "readability": { "method": "readability", "tokens": 77, "chars": 308, "content_recall": 0.1164, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1414, "f_coverage": 0.1414, "f_balanced": 0.2085, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2081, "chars": 8327, "content_recall": 0.4095, "noise_retention": 0.0741, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.442, "f_precision": 0.4609, "f_coverage": 0.4609, "f_balanced": 0.5678, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2149, "chars": 8596, "content_recall": 0.4095, "noise_retention": 0.0741, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.396, "f_precision": 0.4609, "f_coverage": 0.4609, "f_balanced": 0.5678, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 870, "chars": 3481, "content_recall": 0.7069, "noise_retention": 0.9259, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.299, "f_precision": 0.261, "f_coverage": 0.261, "f_balanced": 0.1341, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2072, "chars": 8289, "content_recall": 0.4095, "noise_retention": 0.0741, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.448, "f_precision": 0.4609, "f_coverage": 0.4609, "f_balanced": 0.5678, "anchor_diag": { "content_chars": 2080, "noise_chars": 1126, "content_ngrams": 232, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" } }, "scoreable": true }, "apache-httpd": { "meta": { "id": "apache-httpd", "url": "https://httpd.apache.org/docs/", "requested_url": "https://httpd.apache.org/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 6306 } }, "anchors": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 202, "chars": 809, "content_recall": 0.4588, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5145, "f_coverage": 0.5145, "f_balanced": 0.629, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 210, "chars": 840, "content_recall": 0.4588, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5145, "f_coverage": 0.5145, "f_balanced": 0.629, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 169, "chars": 679, "content_recall": 0.3412, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.393, "f_coverage": 0.393, "f_balanced": 0.5088, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 130, "chars": 522, "content_recall": 0.4941, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5497, "f_coverage": 0.5497, "f_balanced": 0.6614, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "readability": { "method": "readability", "tokens": 130, "chars": 522, "content_recall": 0.5882, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.641, "f_coverage": 0.641, "f_balanced": 0.7407, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 705, "chars": 2822, "content_recall": 0.8235, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8537, "f_coverage": 0.8537, "f_balanced": 0.9032, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 644, "chars": 2577, "content_recall": 0.8706, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8937, "f_coverage": 0.8937, "f_balanced": 0.9308, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 323, "chars": 1292, "content_recall": 0.9529, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.962, "f_coverage": 0.962, "f_balanced": 0.9759, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 687, "chars": 2750, "content_recall": 0.8235, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8537, "f_coverage": 0.8537, "f_balanced": 0.9032, "anchor_diag": { "content_chars": 706, "noise_chars": 0, "content_ngrams": 85, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" } }, "scoreable": true }, "arch-wiki": { "meta": { "id": "arch-wiki", "url": "https://wiki.archlinux.org/title/Main_page", "requested_url": "https://wiki.archlinux.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 49518 } }, "anchors": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 405, "chars": 1621, "content_recall": 0.9294, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9427, "f_coverage": 0.9427, "f_balanced": 0.9634, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 405, "chars": 1621, "content_recall": 0.9294, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9427, "f_coverage": 0.9427, "f_balanced": 0.9634, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 195, "chars": 780, "content_recall": 0.3706, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.424, "f_coverage": 0.424, "f_balanced": 0.5408, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 373, "chars": 1495, "content_recall": 0.9059, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9233, "f_coverage": 0.9233, "f_balanced": 0.9506, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" }, "readability": { "method": "readability", "tokens": 3, "chars": 13, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2326, "chars": 9304, "content_recall": 0.7765, "noise_retention": 0.1667, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.43, "f_precision": 0.7872, "f_coverage": 0.7872, "f_balanced": 0.8039, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2414, "chars": 9659, "content_recall": 0.7765, "noise_retention": 0.1667, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.414, "f_precision": 0.7872, "f_coverage": 0.7872, "f_balanced": 0.8039, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 670, "chars": 2683, "content_recall": 0.9059, "noise_retention": 0.8704, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.493, "f_precision": 0.4122, "f_coverage": 0.4122, "f_balanced": 0.2268, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2445, "chars": 9782, "content_recall": 0.7765, "noise_retention": 0.1667, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.409, "f_precision": 0.7872, "f_coverage": 0.7872, "f_balanced": 0.8039, "anchor_diag": { "content_chars": 1523, "noise_chars": 1347, "content_ngrams": 170, "noise_ngrams": 108, "ambiguous_ngrams_removed": 23, "content_sentences": 17 }, "notes": "" } }, "scoreable": true }, "argocd-docs": { "meta": { "id": "argocd-docs", "url": "https://argo-cd.readthedocs.io/en/stable/", "requested_url": "https://argo-cd.readthedocs.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 76825 } }, "anchors": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 973, "chars": 3894, "content_recall": 0.7772, "noise_retention": 0.0038, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.813, "f_coverage": 0.813, "f_balanced": 0.8732, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1014, "chars": 4058, "content_recall": 0.8354, "noise_retention": 0.0038, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8632, "f_coverage": 0.8632, "f_balanced": 0.9087, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 863, "chars": 3455, "content_recall": 0.6368, "noise_retention": 0.0038, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6863, "f_coverage": 0.6863, "f_balanced": 0.7769, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 940, "chars": 3762, "content_recall": 0.8838, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9048, "f_coverage": 0.9048, "f_balanced": 0.9383, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" }, "readability": { "method": "readability", "tokens": 923, "chars": 3695, "content_recall": 0.8838, "noise_retention": 0.0038, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9042, "f_coverage": 0.9042, "f_balanced": 0.9366, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5096, "chars": 20385, "content_recall": 0.8281, "noise_retention": 0.1469, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.833, "f_coverage": 0.833, "f_balanced": 0.8404, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5180, "chars": 20720, "content_recall": 0.8281, "noise_retention": 0.1469, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.833, "f_coverage": 0.833, "f_balanced": 0.8404, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2162, "chars": 8649, "content_recall": 0.8838, "noise_retention": 0.8473, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4514, "f_coverage": 0.4514, "f_balanced": 0.2604, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5113, "chars": 20453, "content_recall": 0.8281, "noise_retention": 0.1469, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.833, "f_coverage": 0.833, "f_balanced": 0.8404, "anchor_diag": { "content_chars": 3728, "noise_chars": 7511, "content_ngrams": 413, "noise_ngrams": 524, "ambiguous_ngrams_removed": 13, "content_sentences": 39 }, "notes": "" } }, "scoreable": true }, "arxiv-abs-htmlrag": { "meta": { "id": "arxiv-abs-htmlrag", "url": "https://arxiv.org/abs/2411.02959", "requested_url": "https://arxiv.org/abs/2411.02959", "category": "article", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 44569 } }, "anchors": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1132, "chars": 4531, "content_recall": 0.6321, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6823, "f_coverage": 0.6823, "f_balanced": 0.7746, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1132, "chars": 4531, "content_recall": 0.6321, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6823, "f_coverage": 0.6823, "f_balanced": 0.7746, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1010, "chars": 4042, "content_recall": 0.4922, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5479, "f_coverage": 0.5479, "f_balanced": 0.6597, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 831, "chars": 3327, "content_recall": 0.4974, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.553, "f_coverage": 0.553, "f_balanced": 0.6644, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "readability": { "method": "readability", "tokens": 454, "chars": 1816, "content_recall": 0.0725, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0891, "f_coverage": 0.0891, "f_balanced": 0.1353, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2239, "chars": 8956, "content_recall": 0.6788, "noise_retention": 0.1154, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.34, "f_precision": 0.7119, "f_coverage": 0.7119, "f_balanced": 0.7681, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2230, "chars": 8920, "content_recall": 0.6788, "noise_retention": 0.1154, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.345, "f_precision": 0.7119, "f_coverage": 0.7119, "f_balanced": 0.7681, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1287, "chars": 5149, "content_recall": 0.7098, "noise_retention": 0.4615, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.777, "f_precision": 0.6674, "f_coverage": 0.6674, "f_balanced": 0.6124, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2210, "chars": 8842, "content_recall": 0.6788, "noise_retention": 0.1154, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.905, "f_precision": 0.7119, "f_coverage": 0.7119, "f_balanced": 0.7681, "anchor_diag": { "content_chars": 1668, "noise_chars": 1035, "content_ngrams": 193, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" } }, "scoreable": true }, "arxiv-html-htmlrag": { "meta": { "id": "arxiv-html-htmlrag", "url": "https://arxiv.org/html/2411.02959", "requested_url": "https://arxiv.org/html/2411.02959", "category": "article", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 354982 } }, "anchors": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 22950, "chars": 91800, "content_recall": 0.8925, "noise_retention": 0.1082, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8924, "f_coverage": 0.8924, "f_balanced": 0.8922, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 22958, "chars": 91832, "content_recall": 0.8926, "noise_retention": 0.1082, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8925, "f_coverage": 0.8925, "f_balanced": 0.8922, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 21699, "chars": 86797, "content_recall": 0.8689, "noise_retention": 0.1082, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8734, "f_coverage": 0.8734, "f_balanced": 0.8802, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 20564, "chars": 82257, "content_recall": 0.9237, "noise_retention": 0.0131, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9357, "f_coverage": 0.9357, "f_balanced": 0.9542, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2618, "chars": 10475, "content_recall": 0.1219, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1479, "f_coverage": 0.1479, "f_balanced": 0.2173, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 27415, "chars": 109661, "content_recall": 0.9252, "noise_retention": 0.4262, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.073, "f_precision": 0.8242, "f_coverage": 0.8242, "f_balanced": 0.7083, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 24461, "chars": 97844, "content_recall": 0.9682, "noise_retention": 0.7082, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.082, "f_precision": 0.6615, "f_coverage": 0.6615, "f_balanced": 0.4485, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 23627, "chars": 94510, "content_recall": 0.9846, "noise_retention": 0.859, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.042, "f_precision": 0.4482, "f_coverage": 0.4482, "f_balanced": 0.2467, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 27142, "chars": 108569, "content_recall": 0.9254, "noise_retention": 0.4295, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.074, "f_precision": 0.823, "f_coverage": 0.823, "f_balanced": 0.7059, "anchor_diag": { "content_chars": 84656, "noise_chars": 4110, "content_ngrams": 9695, "noise_ngrams": 305, "ambiguous_ngrams_removed": 4, "content_sentences": 630 }, "notes": "" } }, "scoreable": true }, "aspnet-core": { "meta": { "id": "aspnet-core", "url": "https://learn.microsoft.com/en-us/aspnet/core/?view=aspnetcore-10.0", "requested_url": "https://learn.microsoft.com/en-us/aspnet/core/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 74296 } }, "anchors": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 511, "chars": 2047, "content_recall": 0.1809, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2164, "f_coverage": 0.2164, "f_balanced": 0.3064, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 546, "chars": 2184, "content_recall": 0.2094, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2487, "f_coverage": 0.2487, "f_balanced": 0.3463, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 460, "chars": 1843, "content_recall": 0.1595, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1918, "f_coverage": 0.1918, "f_balanced": 0.2752, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 384, "chars": 1538, "content_recall": 0.2009, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2391, "f_coverage": 0.2391, "f_balanced": 0.3345, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "readability": { "method": "readability", "tokens": 62, "chars": 248, "content_recall": 0.0342, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0424, "f_coverage": 0.0424, "f_balanced": 0.0661, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3067, "chars": 12268, "content_recall": 0.4444, "noise_retention": 0.449, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4623, "f_coverage": 0.4623, "f_balanced": 0.492, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3160, "chars": 12640, "content_recall": 0.4444, "noise_retention": 0.5102, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4528, "f_coverage": 0.4528, "f_balanced": 0.466, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1211, "chars": 4847, "content_recall": 0.8134, "noise_retention": 0.9184, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2912, "f_coverage": 0.2912, "f_balanced": 0.1484, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3049, "chars": 12196, "content_recall": 0.4444, "noise_retention": 0.449, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4623, "f_coverage": 0.4623, "f_balanced": 0.492, "anchor_diag": { "content_chars": 7039, "noise_chars": 422, "content_ngrams": 702, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" } }, "scoreable": true }, "atlassian-confluence": { "meta": { "id": "atlassian-confluence", "url": "https://support.atlassian.com/confluence-cloud/", "requested_url": "https://support.atlassian.com/confluence-cloud/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 92294 } }, "anchors": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 56, "chars": 224, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 56, "chars": 224, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 56, "chars": 224, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 57, "chars": 228, "content_recall": 0.1587, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1908, "f_coverage": 0.1908, "f_balanced": 0.274, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "readability": { "method": "readability", "tokens": 40, "chars": 160, "content_recall": 0.0635, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0781, "f_coverage": 0.0781, "f_balanced": 0.1194, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 797, "chars": 3188, "content_recall": 0.5397, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.255, "f_precision": 0.5944, "f_coverage": 0.5944, "f_balanced": 0.701, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 777, "chars": 3111, "content_recall": 0.3016, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.287, "f_precision": 0.3506, "f_coverage": 0.3506, "f_balanced": 0.4634, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 264, "chars": 1059, "content_recall": 0.5397, "noise_retention": 0.4138, "noise_keyword_total": 1, "noise_per_1k_tokens": 3.788, "f_precision": 0.5484, "f_coverage": 0.5484, "f_balanced": 0.562, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 780, "chars": 3120, "content_recall": 0.5397, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.282, "f_precision": 0.5944, "f_coverage": 0.5944, "f_balanced": 0.701, "anchor_diag": { "content_chars": 1133, "noise_chars": 276, "content_ngrams": 126, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" } }, "scoreable": true }, "atlassian-jira": { "meta": { "id": "atlassian-jira", "url": "https://support.atlassian.com/jira-software-cloud/", "requested_url": "https://support.atlassian.com/jira-software-cloud/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 91431 } }, "anchors": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 53, "chars": 212, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 53, "chars": 212, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 53, "chars": 212, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 57, "chars": 228, "content_recall": 0.1587, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1908, "f_coverage": 0.1908, "f_balanced": 0.274, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "readability": { "method": "readability", "tokens": 37, "chars": 148, "content_recall": 0.0635, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0781, "f_coverage": 0.0781, "f_balanced": 0.1194, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 796, "chars": 3187, "content_recall": 0.5397, "noise_retention": 0.0323, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.256, "f_precision": 0.5921, "f_coverage": 0.5921, "f_balanced": 0.6929, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 780, "chars": 3122, "content_recall": 0.3016, "noise_retention": 0.0323, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.282, "f_precision": 0.3497, "f_coverage": 0.3497, "f_balanced": 0.4599, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 261, "chars": 1044, "content_recall": 0.5397, "noise_retention": 0.4194, "noise_keyword_total": 1, "noise_per_1k_tokens": 3.831, "f_precision": 0.5474, "f_coverage": 0.5474, "f_balanced": 0.5594, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 782, "chars": 3131, "content_recall": 0.5397, "noise_retention": 0.0323, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.279, "f_precision": 0.5921, "f_coverage": 0.5921, "f_balanced": 0.6929, "anchor_diag": { "content_chars": 1133, "noise_chars": 279, "content_ngrams": 126, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" } }, "scoreable": true }, "auth0-docs": { "meta": { "id": "auth0-docs", "url": "https://auth0.com/docs", "requested_url": "https://auth0.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 2721508 } }, "anchors": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 178, "chars": 713, "content_recall": 0.4146, "noise_retention": 0.075, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4661, "f_coverage": 0.4661, "f_balanced": 0.5726, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 178, "chars": 713, "content_recall": 0.4146, "noise_retention": 0.075, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4661, "f_coverage": 0.4661, "f_balanced": 0.5726, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 167, "chars": 669, "content_recall": 0.3659, "noise_retention": 0.075, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4162, "f_coverage": 0.4162, "f_balanced": 0.5243, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 129, "chars": 519, "content_recall": 0.4146, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4696, "f_coverage": 0.4696, "f_balanced": 0.5862, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "readability": { "method": "readability", "tokens": 147, "chars": 589, "content_recall": 0.4146, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4696, "f_coverage": 0.4696, "f_balanced": 0.5862, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 901, "chars": 3605, "content_recall": 0.439, "noise_retention": 0.1375, "noise_keyword_total": 4, "noise_per_1k_tokens": 4.44, "f_precision": 0.4868, "f_coverage": 0.4868, "f_balanced": 0.5819, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 879, "chars": 3518, "content_recall": 0.439, "noise_retention": 0.1375, "noise_keyword_total": 4, "noise_per_1k_tokens": 4.551, "f_precision": 0.4868, "f_coverage": 0.4868, "f_balanced": 0.5819, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 353, "chars": 1415, "content_recall": 0.6098, "noise_retention": 0.925, "noise_keyword_total": 2, "noise_per_1k_tokens": 5.666, "f_precision": 0.2513, "f_coverage": 0.2513, "f_balanced": 0.1336, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 891, "chars": 3566, "content_recall": 0.439, "noise_retention": 0.1375, "noise_keyword_total": 4, "noise_per_1k_tokens": 4.489, "f_precision": 0.4868, "f_coverage": 0.4868, "f_balanced": 0.5819, "anchor_diag": { "content_chars": 340, "noise_chars": 623, "content_ngrams": 41, "noise_ngrams": 80, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" } }, "scoreable": false }, "avro-docs": { "meta": { "id": "avro-docs", "url": "https://avro.apache.org/docs/", "requested_url": "https://avro.apache.org/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 48117 } }, "anchors": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 818, "chars": 3272, "content_recall": 0.9249, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.939, "f_coverage": 0.939, "f_balanced": 0.961, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 835, "chars": 3342, "content_recall": 0.9249, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.939, "f_coverage": 0.939, "f_balanced": 0.961, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 775, "chars": 3102, "content_recall": 0.9249, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.939, "f_coverage": 0.939, "f_balanced": 0.961, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 592, "chars": 2369, "content_recall": 0.9113, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9277, "f_coverage": 0.9277, "f_balanced": 0.9536, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 606, "chars": 2426, "content_recall": 0.9113, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9277, "f_coverage": 0.9277, "f_balanced": 0.9536, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2749, "chars": 10996, "content_recall": 0.9044, "noise_retention": 0.2301, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8739, "f_coverage": 0.8739, "f_balanced": 0.8318, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2905, "chars": 11623, "content_recall": 0.9044, "noise_retention": 0.2389, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8716, "f_coverage": 0.8716, "f_balanced": 0.8266, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1085, "chars": 4343, "content_recall": 0.9454, "noise_retention": 0.8938, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3664, "f_coverage": 0.3664, "f_balanced": 0.1909, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2951, "chars": 11806, "content_recall": 0.9044, "noise_retention": 0.2212, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8762, "f_coverage": 0.8762, "f_balanced": 0.8369, "anchor_diag": { "content_chars": 2395, "noise_chars": 3025, "content_ngrams": 293, "noise_ngrams": 113, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "awesome-python": { "meta": { "id": "awesome-python", "url": "https://github.com/vinta/awesome-python", "requested_url": "https://github.com/vinta/awesome-python", "category": "hub", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": true, "bytes": 668349 } }, "anchors": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 11507, "chars": 46028, "content_recall": 0.8101, "noise_retention": 0.0, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.261, "f_precision": 0.8421, "f_coverage": 0.8421, "f_balanced": 0.8951, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 11913, "chars": 47654, "content_recall": 0.8497, "noise_retention": 0.0, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.252, "f_precision": 0.876, "f_coverage": 0.876, "f_balanced": 0.9187, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 10624, "chars": 42499, "content_recall": 0.722, "noise_retention": 0.0, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.282, "f_precision": 0.7645, "f_coverage": 0.7645, "f_balanced": 0.8385, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 10518, "chars": 42073, "content_recall": 0.7775, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.19, "f_precision": 0.8137, "f_coverage": 0.8137, "f_balanced": 0.8748, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" }, "readability": { "method": "readability", "tokens": 11004, "chars": 44017, "content_recall": 0.8704, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.182, "f_precision": 0.8936, "f_coverage": 0.8936, "f_balanced": 0.9307, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 21404, "chars": 85617, "content_recall": 0.606, "noise_retention": 0.063, "noise_keyword_total": 9, "noise_per_1k_tokens": 0.42, "f_precision": 0.652, "f_coverage": 0.652, "f_balanced": 0.736, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 21600, "chars": 86403, "content_recall": 0.605, "noise_retention": 0.0591, "noise_keyword_total": 9, "noise_per_1k_tokens": 0.417, "f_precision": 0.6515, "f_coverage": 0.6515, "f_balanced": 0.7364, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 12675, "chars": 50702, "content_recall": 0.8597, "noise_retention": 0.9213, "noise_keyword_total": 6, "noise_per_1k_tokens": 0.473, "f_precision": 0.2881, "f_coverage": 0.2881, "f_balanced": 0.1443, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 21359, "chars": 85438, "content_recall": 0.606, "noise_retention": 0.063, "noise_keyword_total": 9, "noise_per_1k_tokens": 0.421, "f_precision": 0.652, "f_coverage": 0.652, "f_balanced": 0.736, "anchor_diag": { "content_chars": 71465, "noise_chars": 3718, "content_ngrams": 6035, "noise_ngrams": 254, "ambiguous_ngrams_removed": 0, "content_sentences": 865 }, "notes": "" } }, "scoreable": true }, "awesome-selfhosted": { "meta": { "id": "awesome-selfhosted", "url": "https://github.com/awesome-selfhosted/awesome-selfhosted", "requested_url": "https://github.com/awesome-selfhosted/awesome-selfhosted", "category": "hub", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": true, "bytes": 249627 } }, "anchors": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 341, "chars": 1366, "content_recall": 0.531, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5859, "f_coverage": 0.5859, "f_balanced": 0.6936, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 341, "chars": 1366, "content_recall": 0.531, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5859, "f_coverage": 0.5859, "f_balanced": 0.6936, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 321, "chars": 1286, "content_recall": 0.3982, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4527, "f_coverage": 0.4527, "f_balanced": 0.5696, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 99, "chars": 397, "content_recall": 0.0885, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1082, "f_coverage": 0.1082, "f_balanced": 0.1626, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "readability": { "method": "readability", "tokens": 40, "chars": 163, "content_recall": 0.0885, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1082, "f_coverage": 0.1082, "f_balanced": 0.1626, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2333, "chars": 9332, "content_recall": 0.4956, "noise_retention": 0.0522, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.857, "f_precision": 0.5479, "f_coverage": 0.5479, "f_balanced": 0.6508, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2377, "chars": 9511, "content_recall": 0.5044, "noise_retention": 0.0482, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.841, "f_precision": 0.5568, "f_coverage": 0.5568, "f_balanced": 0.6594, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 815, "chars": 3261, "content_recall": 0.8761, "noise_retention": 0.9197, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.454, "f_precision": 0.2938, "f_coverage": 0.2938, "f_balanced": 0.1472, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2282, "chars": 9130, "content_recall": 0.4956, "noise_retention": 0.0522, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.876, "f_precision": 0.5479, "f_coverage": 0.5479, "f_balanced": 0.6508, "anchor_diag": { "content_chars": 1028, "noise_chars": 3659, "content_ngrams": 113, "noise_ngrams": 249, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" } }, "scoreable": true }, "aws-bedrock": { "meta": { "id": "aws-bedrock", "url": "https://aws.amazon.com/bedrock/", "requested_url": "https://aws.amazon.com/bedrock/", "category": "cloud", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 429549 } }, "anchors": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1806, "chars": 7224, "content_recall": 0.8747, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8972, "f_coverage": 0.8972, "f_balanced": 0.9332, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1814, "chars": 7258, "content_recall": 0.8759, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8982, "f_coverage": 0.8982, "f_balanced": 0.9339, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1781, "chars": 7127, "content_recall": 0.8587, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8837, "f_coverage": 0.8837, "f_balanced": 0.924, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1570, "chars": 6283, "content_recall": 0.8342, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8628, "f_coverage": 0.8628, "f_balanced": 0.9096, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1671, "chars": 6685, "content_recall": 0.828, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8575, "f_coverage": 0.8575, "f_balanced": 0.9059, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5939, "chars": 23758, "content_recall": 0.8477, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.168, "f_precision": 0.8203, "f_coverage": 0.8203, "f_balanced": 0.7825, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6003, "chars": 24014, "content_recall": 0.8477, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.167, "f_precision": 0.8203, "f_coverage": 0.8203, "f_balanced": 0.7825, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3593, "chars": 14375, "content_recall": 0.8845, "noise_retention": 0.9062, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.278, "f_precision": 0.3292, "f_coverage": 0.3292, "f_balanced": 0.1695, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5916, "chars": 23665, "content_recall": 0.8477, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.169, "f_precision": 0.8203, "f_coverage": 0.8203, "f_balanced": 0.7825, "anchor_diag": { "content_chars": 6678, "noise_chars": 1022, "content_ngrams": 814, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 47 }, "notes": "" } }, "scoreable": true }, "aws-ec2-home": { "meta": { "id": "aws-ec2-home", "url": "https://aws.amazon.com/ec2/", "requested_url": "https://aws.amazon.com/ec2/", "category": "cloud", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 447711 } }, "anchors": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 995, "chars": 3981, "content_recall": 0.5029, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5584, "f_coverage": 0.5584, "f_balanced": 0.6693, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1004, "chars": 4019, "content_recall": 0.5132, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5685, "f_coverage": 0.5685, "f_balanced": 0.6783, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 995, "chars": 3981, "content_recall": 0.5029, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5584, "f_coverage": 0.5584, "f_balanced": 0.6693, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1200, "chars": 4801, "content_recall": 0.5994, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6516, "f_coverage": 0.6516, "f_balanced": 0.7495, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "readability": { "method": "readability", "tokens": 99, "chars": 397, "content_recall": 0.057, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0703, "f_coverage": 0.0703, "f_balanced": 0.1079, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 6295, "chars": 25181, "content_recall": 0.7953, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.159, "f_precision": 0.7805, "f_coverage": 0.7805, "f_balanced": 0.7594, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6360, "chars": 25441, "content_recall": 0.7953, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.157, "f_precision": 0.7805, "f_coverage": 0.7805, "f_balanced": 0.7594, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3440, "chars": 13763, "content_recall": 0.8553, "noise_retention": 0.9062, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.291, "f_precision": 0.3259, "f_coverage": 0.3259, "f_balanced": 0.169, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 6273, "chars": 25095, "content_recall": 0.7953, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.159, "f_precision": 0.7805, "f_coverage": 0.7805, "f_balanced": 0.7594, "anchor_diag": { "content_chars": 6328, "noise_chars": 997, "content_ngrams": 684, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" } }, "scoreable": true }, "aws-ec2-instance-types": { "meta": { "id": "aws-ec2-instance-types", "url": "https://aws.amazon.com/ec2/instance-types/", "requested_url": "https://aws.amazon.com/ec2/instance-types/", "category": "cloud", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 426618 } }, "anchors": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 697, "chars": 2790, "content_recall": 0.8305, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8596, "f_coverage": 0.8596, "f_balanced": 0.9074, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 697, "chars": 2790, "content_recall": 0.8305, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8596, "f_coverage": 0.8596, "f_balanced": 0.9074, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 665, "chars": 2660, "content_recall": 0.7062, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7503, "f_coverage": 0.7503, "f_balanced": 0.8278, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 67, "chars": 271, "content_recall": 0.065, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0799, "f_coverage": 0.0799, "f_balanced": 0.122, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" }, "readability": { "method": "readability", "tokens": 91, "chars": 366, "content_recall": 0.1158, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1407, "f_coverage": 0.1407, "f_balanced": 0.2076, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4394, "chars": 17579, "content_recall": 0.7514, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.228, "f_precision": 0.7463, "f_coverage": 0.7463, "f_balanced": 0.7388, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4471, "chars": 17887, "content_recall": 0.678, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.224, "f_precision": 0.6872, "f_coverage": 0.6872, "f_balanced": 0.7014, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2516, "chars": 10066, "content_recall": 0.8559, "noise_retention": 0.9062, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.397, "f_precision": 0.3259, "f_coverage": 0.3259, "f_balanced": 0.169, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4387, "chars": 17550, "content_recall": 0.7514, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.228, "f_precision": 0.7463, "f_coverage": 0.7463, "f_balanced": 0.7388, "anchor_diag": { "content_chars": 4246, "noise_chars": 1003, "content_ngrams": 354, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 40 }, "notes": "" } }, "scoreable": true }, "aws-ec2-pricing": { "meta": { "id": "aws-ec2-pricing", "url": "https://aws.amazon.com/ec2/pricing/on-demand/", "requested_url": "https://aws.amazon.com/ec2/pricing/on-demand/", "category": "pricing", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 367082 } }, "anchors": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2273, "chars": 9095, "content_recall": 0.9429, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.88, "f_precision": 0.9538, "f_coverage": 0.9538, "f_balanced": 0.9706, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2273, "chars": 9095, "content_recall": 0.9429, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.88, "f_precision": 0.9538, "f_coverage": 0.9538, "f_balanced": 0.9706, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2135, "chars": 8542, "content_recall": 0.8956, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.937, "f_precision": 0.9147, "f_coverage": 0.9147, "f_balanced": 0.9449, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2214, "chars": 8856, "content_recall": 0.9376, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9494, "f_coverage": 0.9494, "f_balanced": 0.9678, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2175, "chars": 8703, "content_recall": 0.9197, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.46, "f_precision": 0.9347, "f_coverage": 0.9347, "f_balanced": 0.9582, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 6250, "chars": 25002, "content_recall": 0.8769, "noise_retention": 0.2734, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.64, "f_precision": 0.842, "f_coverage": 0.842, "f_balanced": 0.7947, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6311, "chars": 25246, "content_recall": 0.8769, "noise_retention": 0.2734, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.634, "f_precision": 0.842, "f_coverage": 0.842, "f_balanced": 0.7947, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4097, "chars": 16391, "content_recall": 0.9474, "noise_retention": 0.9062, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.732, "f_precision": 0.3358, "f_coverage": 0.3358, "f_balanced": 0.1706, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 6237, "chars": 24951, "content_recall": 0.8769, "noise_retention": 0.2734, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.641, "f_precision": 0.842, "f_coverage": 0.842, "f_balanced": 0.7947, "anchor_diag": { "content_chars": 8669, "noise_chars": 1006, "content_ngrams": 1121, "noise_ngrams": 128, "ambiguous_ngrams_removed": 1, "content_sentences": 79 }, "notes": "" } }, "scoreable": true }, "aws-eks": { "meta": { "id": "aws-eks", "url": "https://aws.amazon.com/eks/", "requested_url": "https://aws.amazon.com/eks/", "category": "cloud", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 383096 } }, "anchors": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 450, "chars": 1800, "content_recall": 0.4362, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4917, "f_coverage": 0.4917, "f_balanced": 0.6075, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 450, "chars": 1800, "content_recall": 0.4362, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4917, "f_coverage": 0.4917, "f_balanced": 0.6075, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 450, "chars": 1800, "content_recall": 0.4362, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4917, "f_coverage": 0.4917, "f_balanced": 0.6075, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 682, "chars": 2728, "content_recall": 0.727, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.769, "f_coverage": 0.769, "f_balanced": 0.8419, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "readability": { "method": "readability", "tokens": 542, "chars": 2171, "content_recall": 0.5918, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6444, "f_coverage": 0.6444, "f_balanced": 0.7436, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4527, "chars": 18110, "content_recall": 0.8724, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.221, "f_precision": 0.8388, "f_coverage": 0.8388, "f_balanced": 0.7929, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4610, "chars": 18443, "content_recall": 0.8724, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.217, "f_precision": 0.8388, "f_coverage": 0.8388, "f_balanced": 0.7929, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2652, "chars": 10611, "content_recall": 0.9082, "noise_retention": 0.9062, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.377, "f_precision": 0.3318, "f_coverage": 0.3318, "f_balanced": 0.17, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4512, "chars": 18050, "content_recall": 0.8724, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.222, "f_precision": 0.8388, "f_coverage": 0.8388, "f_balanced": 0.7929, "anchor_diag": { "content_chars": 3375, "noise_chars": 1000, "content_ngrams": 392, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" } }, "scoreable": true }, "aws-lambda-home": { "meta": { "id": "aws-lambda-home", "url": "https://aws.amazon.com/lambda/", "requested_url": "https://aws.amazon.com/lambda/", "category": "cloud", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 428390 } }, "anchors": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1412, "chars": 5650, "content_recall": 0.812, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8437, "f_coverage": 0.8437, "f_balanced": 0.8962, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1422, "chars": 5688, "content_recall": 0.8248, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8547, "f_coverage": 0.8547, "f_balanced": 0.904, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1412, "chars": 5650, "content_recall": 0.812, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8437, "f_coverage": 0.8437, "f_balanced": 0.8962, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 809, "chars": 3238, "content_recall": 0.5256, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5807, "f_coverage": 0.5807, "f_balanced": 0.6891, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "readability": { "method": "readability", "tokens": 120, "chars": 480, "content_recall": 0.0755, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0926, "f_coverage": 0.0926, "f_balanced": 0.1404, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5451, "chars": 21806, "content_recall": 0.7949, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.183, "f_precision": 0.7802, "f_coverage": 0.7802, "f_balanced": 0.7592, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5485, "chars": 21941, "content_recall": 0.8063, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.182, "f_precision": 0.789, "f_coverage": 0.789, "f_balanced": 0.7643, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3173, "chars": 12694, "content_recall": 0.8604, "noise_retention": 0.9062, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.315, "f_precision": 0.3265, "f_coverage": 0.3265, "f_balanced": 0.1691, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5433, "chars": 21732, "content_recall": 0.7949, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.184, "f_precision": 0.7802, "f_coverage": 0.7802, "f_balanced": 0.7592, "anchor_diag": { "content_chars": 6392, "noise_chars": 997, "content_ngrams": 702, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 59 }, "notes": "" } }, "scoreable": true }, "aws-lambda-pricing": { "meta": { "id": "aws-lambda-pricing", "url": "https://aws.amazon.com/lambda/pricing/", "requested_url": "https://aws.amazon.com/lambda/pricing/", "category": "pricing", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": true, "bytes": 496604 } }, "anchors": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 12840, "chars": 51363, "content_recall": 0.9217, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9364, "f_coverage": 0.9364, "f_balanced": 0.9593, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 12870, "chars": 51481, "content_recall": 0.9251, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9392, "f_coverage": 0.9392, "f_balanced": 0.9611, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 12438, "chars": 49753, "content_recall": 0.8917, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9114, "f_coverage": 0.9114, "f_balanced": 0.9427, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 13491, "chars": 53965, "content_recall": 0.9113, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9278, "f_coverage": 0.9278, "f_balanced": 0.9536, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" }, "readability": { "method": "readability", "tokens": 12545, "chars": 50183, "content_recall": 0.8988, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9173, "f_coverage": 0.9173, "f_balanced": 0.9467, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 17885, "chars": 71542, "content_recall": 0.9353, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.056, "f_precision": 0.9476, "f_coverage": 0.9476, "f_balanced": 0.9666, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 17637, "chars": 70548, "content_recall": 0.9353, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.057, "f_precision": 0.9476, "f_coverage": 0.9476, "f_balanced": 0.9666, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 15027, "chars": 60111, "content_recall": 0.9468, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.067, "f_precision": 0.957, "f_coverage": 0.957, "f_balanced": 0.9727, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 17781, "chars": 71124, "content_recall": 0.9353, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.056, "f_precision": 0.9476, "f_coverage": 0.9476, "f_balanced": 0.9666, "anchor_diag": { "content_chars": 139847, "noise_chars": 996, "content_ngrams": 5660, "noise_ngrams": 4, "ambiguous_ngrams_removed": 124, "content_sentences": 864 }, "notes": "" } }, "scoreable": true }, "aws-rds": { "meta": { "id": "aws-rds", "url": "https://aws.amazon.com/rds/", "requested_url": "https://aws.amazon.com/rds/", "category": "cloud", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 424026 } }, "anchors": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1262, "chars": 5049, "content_recall": 0.7517, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.792, "f_precision": 0.7909, "f_coverage": 0.7909, "f_balanced": 0.8582, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1262, "chars": 5049, "content_recall": 0.7517, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.792, "f_precision": 0.7909, "f_coverage": 0.7909, "f_balanced": 0.8582, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1200, "chars": 4802, "content_recall": 0.7169, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.833, "f_precision": 0.7599, "f_coverage": 0.7599, "f_balanced": 0.8351, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 946, "chars": 3784, "content_recall": 0.6258, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6764, "f_coverage": 0.6764, "f_balanced": 0.7699, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "readability": { "method": "readability", "tokens": 191, "chars": 765, "content_recall": 0.1391, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.168, "f_coverage": 0.168, "f_balanced": 0.2442, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5429, "chars": 21717, "content_recall": 0.7517, "noise_retention": 0.2734, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.368, "f_precision": 0.7465, "f_coverage": 0.7465, "f_balanced": 0.7389, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5497, "chars": 21990, "content_recall": 0.7517, "noise_retention": 0.2734, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.364, "f_precision": 0.7465, "f_coverage": 0.7465, "f_balanced": 0.7389, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3115, "chars": 12460, "content_recall": 0.8543, "noise_retention": 0.9062, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.642, "f_precision": 0.3258, "f_coverage": 0.3258, "f_balanced": 0.169, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5412, "chars": 21648, "content_recall": 0.7517, "noise_retention": 0.2734, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.37, "f_precision": 0.7465, "f_coverage": 0.7465, "f_balanced": 0.7389, "anchor_diag": { "content_chars": 5041, "noise_chars": 999, "content_ngrams": 604, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" } }, "scoreable": true }, "aws-s3-docs": { "meta": { "id": "aws-s3-docs", "url": "https://docs.aws.amazon.com/AmazonS3/latest/userguide/Welcome.html", "requested_url": "https://docs.aws.amazon.com/AmazonS3/latest/userguide/Welcome.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 62278 } }, "anchors": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 8642, "chars": 34570, "content_recall": 0.9294, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.116, "f_precision": 0.9427, "f_coverage": 0.9427, "f_balanced": 0.9634, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 8705, "chars": 34823, "content_recall": 0.9351, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.115, "f_precision": 0.9474, "f_coverage": 0.9474, "f_balanced": 0.9665, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 8129, "chars": 32517, "content_recall": 0.8678, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.123, "f_precision": 0.8914, "f_coverage": 0.8914, "f_balanced": 0.9292, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 8661, "chars": 34644, "content_recall": 0.9129, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.115, "f_precision": 0.9291, "f_coverage": 0.9291, "f_balanced": 0.9545, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" }, "readability": { "method": "readability", "tokens": 8778, "chars": 35115, "content_recall": 0.9219, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.114, "f_precision": 0.9366, "f_coverage": 0.9366, "f_balanced": 0.9594, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 10399, "chars": 41599, "content_recall": 0.8852, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.096, "f_precision": 0.906, "f_coverage": 0.906, "f_balanced": 0.9391, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 10278, "chars": 41112, "content_recall": 0.8898, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.097, "f_precision": 0.9099, "f_coverage": 0.9099, "f_balanced": 0.9417, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 9095, "chars": 36383, "content_recall": 0.9371, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.11, "f_precision": 0.949, "f_coverage": 0.949, "f_balanced": 0.9675, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 10386, "chars": 41546, "content_recall": 0.8852, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.096, "f_precision": 0.906, "f_coverage": 0.906, "f_balanced": 0.9391, "anchor_diag": { "content_chars": 43157, "noise_chars": 0, "content_ngrams": 4547, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 370 }, "notes": "" } }, "scoreable": true }, "aws-sagemaker": { "meta": { "id": "aws-sagemaker", "url": "https://aws.amazon.com/sagemaker/", "requested_url": "https://aws.amazon.com/sagemaker/", "category": "cloud", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 452357 } }, "anchors": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1462, "chars": 5849, "content_recall": 0.5706, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6242, "f_coverage": 0.6242, "f_balanced": 0.7266, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1473, "chars": 5892, "content_recall": 0.5752, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6286, "f_coverage": 0.6286, "f_balanced": 0.7303, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1058, "chars": 4232, "content_recall": 0.3771, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4307, "f_coverage": 0.4307, "f_balanced": 0.5476, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1684, "chars": 6738, "content_recall": 0.7092, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.753, "f_coverage": 0.753, "f_balanced": 0.8298, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "readability": { "method": "readability", "tokens": 143, "chars": 575, "content_recall": 0.0569, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0701, "f_coverage": 0.0701, "f_balanced": 0.1076, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 6152, "chars": 24609, "content_recall": 0.8606, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.163, "f_precision": 0.8299, "f_coverage": 0.8299, "f_balanced": 0.7879, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6219, "chars": 24879, "content_recall": 0.8606, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.161, "f_precision": 0.8299, "f_coverage": 0.8299, "f_balanced": 0.7879, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3946, "chars": 15786, "content_recall": 0.9092, "noise_retention": 0.9062, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.253, "f_precision": 0.3319, "f_coverage": 0.3319, "f_balanced": 0.17, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 6130, "chars": 24520, "content_recall": 0.8606, "noise_retention": 0.2734, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.163, "f_precision": 0.8299, "f_coverage": 0.8299, "f_balanced": 0.7879, "anchor_diag": { "content_chars": 9384, "noise_chars": 1005, "content_ngrams": 1090, "noise_ngrams": 128, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" } }, "scoreable": true }, "azure-aks": { "meta": { "id": "azure-aks", "url": "https://learn.microsoft.com/en-us/azure/aks/what-is-aks", "requested_url": "https://learn.microsoft.com/en-us/azure/aks/what-is-aks", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": true, "bytes": 64922 } }, "anchors": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2926, "chars": 11707, "content_recall": 0.8232, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8534, "f_coverage": 0.8534, "f_balanced": 0.903, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2926, "chars": 11707, "content_recall": 0.8232, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8534, "f_coverage": 0.8534, "f_balanced": 0.903, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2822, "chars": 11290, "content_recall": 0.7934, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8276, "f_coverage": 0.8276, "f_balanced": 0.8848, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2643, "chars": 10574, "content_recall": 0.878, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9, "f_coverage": 0.9, "f_balanced": 0.935, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2223, "chars": 8892, "content_recall": 0.7784, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8145, "f_coverage": 0.8145, "f_balanced": 0.8754, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3944, "chars": 15777, "content_recall": 0.7602, "noise_retention": 0.5156, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6825, "f_coverage": 0.6825, "f_balanced": 0.5917, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3916, "chars": 15666, "content_recall": 0.7577, "noise_retention": 0.5625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6609, "f_coverage": 0.6609, "f_balanced": 0.5547, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2851, "chars": 11407, "content_recall": 0.9062, "noise_retention": 0.875, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4028, "f_coverage": 0.4028, "f_balanced": 0.2197, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3900, "chars": 15601, "content_recall": 0.7577, "noise_retention": 0.5156, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6808, "f_coverage": 0.6808, "f_balanced": 0.591, "anchor_diag": { "content_chars": 9949, "noise_chars": 629, "content_ngrams": 1205, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 97 }, "notes": "" } }, "scoreable": true }, "azure-architecture": { "meta": { "id": "azure-architecture", "url": "https://learn.microsoft.com/en-us/azure/architecture/browse/", "requested_url": "https://learn.microsoft.com/en-us/azure/architecture/browse/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 19905 } }, "anchors": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 140, "chars": 561, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 140, "chars": 561, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 140, "chars": 561, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 81, "chars": 325, "content_recall": 1.0, "noise_retention": 0.2653, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9326, "f_coverage": 0.9326, "f_balanced": 0.8471, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "readability": { "method": "readability", "tokens": 63, "chars": 254, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 394, "chars": 1577, "content_recall": 1.0, "noise_retention": 0.449, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8599, "f_coverage": 0.8599, "f_balanced": 0.7105, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 376, "chars": 1506, "content_recall": 1.0, "noise_retention": 0.5102, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8276, "f_coverage": 0.8276, "f_balanced": 0.6575, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 175, "chars": 700, "content_recall": 1.0, "noise_retention": 0.9184, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3077, "f_coverage": 0.3077, "f_balanced": 0.1509, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 368, "chars": 1472, "content_recall": 1.0, "noise_retention": 0.449, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8599, "f_coverage": 0.8599, "f_balanced": 0.7105, "anchor_diag": { "content_chars": 177, "noise_chars": 422, "content_ngrams": 17, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" } }, "scoreable": false }, "azure-blob": { "meta": { "id": "azure-blob", "url": "https://learn.microsoft.com/en-us/azure/storage/blobs/storage-blobs-overview", "requested_url": "https://learn.microsoft.com/en-us/azure/storage/blobs/storage-blobs-overview", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 50185 } }, "anchors": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 524, "chars": 2096, "content_recall": 0.6878, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7336, "f_coverage": 0.7336, "f_balanced": 0.815, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 557, "chars": 2230, "content_recall": 0.7376, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7784, "f_coverage": 0.7784, "f_balanced": 0.849, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 448, "chars": 1793, "content_recall": 0.5882, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.641, "f_coverage": 0.641, "f_balanced": 0.7407, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 435, "chars": 1741, "content_recall": 0.7738, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8104, "f_coverage": 0.8104, "f_balanced": 0.8724, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 451, "chars": 1805, "content_recall": 0.6968, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7418, "f_coverage": 0.7418, "f_balanced": 0.8213, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1155, "chars": 4622, "content_recall": 0.7511, "noise_retention": 0.5156, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6766, "f_coverage": 0.6766, "f_balanced": 0.589, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1141, "chars": 4566, "content_recall": 0.7511, "noise_retention": 0.5625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6569, "f_coverage": 0.6569, "f_balanced": 0.5529, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 741, "chars": 2966, "content_recall": 0.819, "noise_retention": 0.875, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3881, "f_coverage": 0.3881, "f_balanced": 0.2169, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1117, "chars": 4469, "content_recall": 0.7511, "noise_retention": 0.5156, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6766, "f_coverage": 0.6766, "f_balanced": 0.589, "anchor_diag": { "content_chars": 2003, "noise_chars": 629, "content_ngrams": 221, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "azure-blog": { "meta": { "id": "azure-blog", "url": "https://azure.microsoft.com/en-us/blog/", "requested_url": "https://azure.microsoft.com/en-us/blog/", "category": "article", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 371710 } }, "anchors": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1182, "chars": 4728, "content_recall": 0.6476, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6967, "f_coverage": 0.6967, "f_balanced": 0.7861, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1182, "chars": 4728, "content_recall": 0.6476, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6967, "f_coverage": 0.6967, "f_balanced": 0.7861, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1107, "chars": 4428, "content_recall": 0.592, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6446, "f_coverage": 0.6446, "f_balanced": 0.7437, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 557, "chars": 2229, "content_recall": 0.306, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3553, "f_coverage": 0.3553, "f_balanced": 0.4686, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" }, "readability": { "method": "readability", "tokens": 70, "chars": 280, "content_recall": 0.0325, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0402, "f_coverage": 0.0402, "f_balanced": 0.0629, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 10783, "chars": 43135, "content_recall": 0.592, "noise_retention": 0.4282, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.093, "f_precision": 0.5878, "f_coverage": 0.5878, "f_balanced": 0.5817, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 10837, "chars": 43348, "content_recall": 0.592, "noise_retention": 0.4282, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.092, "f_precision": 0.5878, "f_coverage": 0.5878, "f_balanced": 0.5817, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2725, "chars": 10903, "content_recall": 0.6924, "noise_retention": 1.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.367, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 10757, "chars": 43030, "content_recall": 0.592, "noise_retention": 0.4282, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.093, "f_precision": 0.5878, "f_coverage": 0.5878, "f_balanced": 0.5817, "anchor_diag": { "content_chars": 9923, "noise_chars": 2705, "content_ngrams": 647, "noise_ngrams": 355, "ambiguous_ngrams_removed": 0, "content_sentences": 83 }, "notes": "" } }, "scoreable": true }, "azure-functions": { "meta": { "id": "azure-functions", "url": "https://learn.microsoft.com/en-us/azure/azure-functions/functions-overview", "requested_url": "https://learn.microsoft.com/en-us/azure/azure-functions/functions-overview", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": true, "bytes": 52553 } }, "anchors": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 962, "chars": 3848, "content_recall": 0.6218, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6726, "f_coverage": 0.6726, "f_balanced": 0.7668, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1027, "chars": 4109, "content_recall": 0.7176, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7606, "f_coverage": 0.7606, "f_balanced": 0.8356, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 896, "chars": 3587, "content_recall": 0.5674, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6211, "f_coverage": 0.6211, "f_balanced": 0.724, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 830, "chars": 3322, "content_recall": 0.7642, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8021, "f_coverage": 0.8021, "f_balanced": 0.8664, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" }, "readability": { "method": "readability", "tokens": 20, "chars": 81, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1616, "chars": 6466, "content_recall": 0.7332, "noise_retention": 0.5156, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6649, "f_coverage": 0.6649, "f_balanced": 0.5833, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1592, "chars": 6369, "content_recall": 0.7332, "noise_retention": 0.5625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6459, "f_coverage": 0.6459, "f_balanced": 0.548, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1086, "chars": 4344, "content_recall": 0.7927, "noise_retention": 0.875, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3833, "f_coverage": 0.3833, "f_balanced": 0.2159, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1583, "chars": 6332, "content_recall": 0.7332, "noise_retention": 0.5156, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6649, "f_coverage": 0.6649, "f_balanced": 0.5833, "anchor_diag": { "content_chars": 3238, "noise_chars": 629, "content_ngrams": 386, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 35 }, "notes": "" } }, "scoreable": true }, "azure-overview": { "meta": { "id": "azure-overview", "url": "https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/overview", "requested_url": "https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/overview", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 65076 } }, "anchors": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 3449, "chars": 13796, "content_recall": 0.8697, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.893, "f_coverage": 0.893, "f_balanced": 0.9303, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 3532, "chars": 14131, "content_recall": 0.8944, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9137, "f_coverage": 0.9137, "f_balanced": 0.9443, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 3064, "chars": 12256, "content_recall": 0.7653, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.803, "f_coverage": 0.803, "f_balanced": 0.867, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 3316, "chars": 13267, "content_recall": 0.9087, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9256, "f_coverage": 0.9256, "f_balanced": 0.9522, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" }, "readability": { "method": "readability", "tokens": 3106, "chars": 12425, "content_recall": 0.8664, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8902, "f_coverage": 0.8902, "f_balanced": 0.9284, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4323, "chars": 17294, "content_recall": 0.8653, "noise_retention": 0.5156, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7477, "f_coverage": 0.7477, "f_balanced": 0.6211, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4292, "chars": 17169, "content_recall": 0.8659, "noise_retention": 0.5625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7241, "f_coverage": 0.7241, "f_balanced": 0.5813, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3570, "chars": 14281, "content_recall": 0.9203, "noise_retention": 0.875, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.405, "f_coverage": 0.405, "f_balanced": 0.2201, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4282, "chars": 17128, "content_recall": 0.8637, "noise_retention": 0.5156, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7467, "f_coverage": 0.7467, "f_balanced": 0.6207, "anchor_diag": { "content_chars": 18949, "noise_chars": 629, "content_ngrams": 1819, "noise_ngrams": 64, "ambiguous_ngrams_removed": 18, "content_sentences": 193 }, "notes": "" } }, "scoreable": true }, "azure-pricing": { "meta": { "id": "azure-pricing", "url": "https://azure.microsoft.com/en-us/pricing/", "requested_url": "https://azure.microsoft.com/en-us/pricing/", "category": "pricing", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 630271 } }, "anchors": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2398, "chars": 9592, "content_recall": 0.4129, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4678, "f_coverage": 0.4678, "f_balanced": 0.5845, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2468, "chars": 9872, "content_recall": 0.4285, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4837, "f_coverage": 0.4837, "f_balanced": 0.5999, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2164, "chars": 8657, "content_recall": 0.3649, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.418, "f_coverage": 0.418, "f_balanced": 0.5347, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1476, "chars": 5907, "content_recall": 0.2971, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3457, "f_coverage": 0.3457, "f_balanced": 0.4581, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" }, "readability": { "method": "readability", "tokens": 25, "chars": 102, "content_recall": 0.0021, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0026, "f_coverage": 0.0026, "f_balanced": 0.0042, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 19509, "chars": 78036, "content_recall": 0.6258, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.051, "f_precision": 0.6765, "f_coverage": 0.6765, "f_balanced": 0.7699, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 19556, "chars": 78224, "content_recall": 0.6305, "noise_retention": 0.5789, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.051, "f_precision": 0.5734, "f_coverage": 0.5734, "f_balanced": 0.5049, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 6743, "chars": 26974, "content_recall": 0.6578, "noise_retention": 1.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.148, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 19415, "chars": 77662, "content_recall": 0.6258, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.052, "f_precision": 0.6765, "f_coverage": 0.6765, "f_balanced": 0.7699, "anchor_diag": { "content_chars": 25721, "noise_chars": 189, "content_ngrams": 2376, "noise_ngrams": 19, "ambiguous_ngrams_removed": 0, "content_sentences": 281 }, "notes": "" } }, "scoreable": true }, "azure-vm-pricing": { "meta": { "id": "azure-vm-pricing", "url": "https://azure.microsoft.com/en-us/pricing/details/virtual-machines/linux/", "requested_url": "https://azure.microsoft.com/en-us/pricing/details/virtual-machines/linux/", "category": "pricing", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 468716 } }, "anchors": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2731, "chars": 10925, "content_recall": 0.6808, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7272, "f_coverage": 0.7272, "f_balanced": 0.8101, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2772, "chars": 11090, "content_recall": 0.6945, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7397, "f_coverage": 0.7397, "f_balanced": 0.8197, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2488, "chars": 9955, "content_recall": 0.6077, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6594, "f_coverage": 0.6594, "f_balanced": 0.756, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2609, "chars": 10438, "content_recall": 0.7464, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7863, "f_coverage": 0.7863, "f_balanced": 0.8548, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1282, "chars": 5131, "content_recall": 0.3787, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4324, "f_coverage": 0.4324, "f_balanced": 0.5493, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 23791, "chars": 95167, "content_recall": 0.8496, "noise_retention": 0.3578, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.168, "f_precision": 0.7981, "f_coverage": 0.7981, "f_balanced": 0.7315, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 23684, "chars": 94737, "content_recall": 0.8496, "noise_retention": 0.3284, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.169, "f_precision": 0.8068, "f_coverage": 0.8068, "f_balanced": 0.7502, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 11140, "chars": 44560, "content_recall": 0.8715, "noise_retention": 0.9216, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.359, "f_precision": 0.2884, "f_coverage": 0.2884, "f_balanced": 0.1439, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 23774, "chars": 95096, "content_recall": 0.8496, "noise_retention": 0.3578, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.168, "f_precision": 0.7981, "f_coverage": 0.7981, "f_balanced": 0.7315, "anchor_diag": { "content_chars": 16513, "noise_chars": 1750, "content_ngrams": 1463, "noise_ngrams": 204, "ambiguous_ngrams_removed": 8, "content_sentences": 150 }, "notes": "" } }, "scoreable": true }, "bazel-docs": { "meta": { "id": "bazel-docs", "url": "https://bazel.build/docs/bazel-and-cpp", "requested_url": "https://bazel.build/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 314589 } }, "anchors": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 556, "chars": 2226, "content_recall": 0.8401, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8679, "f_coverage": 0.8679, "f_balanced": 0.9131, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 562, "chars": 2249, "content_recall": 0.8401, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8679, "f_coverage": 0.8679, "f_balanced": 0.9131, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 509, "chars": 2039, "content_recall": 0.7585, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.797, "f_coverage": 0.797, "f_balanced": 0.8627, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 638, "chars": 2552, "content_recall": 0.7585, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.797, "f_coverage": 0.797, "f_balanced": 0.8627, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" }, "readability": { "method": "readability", "tokens": 619, "chars": 2478, "content_recall": 0.7619, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8, "f_coverage": 0.8, "f_balanced": 0.8649, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2504, "chars": 10016, "content_recall": 0.8265, "noise_retention": 0.1934, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.399, "f_precision": 0.8225, "f_coverage": 0.8225, "f_balanced": 0.8164, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2506, "chars": 10026, "content_recall": 0.8265, "noise_retention": 0.1934, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.399, "f_precision": 0.8225, "f_coverage": 0.8225, "f_balanced": 0.8164, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1401, "chars": 5605, "content_recall": 0.8571, "noise_retention": 0.9475, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.714, "f_precision": 0.2107, "f_coverage": 0.2107, "f_balanced": 0.0989, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2495, "chars": 9980, "content_recall": 0.8265, "noise_retention": 0.1934, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.401, "f_precision": 0.8225, "f_coverage": 0.8225, "f_balanced": 0.8164, "anchor_diag": { "content_chars": 2558, "noise_chars": 2484, "content_ngrams": 294, "noise_ngrams": 305, "ambiguous_ngrams_removed": 9, "content_sentences": 22 }, "notes": "" } }, "scoreable": true }, "beautifulsoup-docs": { "meta": { "id": "beautifulsoup-docs", "url": "https://www.crummy.com/software/BeautifulSoup/bs4/doc/", "requested_url": "https://www.crummy.com/software/BeautifulSoup/bs4/doc/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 381071 } }, "anchors": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 31904, "chars": 127616, "content_recall": 0.807, "noise_retention": 0.0034, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8389, "f_coverage": 0.8389, "f_balanced": 0.8918, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 32243, "chars": 128973, "content_recall": 0.8112, "noise_retention": 0.0034, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8425, "f_coverage": 0.8425, "f_balanced": 0.8944, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 25665, "chars": 102661, "content_recall": 0.6713, "noise_retention": 0.0034, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7181, "f_coverage": 0.7181, "f_balanced": 0.8022, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 26268, "chars": 105074, "content_recall": 0.7931, "noise_retention": 0.0068, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8264, "f_coverage": 0.8264, "f_balanced": 0.882, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" }, "readability": { "method": "readability", "tokens": 29272, "chars": 117090, "content_recall": 0.8989, "noise_retention": 0.0068, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9163, "f_coverage": 0.9163, "f_balanced": 0.9437, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 35103, "chars": 140413, "content_recall": 0.8688, "noise_retention": 0.5153, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.75, "f_coverage": 0.75, "f_balanced": 0.6223, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 33394, "chars": 133576, "content_recall": 0.9037, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 30493, "chars": 121975, "content_recall": 0.9111, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 35083, "chars": 140333, "content_recall": 0.8688, "noise_retention": 0.5153, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.75, "f_coverage": 0.75, "f_balanced": 0.6223, "anchor_diag": { "content_chars": 166758, "noise_chars": 2492, "content_ngrams": 13743, "noise_ngrams": 295, "ambiguous_ngrams_removed": 21, "content_sentences": 1438 }, "notes": "" } }, "scoreable": true }, "black-docs": { "meta": { "id": "black-docs", "url": "https://black.readthedocs.io/en/stable/", "requested_url": "https://black.readthedocs.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 44777 } }, "anchors": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 616, "chars": 2465, "content_recall": 0.368, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4212, "f_coverage": 0.4212, "f_balanced": 0.538, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 710, "chars": 2842, "content_recall": 0.368, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4212, "f_coverage": 0.4212, "f_balanced": 0.538, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 558, "chars": 2234, "content_recall": 0.3498, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4021, "f_coverage": 0.4021, "f_balanced": 0.5183, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 582, "chars": 2330, "content_recall": 0.4092, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4641, "f_coverage": 0.4641, "f_balanced": 0.5808, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" }, "readability": { "method": "readability", "tokens": 352, "chars": 1409, "content_recall": 0.2508, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.295, "f_coverage": 0.295, "f_balanced": 0.4011, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3840, "chars": 15361, "content_recall": 0.538, "noise_retention": 0.1383, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5817, "f_coverage": 0.5817, "f_balanced": 0.6624, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3847, "chars": 15391, "content_recall": 0.538, "noise_retention": 0.2128, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5743, "f_coverage": 0.5743, "f_balanced": 0.6391, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1519, "chars": 6078, "content_recall": 0.8482, "noise_retention": 0.9149, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3037, "f_coverage": 0.3037, "f_balanced": 0.1547, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3829, "chars": 15319, "content_recall": 0.538, "noise_retention": 0.1383, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5817, "f_coverage": 0.5817, "f_balanced": 0.6624, "anchor_diag": { "content_chars": 6288, "noise_chars": 843, "content_ngrams": 606, "noise_ngrams": 94, "ambiguous_ngrams_removed": 13, "content_sentences": 56 }, "notes": "" } }, "scoreable": true }, "bootstrap-docs": { "meta": { "id": "bootstrap-docs", "url": "https://getbootstrap.com/docs/", "requested_url": "https://getbootstrap.com/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 406 } }, "anchors": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 15, "chars": 63, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 15, "chars": 63, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 15, "chars": 63, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 5, "chars": 23, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2, "chars": 11, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1, "chars": 1, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2, "chars": 9, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2, "chars": 9, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "box-api": { "meta": { "id": "box-api", "url": "https://developer.box.com/", "requested_url": "https://developer.box.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 552383 } }, "anchors": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 731, "chars": 2926, "content_recall": 0.6557, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7042, "f_coverage": 0.7042, "f_balanced": 0.792, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 731, "chars": 2926, "content_recall": 0.6557, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7042, "f_coverage": 0.7042, "f_balanced": 0.792, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 689, "chars": 2757, "content_recall": 0.5788, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.632, "f_coverage": 0.632, "f_balanced": 0.7332, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 599, "chars": 2396, "content_recall": 0.6081, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6598, "f_coverage": 0.6598, "f_balanced": 0.7563, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "readability": { "method": "readability", "tokens": 543, "chars": 2175, "content_recall": 0.5824, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6355, "f_coverage": 0.6355, "f_balanced": 0.7361, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1902, "chars": 7609, "content_recall": 0.6703, "noise_retention": 0.4652, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.629, "f_precision": 0.638, "f_coverage": 0.638, "f_balanced": 0.5949, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1958, "chars": 7834, "content_recall": 0.663, "noise_retention": 0.4652, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.554, "f_precision": 0.6327, "f_coverage": 0.6327, "f_balanced": 0.592, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1092, "chars": 4371, "content_recall": 0.6703, "noise_retention": 0.9478, "noise_keyword_total": 4, "noise_per_1k_tokens": 3.663, "f_precision": 0.1989, "f_coverage": 0.1989, "f_balanced": 0.0968, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1897, "chars": 7589, "content_recall": 0.6703, "noise_retention": 0.4652, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.636, "f_precision": 0.638, "f_coverage": 0.638, "f_balanced": 0.5949, "anchor_diag": { "content_chars": 2054, "noise_chars": 1771, "content_ngrams": 273, "noise_ngrams": 230, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" } }, "scoreable": true }, "cdk-aws": { "meta": { "id": "cdk-aws", "url": "https://docs.aws.amazon.com/cdk/v2/guide/home.html", "requested_url": "https://docs.aws.amazon.com/cdk/v2/guide/home.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 39999 } }, "anchors": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 3134, "chars": 12538, "content_recall": 0.8786, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9004, "f_coverage": 0.9004, "f_balanced": 0.9354, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 3147, "chars": 12591, "content_recall": 0.8759, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8982, "f_coverage": 0.8982, "f_balanced": 0.9338, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2971, "chars": 11887, "content_recall": 0.8124, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8441, "f_coverage": 0.8441, "f_balanced": 0.8965, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2009, "chars": 8039, "content_recall": 0.588, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6408, "f_coverage": 0.6408, "f_balanced": 0.7405, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1573, "chars": 6293, "content_recall": 0.5123, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5676, "f_coverage": 0.5676, "f_balanced": 0.6775, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4681, "chars": 18724, "content_recall": 0.8131, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8447, "f_coverage": 0.8447, "f_balanced": 0.8969, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4730, "chars": 18923, "content_recall": 0.8131, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8447, "f_coverage": 0.8447, "f_balanced": 0.8969, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3399, "chars": 13598, "content_recall": 0.897, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9159, "f_coverage": 0.9159, "f_balanced": 0.9457, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4665, "chars": 18660, "content_recall": 0.8131, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8447, "f_coverage": 0.8447, "f_balanced": 0.8969, "anchor_diag": { "content_chars": 16708, "noise_chars": 0, "content_ngrams": 1466, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 115 }, "notes": "" } }, "scoreable": true }, "celery-docs": { "meta": { "id": "celery-docs", "url": "https://docs.celeryq.dev/en/stable/", "requested_url": "https://docs.celeryq.dev/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 11648 } }, "anchors": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 321, "chars": 1285, "content_recall": 0.5083, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5637, "f_coverage": 0.5637, "f_balanced": 0.674, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 333, "chars": 1334, "content_recall": 0.547, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6015, "f_coverage": 0.6015, "f_balanced": 0.7071, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 276, "chars": 1107, "content_recall": 0.3757, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4293, "f_coverage": 0.4293, "f_balanced": 0.5462, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 240, "chars": 960, "content_recall": 0.6243, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.675, "f_coverage": 0.675, "f_balanced": 0.7687, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "readability": { "method": "readability", "tokens": 218, "chars": 874, "content_recall": 0.5304, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5854, "f_coverage": 0.5854, "f_balanced": 0.6931, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1054, "chars": 4218, "content_recall": 0.5083, "noise_retention": 0.2903, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5389, "f_coverage": 0.5389, "f_balanced": 0.5923, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1024, "chars": 4098, "content_recall": 0.5249, "noise_retention": 0.2903, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5537, "f_coverage": 0.5537, "f_balanced": 0.6034, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 496, "chars": 1986, "content_recall": 0.895, "noise_retention": 0.871, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4092, "f_coverage": 0.4092, "f_balanced": 0.2255, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1035, "chars": 4141, "content_recall": 0.5083, "noise_retention": 0.2903, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5389, "f_coverage": 0.5389, "f_balanced": 0.5923, "anchor_diag": { "content_chars": 1509, "noise_chars": 343, "content_ngrams": 181, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" } }, "scoreable": true }, "chef-docs": { "meta": { "id": "chef-docs", "url": "https://docs.chef.io/", "requested_url": "https://docs.chef.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 134652 } }, "anchors": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 471, "chars": 1885, "content_recall": 0.8741, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8967, "f_coverage": 0.8967, "f_balanced": 0.9328, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 479, "chars": 1918, "content_recall": 0.8741, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8967, "f_coverage": 0.8967, "f_balanced": 0.9328, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 459, "chars": 1838, "content_recall": 0.8671, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8908, "f_coverage": 0.8908, "f_balanced": 0.9288, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 276, "chars": 1107, "content_recall": 0.6993, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.744, "f_coverage": 0.744, "f_balanced": 0.823, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "readability": { "method": "readability", "tokens": 76, "chars": 304, "content_recall": 0.1259, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1525, "f_coverage": 0.1525, "f_balanced": 0.2236, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 25628, "chars": 102512, "content_recall": 0.6503, "noise_retention": 0.7528, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.117, "f_precision": 0.4904, "f_coverage": 0.4904, "f_balanced": 0.3582, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 26315, "chars": 105261, "content_recall": 0.6503, "noise_retention": 0.7528, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.114, "f_precision": 0.4904, "f_coverage": 0.4904, "f_balanced": 0.3582, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 7495, "chars": 29981, "content_recall": 0.6503, "noise_retention": 0.9101, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.267, "f_precision": 0.2894, "f_coverage": 0.2894, "f_balanced": 0.1579, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 25623, "chars": 102494, "content_recall": 0.6503, "noise_retention": 0.7528, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.117, "f_precision": 0.4904, "f_coverage": 0.4904, "f_balanced": 0.3582, "anchor_diag": { "content_chars": 1206, "noise_chars": 1407, "content_ngrams": 143, "noise_ngrams": 89, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" } }, "scoreable": true }, "cloudflare-d1": { "meta": { "id": "cloudflare-d1", "url": "https://developers.cloudflare.com/d1/", "requested_url": "https://developers.cloudflare.com/d1/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 123835 } }, "anchors": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 536, "chars": 2144, "content_recall": 0.6759, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7227, "f_coverage": 0.7227, "f_balanced": 0.8066, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 615, "chars": 2461, "content_recall": 0.7172, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7602, "f_coverage": 0.7602, "f_balanced": 0.8353, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 421, "chars": 1687, "content_recall": 0.4621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5178, "f_coverage": 0.5178, "f_balanced": 0.6321, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 477, "chars": 1911, "content_recall": 0.8276, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8571, "f_coverage": 0.8571, "f_balanced": 0.9057, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" }, "readability": { "method": "readability", "tokens": 463, "chars": 1854, "content_recall": 0.6724, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7196, "f_coverage": 0.7196, "f_balanced": 0.8041, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2446, "chars": 9787, "content_recall": 0.6552, "noise_retention": 0.1214, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.453, "f_precision": 0.6903, "f_coverage": 0.6903, "f_balanced": 0.7506, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2473, "chars": 9894, "content_recall": 0.6552, "noise_retention": 0.1357, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.426, "f_precision": 0.6885, "f_coverage": 0.6885, "f_balanced": 0.7453, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1148, "chars": 4594, "content_recall": 0.7862, "noise_retention": 0.9071, "noise_keyword_total": 5, "noise_per_1k_tokens": 4.355, "f_precision": 0.3153, "f_coverage": 0.3153, "f_balanced": 0.1661, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2438, "chars": 9754, "content_recall": 0.6552, "noise_retention": 0.1214, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.461, "f_precision": 0.6903, "f_coverage": 0.6903, "f_balanced": 0.7506, "anchor_diag": { "content_chars": 2550, "noise_chars": 3279, "content_ngrams": 290, "noise_ngrams": 280, "ambiguous_ngrams_removed": 2, "content_sentences": 25 }, "notes": "" } }, "scoreable": true }, "cloudflare-home": { "meta": { "id": "cloudflare-home", "url": "https://www.cloudflare.com/", "requested_url": "https://www.cloudflare.com/", "category": "marketing", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 1324083 } }, "anchors": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1219, "chars": 4878, "content_recall": 0.5908, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6435, "f_coverage": 0.6435, "f_balanced": 0.7428, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1313, "chars": 5255, "content_recall": 0.6302, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6805, "f_coverage": 0.6805, "f_balanced": 0.7732, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 896, "chars": 3585, "content_recall": 0.5361, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5909, "f_coverage": 0.5909, "f_balanced": 0.698, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 644, "chars": 2578, "content_recall": 0.4814, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5371, "f_coverage": 0.5371, "f_balanced": 0.6499, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1085, "chars": 4342, "content_recall": 0.6893, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.735, "f_coverage": 0.735, "f_balanced": 0.8161, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3688, "chars": 14754, "content_recall": 0.6915, "noise_retention": 0.0583, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.813, "f_precision": 0.7303, "f_coverage": 0.7303, "f_balanced": 0.7974, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3685, "chars": 14740, "content_recall": 0.6915, "noise_retention": 0.0583, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.814, "f_precision": 0.7303, "f_coverage": 0.7303, "f_balanced": 0.7974, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1753, "chars": 7012, "content_recall": 0.7484, "noise_retention": 0.9, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.141, "f_precision": 0.3258, "f_coverage": 0.3258, "f_balanced": 0.1764, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3669, "chars": 14677, "content_recall": 0.6915, "noise_retention": 0.0583, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.818, "f_precision": 0.7303, "f_coverage": 0.7303, "f_balanced": 0.7974, "anchor_diag": { "content_chars": 4185, "noise_chars": 1099, "content_ngrams": 457, "noise_ngrams": 120, "ambiguous_ngrams_removed": 12, "content_sentences": 48 }, "notes": "" } }, "scoreable": true }, "cloudflare-pages": { "meta": { "id": "cloudflare-pages", "url": "https://developers.cloudflare.com/pages/", "requested_url": "https://developers.cloudflare.com/pages/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 132329 } }, "anchors": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 532, "chars": 2130, "content_recall": 0.7269, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7689, "f_coverage": 0.7689, "f_balanced": 0.8418, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 532, "chars": 2130, "content_recall": 0.7269, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7689, "f_coverage": 0.7689, "f_balanced": 0.8418, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 273, "chars": 1092, "content_recall": 0.2311, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2731, "f_coverage": 0.2731, "f_balanced": 0.3754, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 413, "chars": 1653, "content_recall": 0.8235, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8537, "f_coverage": 0.8537, "f_balanced": 0.9032, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 432, "chars": 1729, "content_recall": 0.7143, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7576, "f_coverage": 0.7576, "f_balanced": 0.8333, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3402, "chars": 13611, "content_recall": 0.6639, "noise_retention": 0.1875, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.764, "f_precision": 0.6891, "f_coverage": 0.6891, "f_balanced": 0.7307, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3460, "chars": 13842, "content_recall": 0.6639, "noise_retention": 0.1975, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.734, "f_precision": 0.6876, "f_coverage": 0.6876, "f_balanced": 0.7266, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1307, "chars": 5228, "content_recall": 0.7899, "noise_retention": 0.9425, "noise_keyword_total": 5, "noise_per_1k_tokens": 3.826, "f_precision": 0.2227, "f_coverage": 0.2227, "f_balanced": 0.1072, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3393, "chars": 13575, "content_recall": 0.6639, "noise_retention": 0.1875, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.768, "f_precision": 0.6891, "f_coverage": 0.6891, "f_balanced": 0.7307, "anchor_diag": { "content_chars": 2226, "noise_chars": 4979, "content_ngrams": 238, "noise_ngrams": 400, "ambiguous_ngrams_removed": 2, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "cloudflare-r2": { "meta": { "id": "cloudflare-r2", "url": "https://developers.cloudflare.com/r2/", "requested_url": "https://developers.cloudflare.com/r2/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 126633 } }, "anchors": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 521, "chars": 2084, "content_recall": 0.712, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7555, "f_coverage": 0.7555, "f_balanced": 0.8318, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 565, "chars": 2260, "content_recall": 0.764, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8018, "f_coverage": 0.8018, "f_balanced": 0.8662, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 267, "chars": 1069, "content_recall": 0.304, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3532, "f_coverage": 0.3532, "f_balanced": 0.4663, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 380, "chars": 1523, "content_recall": 0.684, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7301, "f_coverage": 0.7301, "f_balanced": 0.8124, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" }, "readability": { "method": "readability", "tokens": 483, "chars": 1933, "content_recall": 0.708, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7519, "f_coverage": 0.7519, "f_balanced": 0.829, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2750, "chars": 11000, "content_recall": 0.676, "noise_retention": 0.1261, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.182, "f_precision": 0.7081, "f_coverage": 0.7081, "f_balanced": 0.7623, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2797, "chars": 11189, "content_recall": 0.676, "noise_retention": 0.1381, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.145, "f_precision": 0.7065, "f_coverage": 0.7065, "f_balanced": 0.7577, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1210, "chars": 4840, "content_recall": 0.768, "noise_retention": 0.9429, "noise_keyword_total": 5, "noise_per_1k_tokens": 4.132, "f_precision": 0.2199, "f_coverage": 0.2199, "f_balanced": 0.1062, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2741, "chars": 10966, "content_recall": 0.676, "noise_retention": 0.1261, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.189, "f_precision": 0.7081, "f_coverage": 0.7081, "f_balanced": 0.7623, "anchor_diag": { "content_chars": 2074, "noise_chars": 4086, "content_ngrams": 250, "noise_ngrams": 333, "ambiguous_ngrams_removed": 2, "content_sentences": 19 }, "notes": "" } }, "scoreable": true }, "cloudflare-workers-get-started": { "meta": { "id": "cloudflare-workers-get-started", "url": "https://developers.cloudflare.com/workers/get-started/guide/", "requested_url": "https://developers.cloudflare.com/workers/get-started/guide/", "category": "api_docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 202986 } }, "anchors": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1723, "chars": 6894, "content_recall": 0.6783, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.725, "f_coverage": 0.725, "f_balanced": 0.8083, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1872, "chars": 7489, "content_recall": 0.751, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.534, "f_precision": 0.7904, "f_coverage": 0.7904, "f_balanced": 0.8578, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1437, "chars": 5748, "content_recall": 0.568, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6217, "f_coverage": 0.6217, "f_balanced": 0.7245, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1404, "chars": 5619, "content_recall": 0.8223, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.712, "f_precision": 0.8526, "f_coverage": 0.8526, "f_balanced": 0.9025, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1314, "chars": 5259, "content_recall": 0.7066, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.761, "f_precision": 0.7506, "f_coverage": 0.7506, "f_balanced": 0.8281, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9788, "chars": 39155, "content_recall": 0.7402, "noise_retention": 0.0357, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.409, "f_precision": 0.7763, "f_coverage": 0.7763, "f_balanced": 0.8375, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 10060, "chars": 40240, "content_recall": 0.7402, "noise_retention": 0.0643, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.398, "f_precision": 0.7725, "f_coverage": 0.7725, "f_balanced": 0.8266, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3647, "chars": 14588, "content_recall": 0.8654, "noise_retention": 0.8071, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.823, "f_precision": 0.5098, "f_coverage": 0.5098, "f_balanced": 0.3154, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9775, "chars": 39103, "content_recall": 0.7402, "noise_retention": 0.0357, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.409, "f_precision": 0.7763, "f_coverage": 0.7763, "f_balanced": 0.8375, "anchor_diag": { "content_chars": 6007, "noise_chars": 1439, "content_ngrams": 743, "noise_ngrams": 140, "ambiguous_ngrams_removed": 13, "content_sentences": 66 }, "notes": "" } }, "scoreable": true }, "cloudflare-workers-routing": { "meta": { "id": "cloudflare-workers-routing", "url": "https://developers.cloudflare.com/workers/configuration/routing/", "requested_url": "https://developers.cloudflare.com/workers/configuration/routing/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 172574 } }, "anchors": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 441, "chars": 1765, "content_recall": 0.7552, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7941, "f_coverage": 0.7941, "f_balanced": 0.8605, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 449, "chars": 1799, "content_recall": 0.8021, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8351, "f_coverage": 0.8351, "f_balanced": 0.8902, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 390, "chars": 1560, "content_recall": 0.6979, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7428, "f_coverage": 0.7428, "f_balanced": 0.8221, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 323, "chars": 1293, "content_recall": 0.8438, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.871, "f_coverage": 0.871, "f_balanced": 0.9153, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" }, "readability": { "method": "readability", "tokens": 329, "chars": 1317, "content_recall": 0.8438, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.871, "f_coverage": 0.871, "f_balanced": 0.9153, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8122, "chars": 32489, "content_recall": 0.75, "noise_retention": 0.0493, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.369, "f_precision": 0.7831, "f_coverage": 0.7831, "f_balanced": 0.8385, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 8365, "chars": 33460, "content_recall": 0.75, "noise_retention": 0.0704, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.359, "f_precision": 0.7801, "f_coverage": 0.7801, "f_balanced": 0.8302, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2373, "chars": 9495, "content_recall": 0.875, "noise_retention": 0.8099, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.843, "f_precision": 0.5086, "f_coverage": 0.5086, "f_balanced": 0.3124, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8110, "chars": 32441, "content_recall": 0.75, "noise_retention": 0.0493, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.37, "f_precision": 0.7831, "f_coverage": 0.7831, "f_balanced": 0.8385, "anchor_diag": { "content_chars": 1873, "noise_chars": 1155, "content_ngrams": 192, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 16 }, "notes": "" } }, "scoreable": true }, "cloudflare-workers": { "meta": { "id": "cloudflare-workers", "url": "https://developers.cloudflare.com/workers/", "requested_url": "https://developers.cloudflare.com/workers/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 204597 } }, "anchors": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 542, "chars": 2171, "content_recall": 0.7783, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8144, "f_coverage": 0.8144, "f_balanced": 0.8753, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 552, "chars": 2209, "content_recall": 0.8235, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8537, "f_coverage": 0.8537, "f_balanced": 0.9032, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 296, "chars": 1185, "content_recall": 0.2896, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3376, "f_coverage": 0.3376, "f_balanced": 0.4491, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 412, "chars": 1651, "content_recall": 0.8281, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8575, "f_coverage": 0.8575, "f_balanced": 0.9059, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" }, "readability": { "method": "readability", "tokens": 442, "chars": 1769, "content_recall": 0.6878, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7336, "f_coverage": 0.7336, "f_balanced": 0.815, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8562, "chars": 34250, "content_recall": 0.5837, "noise_retention": 0.0551, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.35, "f_precision": 0.632, "f_coverage": 0.632, "f_balanced": 0.7216, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 8802, "chars": 35209, "content_recall": 0.5837, "noise_retention": 0.0709, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.341, "f_precision": 0.6306, "f_coverage": 0.6306, "f_balanced": 0.717, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2602, "chars": 10408, "content_recall": 0.7828, "noise_retention": 0.8819, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.769, "f_precision": 0.3683, "f_coverage": 0.3683, "f_balanced": 0.2053, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8552, "chars": 34211, "content_recall": 0.5837, "noise_retention": 0.0551, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.351, "f_precision": 0.632, "f_coverage": 0.632, "f_balanced": 0.7216, "anchor_diag": { "content_chars": 1731, "noise_chars": 1127, "content_ngrams": 221, "noise_ngrams": 127, "ambiguous_ngrams_removed": 3, "content_sentences": 23 }, "notes": "" } }, "scoreable": true }, "cmake-docs": { "meta": { "id": "cmake-docs", "url": "https://cmake.org/documentation/", "requested_url": "https://cmake.org/documentation/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 51441 } }, "anchors": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 622, "chars": 2490, "content_recall": 0.678, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7246, "f_coverage": 0.7246, "f_balanced": 0.8081, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 721, "chars": 2886, "content_recall": 0.7076, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7516, "f_coverage": 0.7516, "f_balanced": 0.8288, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 581, "chars": 2326, "content_recall": 0.6356, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6856, "f_coverage": 0.6856, "f_balanced": 0.7772, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 495, "chars": 1981, "content_recall": 0.7542, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7932, "f_coverage": 0.7932, "f_balanced": 0.8599, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "readability": { "method": "readability", "tokens": 67, "chars": 271, "content_recall": 0.1483, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1788, "f_coverage": 0.1788, "f_balanced": 0.2583, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1603, "chars": 6415, "content_recall": 0.7203, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.763, "f_coverage": 0.763, "f_balanced": 0.8374, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1669, "chars": 6676, "content_recall": 0.7203, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.763, "f_coverage": 0.763, "f_balanced": 0.8374, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 654, "chars": 2617, "content_recall": 0.9025, "noise_retention": 0.6957, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6479, "f_coverage": 0.6479, "f_balanced": 0.4552, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1590, "chars": 6361, "content_recall": 0.7203, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.763, "f_coverage": 0.763, "f_balanced": 0.8374, "anchor_diag": { "content_chars": 2477, "noise_chars": 308, "content_ngrams": 236, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" } }, "scoreable": true }, "conda-docs": { "meta": { "id": "conda-docs", "url": "https://docs.conda.io/en/latest/", "requested_url": "https://docs.conda.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 49520 } }, "anchors": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 452, "chars": 1809, "content_recall": 0.6099, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6615, "f_coverage": 0.6615, "f_balanced": 0.7577, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 502, "chars": 2009, "content_recall": 0.6374, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6872, "f_coverage": 0.6872, "f_balanced": 0.7785, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 223, "chars": 895, "content_recall": 0.3187, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.369, "f_coverage": 0.369, "f_balanced": 0.4833, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 171, "chars": 684, "content_recall": 0.3022, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3512, "f_coverage": 0.3512, "f_balanced": 0.4641, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "readability": { "method": "readability", "tokens": 204, "chars": 818, "content_recall": 0.5495, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6039, "f_coverage": 0.6039, "f_balanced": 0.7092, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1843, "chars": 7375, "content_recall": 0.5934, "noise_retention": 0.3636, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6015, "f_coverage": 0.6015, "f_balanced": 0.6141, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1465, "chars": 5862, "content_recall": 0.5934, "noise_retention": 0.3636, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6015, "f_coverage": 0.6015, "f_balanced": 0.6141, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 745, "chars": 2980, "content_recall": 0.6538, "noise_retention": 0.7576, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4882, "f_coverage": 0.4882, "f_balanced": 0.3537, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1828, "chars": 7313, "content_recall": 0.5934, "noise_retention": 0.3636, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6015, "f_coverage": 0.6015, "f_balanced": 0.6141, "anchor_diag": { "content_chars": 1400, "noise_chars": 279, "content_ngrams": 182, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" } }, "scoreable": true }, "cuelang-docs": { "meta": { "id": "cuelang-docs", "url": "https://cuelang.org/docs/", "requested_url": "https://cuelang.org/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 28327 } }, "anchors": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 335, "chars": 1340, "content_recall": 0.3739, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4274, "f_coverage": 0.4274, "f_balanced": 0.5443, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 335, "chars": 1340, "content_recall": 0.3739, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4274, "f_coverage": 0.4274, "f_balanced": 0.5443, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 284, "chars": 1138, "content_recall": 0.3108, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3605, "f_coverage": 0.3605, "f_balanced": 0.4742, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 503, "chars": 2014, "content_recall": 0.7477, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7875, "f_coverage": 0.7875, "f_balanced": 0.8557, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" }, "readability": { "method": "readability", "tokens": 493, "chars": 1974, "content_recall": 0.7793, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8153, "f_coverage": 0.8153, "f_balanced": 0.8759, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1253, "chars": 5012, "content_recall": 0.7207, "noise_retention": 0.1774, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.798, "f_precision": 0.739, "f_coverage": 0.739, "f_balanced": 0.7683, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1346, "chars": 5387, "content_recall": 0.7207, "noise_retention": 0.1774, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.743, "f_precision": 0.739, "f_coverage": 0.739, "f_balanced": 0.7683, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 652, "chars": 2609, "content_recall": 0.7748, "noise_retention": 0.6613, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.534, "f_precision": 0.6161, "f_coverage": 0.6161, "f_balanced": 0.4714, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1249, "chars": 4997, "content_recall": 0.7207, "noise_retention": 0.1774, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.801, "f_precision": 0.739, "f_coverage": 0.739, "f_balanced": 0.7683, "anchor_diag": { "content_chars": 1937, "noise_chars": 647, "content_ngrams": 222, "noise_ngrams": 62, "ambiguous_ngrams_removed": 5, "content_sentences": 22 }, "notes": "" } }, "scoreable": true }, "cypress-docs": { "meta": { "id": "cypress-docs", "url": "https://docs.cypress.io/", "requested_url": "https://docs.cypress.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 7187 } }, "anchors": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 17, "chars": 69, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 17, "chars": 69, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 17, "chars": 69, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 6, "chars": 26, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5, "chars": 21, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1, "chars": 1, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 5, "chars": 21, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "databricks-docs": { "meta": { "id": "databricks-docs", "url": "https://docs.databricks.com/aws/en", "requested_url": "https://docs.databricks.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 27793 } }, "anchors": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 861, "chars": 3445, "content_recall": 0.5304, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5854, "f_coverage": 0.5854, "f_balanced": 0.6932, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 861, "chars": 3445, "content_recall": 0.5304, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5854, "f_coverage": 0.5854, "f_balanced": 0.6932, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 824, "chars": 3299, "content_recall": 0.4864, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5421, "f_coverage": 0.5421, "f_balanced": 0.6544, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 895, "chars": 3580, "content_recall": 0.8008, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.117, "f_precision": 0.8341, "f_coverage": 0.8341, "f_balanced": 0.8894, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "readability": { "method": "readability", "tokens": 12, "chars": 49, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2210, "chars": 8842, "content_recall": 0.6394, "noise_retention": 0.2963, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.452, "f_precision": 0.6513, "f_coverage": 0.6513, "f_balanced": 0.67, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2138, "chars": 8555, "content_recall": 0.6394, "noise_retention": 0.2963, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.468, "f_precision": 0.6513, "f_coverage": 0.6513, "f_balanced": 0.67, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1001, "chars": 4006, "content_recall": 0.7925, "noise_retention": 0.8889, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.999, "f_precision": 0.3559, "f_coverage": 0.3559, "f_balanced": 0.1949, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1608, "chars": 6432, "content_recall": 0.6394, "noise_retention": 0.2963, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.622, "f_precision": 0.6513, "f_coverage": 0.6513, "f_balanced": 0.67, "anchor_diag": { "content_chars": 5379, "noise_chars": 443, "content_ngrams": 477, "noise_ngrams": 54, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" } }, "scoreable": true }, "datadog-docs": { "meta": { "id": "datadog-docs", "url": "https://docs.datadoghq.com/", "requested_url": "https://docs.datadoghq.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 557705 } }, "anchors": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 144, "chars": 578, "content_recall": 0.7419, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7823, "f_coverage": 0.7823, "f_balanced": 0.8519, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 144, "chars": 578, "content_recall": 0.7419, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7823, "f_coverage": 0.7823, "f_balanced": 0.8519, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 144, "chars": 578, "content_recall": 0.7419, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7823, "f_coverage": 0.7823, "f_balanced": 0.8519, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1911, "chars": 7644, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" }, "readability": { "method": "readability", "tokens": 21, "chars": 86, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 50767, "chars": 203071, "content_recall": 0.7419, "noise_retention": 0.3458, "noise_keyword_total": 7, "noise_per_1k_tokens": 0.138, "f_precision": 0.7225, "f_coverage": 0.7225, "f_balanced": 0.6953, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 51980, "chars": 207923, "content_recall": 0.7419, "noise_retention": 0.3409, "noise_keyword_total": 7, "noise_per_1k_tokens": 0.135, "f_precision": 0.7237, "f_coverage": 0.7237, "f_balanced": 0.698, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 10940, "chars": 43762, "content_recall": 0.7419, "noise_retention": 0.9739, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.274, "f_precision": 0.1144, "f_coverage": 0.1144, "f_balanced": 0.0504, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 50739, "chars": 202956, "content_recall": 0.7419, "noise_retention": 0.3458, "noise_keyword_total": 7, "noise_per_1k_tokens": 0.138, "f_precision": 0.7225, "f_coverage": 0.7225, "f_balanced": 0.6953, "anchor_diag": { "content_chars": 252, "noise_chars": 8497, "content_ngrams": 31, "noise_ngrams": 613, "ambiguous_ngrams_removed": 0, "content_sentences": 3 }, "notes": "" } }, "scoreable": false }, "dbt-docs": { "meta": { "id": "dbt-docs", "url": "https://docs.getdbt.com/", "requested_url": "https://docs.getdbt.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 38355 } }, "anchors": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 89, "chars": 356, "content_recall": 1.0, "noise_retention": 0.0446, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9908, "f_coverage": 0.9908, "f_balanced": 0.9772, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 89, "chars": 356, "content_recall": 1.0, "noise_retention": 0.0446, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9908, "f_coverage": 0.9908, "f_balanced": 0.9772, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 89, "chars": 356, "content_recall": 1.0, "noise_retention": 0.0446, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9908, "f_coverage": 0.9908, "f_balanced": 0.9772, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 227, "chars": 909, "content_recall": 1.0, "noise_retention": 0.0446, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9908, "f_coverage": 0.9908, "f_balanced": 0.9772, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "readability": { "method": "readability", "tokens": 33, "chars": 134, "content_recall": 0.0, "noise_retention": 0.0892, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2271, "chars": 9087, "content_recall": 1.0, "noise_retention": 0.4076, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.202, "f_precision": 0.879, "f_coverage": 0.879, "f_balanced": 0.744, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2321, "chars": 9285, "content_recall": 0.9333, "noise_retention": 0.3949, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.154, "f_precision": 0.842, "f_coverage": 0.842, "f_balanced": 0.7342, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1260, "chars": 5042, "content_recall": 1.0, "noise_retention": 0.9236, "noise_keyword_total": 4, "noise_per_1k_tokens": 3.175, "f_precision": 0.2927, "f_coverage": 0.2927, "f_balanced": 0.142, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2261, "chars": 9044, "content_recall": 1.0, "noise_retention": 0.4076, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.211, "f_precision": 0.879, "f_coverage": 0.879, "f_balanced": 0.744, "anchor_diag": { "content_chars": 144, "noise_chars": 1175, "content_ngrams": 15, "noise_ngrams": 157, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" } }, "scoreable": false }, "debian-docs": { "meta": { "id": "debian-docs", "url": "https://www.debian.org/doc/", "requested_url": "https://www.debian.org/doc/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 13834 } }, "anchors": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 645, "chars": 2580, "content_recall": 0.6504, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6993, "f_coverage": 0.6993, "f_balanced": 0.7882, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 654, "chars": 2617, "content_recall": 0.6632, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7111, "f_coverage": 0.7111, "f_balanced": 0.7975, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 619, "chars": 2477, "content_recall": 0.6478, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6969, "f_coverage": 0.6969, "f_balanced": 0.7863, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 873, "chars": 3494, "content_recall": 0.6607, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7088, "f_coverage": 0.7088, "f_balanced": 0.7957, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" }, "readability": { "method": "readability", "tokens": 915, "chars": 3660, "content_recall": 0.6272, "noise_retention": 0.9167, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2721, "f_coverage": 0.2721, "f_balanced": 0.1471, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1783, "chars": 7134, "content_recall": 0.7326, "noise_retention": 0.8333, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4363, "f_coverage": 0.4363, "f_balanced": 0.2716, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1770, "chars": 7081, "content_recall": 0.7069, "noise_retention": 0.8333, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4289, "f_coverage": 0.4289, "f_balanced": 0.2697, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1346, "chars": 5387, "content_recall": 0.8715, "noise_retention": 0.9167, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3014, "f_coverage": 0.3014, "f_balanced": 0.1521, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1772, "chars": 7091, "content_recall": 0.7326, "noise_retention": 0.8333, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4363, "f_coverage": 0.4363, "f_balanced": 0.2716, "anchor_diag": { "content_chars": 3248, "noise_chars": 389, "content_ngrams": 389, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 28 }, "notes": "" } }, "scoreable": true }, "digitalocean-docs": { "meta": { "id": "digitalocean-docs", "url": "https://docs.digitalocean.com/", "requested_url": "https://docs.digitalocean.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 156799 } }, "anchors": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 11929, "chars": 47717, "content_recall": 0.788, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8229, "f_coverage": 0.8229, "f_balanced": 0.8814, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 12121, "chars": 48486, "content_recall": 0.8035, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8363, "f_coverage": 0.8363, "f_balanced": 0.891, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 9964, "chars": 39859, "content_recall": 0.7119, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7555, "f_coverage": 0.7555, "f_balanced": 0.8317, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 12682, "chars": 50729, "content_recall": 0.8245, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8545, "f_coverage": 0.8545, "f_balanced": 0.9038, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" }, "readability": { "method": "readability", "tokens": 846, "chars": 3387, "content_recall": 0.0633, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0779, "f_coverage": 0.0779, "f_balanced": 0.1191, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 21748, "chars": 86995, "content_recall": 0.6987, "noise_retention": 0.0452, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.138, "f_precision": 0.7383, "f_coverage": 0.7383, "f_balanced": 0.8069, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 22206, "chars": 88827, "content_recall": 0.699, "noise_retention": 0.0452, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.135, "f_precision": 0.7386, "f_coverage": 0.7386, "f_balanced": 0.8071, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 12907, "chars": 51629, "content_recall": 0.8493, "noise_retention": 0.7484, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.155, "f_precision": 0.5757, "f_coverage": 0.5757, "f_balanced": 0.3882, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 21733, "chars": 86932, "content_recall": 0.6987, "noise_retention": 0.0452, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.138, "f_precision": 0.7383, "f_coverage": 0.7383, "f_balanced": 0.8069, "anchor_diag": { "content_chars": 97381, "noise_chars": 1848, "content_ngrams": 5811, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 871 }, "notes": "" } }, "scoreable": true }, "digitalocean-droplets": { "meta": { "id": "digitalocean-droplets", "url": "https://docs.digitalocean.com/products/droplets/", "requested_url": "https://docs.digitalocean.com/products/droplets/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 55682 } }, "anchors": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 718, "chars": 2873, "content_recall": 0.7113, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7549, "f_coverage": 0.7549, "f_balanced": 0.8313, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 718, "chars": 2873, "content_recall": 0.7113, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7549, "f_coverage": 0.7549, "f_balanced": 0.8313, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 670, "chars": 2680, "content_recall": 0.6582, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7065, "f_coverage": 0.7065, "f_balanced": 0.7939, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 619, "chars": 2478, "content_recall": 0.6697, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7171, "f_coverage": 0.7171, "f_balanced": 0.8022, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" }, "readability": { "method": "readability", "tokens": 203, "chars": 814, "content_recall": 0.1917, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2287, "f_coverage": 0.2287, "f_balanced": 0.3217, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2930, "chars": 11720, "content_recall": 0.7067, "noise_retention": 0.162, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.024, "f_precision": 0.7296, "f_coverage": 0.7296, "f_balanced": 0.7668, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3136, "chars": 12546, "content_recall": 0.7067, "noise_retention": 0.162, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.957, "f_precision": 0.7296, "f_coverage": 0.7296, "f_balanced": 0.7668, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1155, "chars": 4623, "content_recall": 0.8406, "noise_retention": 0.8939, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.732, "f_precision": 0.3526, "f_coverage": 0.3526, "f_balanced": 0.1885, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2915, "chars": 11662, "content_recall": 0.7067, "noise_retention": 0.162, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.029, "f_precision": 0.7296, "f_coverage": 0.7296, "f_balanced": 0.7668, "anchor_diag": { "content_chars": 5019, "noise_chars": 2253, "content_ngrams": 433, "noise_ngrams": 179, "ambiguous_ngrams_removed": 0, "content_sentences": 54 }, "notes": "" } }, "scoreable": true }, "digitalocean-k8s": { "meta": { "id": "digitalocean-k8s", "url": "https://docs.digitalocean.com/products/kubernetes/", "requested_url": "https://docs.digitalocean.com/products/kubernetes/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 60263 } }, "anchors": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1009, "chars": 4036, "content_recall": 0.6887, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7344, "f_coverage": 0.7344, "f_balanced": 0.8156, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1009, "chars": 4036, "content_recall": 0.6887, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7344, "f_coverage": 0.7344, "f_balanced": 0.8156, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 900, "chars": 3600, "content_recall": 0.6022, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6543, "f_coverage": 0.6543, "f_balanced": 0.7517, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 917, "chars": 3670, "content_recall": 0.673, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7201, "f_coverage": 0.7201, "f_balanced": 0.8045, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" }, "readability": { "method": "readability", "tokens": 339, "chars": 1357, "content_recall": 0.2107, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2502, "f_coverage": 0.2502, "f_balanced": 0.3481, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3154, "chars": 12616, "content_recall": 0.717, "noise_retention": 0.0979, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.951, "f_precision": 0.7477, "f_coverage": 0.7477, "f_balanced": 0.799, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3439, "chars": 13756, "content_recall": 0.717, "noise_retention": 0.1049, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.872, "f_precision": 0.7467, "f_coverage": 0.7467, "f_balanced": 0.7962, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1457, "chars": 5829, "content_recall": 0.8522, "noise_retention": 0.7203, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.373, "f_precision": 0.6047, "f_coverage": 0.6047, "f_balanced": 0.4212, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3135, "chars": 12543, "content_recall": 0.717, "noise_retention": 0.0979, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.957, "f_precision": 0.7477, "f_coverage": 0.7477, "f_balanced": 0.799, "anchor_diag": { "content_chars": 7504, "noise_chars": 1731, "content_ngrams": 636, "noise_ngrams": 143, "ambiguous_ngrams_removed": 3, "content_sentences": 69 }, "notes": "" } }, "scoreable": true }, "digitalocean-spaces": { "meta": { "id": "digitalocean-spaces", "url": "https://docs.digitalocean.com/products/spaces/", "requested_url": "https://docs.digitalocean.com/products/spaces/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 48551 } }, "anchors": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 512, "chars": 2048, "content_recall": 0.6209, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6718, "f_coverage": 0.6718, "f_balanced": 0.7661, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 542, "chars": 2171, "content_recall": 0.6507, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6996, "f_coverage": 0.6996, "f_balanced": 0.7884, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 512, "chars": 2048, "content_recall": 0.6209, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6718, "f_coverage": 0.6718, "f_balanced": 0.7661, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 453, "chars": 1812, "content_recall": 0.597, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6494, "f_coverage": 0.6494, "f_balanced": 0.7477, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" }, "readability": { "method": "readability", "tokens": 186, "chars": 746, "content_recall": 0.2119, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2516, "f_coverage": 0.2516, "f_balanced": 0.3498, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2311, "chars": 9246, "content_recall": 0.6836, "noise_retention": 0.1275, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.298, "f_precision": 0.7145, "f_coverage": 0.7145, "f_balanced": 0.7666, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2495, "chars": 9980, "content_recall": 0.6836, "noise_retention": 0.1275, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.202, "f_precision": 0.7145, "f_coverage": 0.7145, "f_balanced": 0.7666, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 941, "chars": 3764, "content_recall": 0.8328, "noise_retention": 0.8859, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.125, "f_precision": 0.3685, "f_coverage": 0.3685, "f_balanced": 0.2007, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2293, "chars": 9175, "content_recall": 0.6836, "noise_retention": 0.1275, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.308, "f_precision": 0.7145, "f_coverage": 0.7145, "f_balanced": 0.7666, "anchor_diag": { "content_chars": 3689, "noise_chars": 1841, "content_ngrams": 335, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 40 }, "notes": "" } }, "scoreable": true }, "discord-api": { "meta": { "id": "discord-api", "url": "https://docs.discord.com/developers/intro", "requested_url": "https://discord.com/developers/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 344355 } }, "anchors": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 299, "chars": 1197, "content_recall": 0.6429, "noise_retention": 0.0752, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6846, "f_coverage": 0.6846, "f_balanced": 0.7585, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 299, "chars": 1197, "content_recall": 0.6429, "noise_retention": 0.0752, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6846, "f_coverage": 0.6846, "f_balanced": 0.7585, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 270, "chars": 1081, "content_recall": 0.5119, "noise_retention": 0.0752, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5621, "f_coverage": 0.5621, "f_balanced": 0.659, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 217, "chars": 869, "content_recall": 0.6429, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6923, "f_coverage": 0.6923, "f_balanced": 0.7826, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" }, "readability": { "method": "readability", "tokens": 251, "chars": 1005, "content_recall": 0.6429, "noise_retention": 0.0752, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6846, "f_coverage": 0.6846, "f_balanced": 0.7585, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1163, "chars": 4652, "content_recall": 0.6429, "noise_retention": 0.2105, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6677, "f_coverage": 0.6677, "f_balanced": 0.7087, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1151, "chars": 4604, "content_recall": 0.6429, "noise_retention": 0.2105, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6677, "f_coverage": 0.6677, "f_balanced": 0.7087, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 534, "chars": 2136, "content_recall": 0.6429, "noise_retention": 0.8797, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.344, "f_coverage": 0.344, "f_balanced": 0.2027, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1150, "chars": 4601, "content_recall": 0.6429, "noise_retention": 0.2105, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6677, "f_coverage": 0.6677, "f_balanced": 0.7087, "anchor_diag": { "content_chars": 618, "noise_chars": 1108, "content_ngrams": 84, "noise_ngrams": 133, "ambiguous_ngrams_removed": 1, "content_sentences": 8 }, "notes": "" } }, "scoreable": true }, "django-docs": { "meta": { "id": "django-docs", "url": "https://docs.djangoproject.com/en/6.1/", "requested_url": "https://docs.djangoproject.com/en/stable/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 54126 } }, "anchors": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 911, "chars": 3644, "content_recall": 0.3963, "noise_retention": 0.0024, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4506, "f_coverage": 0.4506, "f_balanced": 0.5672, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1057, "chars": 4228, "content_recall": 0.4555, "noise_retention": 0.0024, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5111, "f_coverage": 0.5111, "f_balanced": 0.6255, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 797, "chars": 3190, "content_recall": 0.3326, "noise_retention": 0.0024, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3838, "f_coverage": 0.3838, "f_balanced": 0.4989, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1654, "chars": 6617, "content_recall": 0.7168, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7598, "f_coverage": 0.7598, "f_balanced": 0.835, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" }, "readability": { "method": "readability", "tokens": 839, "chars": 3359, "content_recall": 0.3864, "noise_retention": 0.0024, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4403, "f_coverage": 0.4403, "f_balanced": 0.557, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5236, "chars": 20945, "content_recall": 0.4029, "noise_retention": 0.558, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.191, "f_precision": 0.4101, "f_coverage": 0.4101, "f_balanced": 0.4215, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5065, "chars": 20261, "content_recall": 0.4248, "noise_retention": 0.5556, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.197, "f_precision": 0.4286, "f_coverage": 0.4286, "f_balanced": 0.4344, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2615, "chars": 10462, "content_recall": 0.7398, "noise_retention": 0.9541, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.382, "f_precision": 0.1839, "f_coverage": 0.1839, "f_balanced": 0.0864, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5220, "chars": 20883, "content_recall": 0.4029, "noise_retention": 0.5556, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.192, "f_precision": 0.4105, "f_coverage": 0.4105, "f_balanced": 0.4226, "anchor_diag": { "content_chars": 9991, "noise_chars": 3551, "content_ngrams": 911, "noise_ngrams": 414, "ambiguous_ngrams_removed": 6, "content_sentences": 93 }, "notes": "" } }, "scoreable": true }, "docker-blog": { "meta": { "id": "docker-blog", "url": "https://www.docker.com/blog/", "requested_url": "https://www.docker.com/blog/", "category": "article", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 243921 } }, "anchors": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 660, "chars": 2640, "content_recall": 0.7716, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8085, "f_coverage": 0.8085, "f_balanced": 0.8711, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 660, "chars": 2640, "content_recall": 0.7716, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8085, "f_coverage": 0.8085, "f_balanced": 0.8711, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 660, "chars": 2640, "content_recall": 0.7716, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8085, "f_coverage": 0.8085, "f_balanced": 0.8711, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 598, "chars": 2393, "content_recall": 0.5127, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5681, "f_coverage": 0.5681, "f_balanced": 0.6779, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "readability": { "method": "readability", "tokens": 633, "chars": 2535, "content_recall": 0.7538, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7928, "f_coverage": 0.7928, "f_balanced": 0.8596, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2921, "chars": 11685, "content_recall": 0.731, "noise_retention": 0.4227, "noise_keyword_total": 12, "noise_per_1k_tokens": 4.108, "f_precision": 0.694, "f_coverage": 0.694, "f_balanced": 0.6451, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2882, "chars": 11528, "content_recall": 0.731, "noise_retention": 0.4227, "noise_keyword_total": 12, "noise_per_1k_tokens": 4.164, "f_precision": 0.694, "f_coverage": 0.694, "f_balanced": 0.6451, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1334, "chars": 5337, "content_recall": 0.8274, "noise_retention": 0.9779, "noise_keyword_total": 3, "noise_per_1k_tokens": 2.249, "f_precision": 0.0998, "f_coverage": 0.0998, "f_balanced": 0.043, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2898, "chars": 11594, "content_recall": 0.731, "noise_retention": 0.4227, "noise_keyword_total": 12, "noise_per_1k_tokens": 4.141, "f_precision": 0.694, "f_coverage": 0.694, "f_balanced": 0.6451, "anchor_diag": { "content_chars": 4845, "noise_chars": 4456, "content_ngrams": 394, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" } }, "scoreable": true }, "docker-compose": { "meta": { "id": "docker-compose", "url": "https://docs.docker.com/compose/", "requested_url": "https://docs.docker.com/compose/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 511270 } }, "anchors": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 251, "chars": 1006, "content_recall": 0.3462, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3982, "f_coverage": 0.3982, "f_balanced": 0.5143, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 286, "chars": 1147, "content_recall": 0.4423, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4978, "f_coverage": 0.4978, "f_balanced": 0.6133, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 240, "chars": 961, "content_recall": 0.3365, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.388, "f_coverage": 0.388, "f_balanced": 0.5036, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 196, "chars": 784, "content_recall": 0.4375, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.493, "f_coverage": 0.493, "f_balanced": 0.6087, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "readability": { "method": "readability", "tokens": 139, "chars": 559, "content_recall": 0.2548, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2994, "f_coverage": 0.2994, "f_balanced": 0.4061, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 22052, "chars": 88210, "content_recall": 0.7308, "noise_retention": 0.3542, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.045, "f_precision": 0.712, "f_coverage": 0.712, "f_balanced": 0.6857, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 22542, "chars": 90170, "content_recall": 0.601, "noise_retention": 0.3542, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.044, "f_precision": 0.6094, "f_coverage": 0.6094, "f_balanced": 0.6226, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4166, "chars": 16664, "content_recall": 0.8654, "noise_retention": 0.6667, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.24, "f_precision": 0.656, "f_coverage": 0.656, "f_balanced": 0.4813, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 22042, "chars": 88170, "content_recall": 0.7308, "noise_retention": 0.3542, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.045, "f_precision": 0.712, "f_coverage": 0.712, "f_balanced": 0.6857, "anchor_diag": { "content_chars": 1973, "noise_chars": 382, "content_ngrams": 208, "noise_ngrams": 48, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" } }, "scoreable": true }, "docker-docs": { "meta": { "id": "docker-docs", "url": "https://docs.docker.com/", "requested_url": "https://docs.docker.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 187074 } }, "anchors": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 126, "chars": 506, "content_recall": 0.0641, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0788, "f_coverage": 0.0788, "f_balanced": 0.1204, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 136, "chars": 544, "content_recall": 0.0808, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.099, "f_coverage": 0.099, "f_balanced": 0.1495, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 114, "chars": 457, "content_recall": 0.0362, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0449, "f_coverage": 0.0449, "f_balanced": 0.0699, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 519, "chars": 2077, "content_recall": 0.5822, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6353, "f_coverage": 0.6353, "f_balanced": 0.7359, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "readability": { "method": "readability", "tokens": 33, "chars": 133, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1175, "chars": 4700, "content_recall": 0.8134, "noise_retention": 0.4359, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.851, "f_precision": 0.7473, "f_coverage": 0.7473, "f_balanced": 0.6662, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1206, "chars": 4827, "content_recall": 0.7799, "noise_retention": 0.4359, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.829, "f_precision": 0.7245, "f_coverage": 0.7245, "f_balanced": 0.6547, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 771, "chars": 3086, "content_recall": 0.9443, "noise_retention": 0.7949, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.297, "f_precision": 0.5488, "f_coverage": 0.5488, "f_balanced": 0.337, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1170, "chars": 4680, "content_recall": 0.8134, "noise_retention": 0.4359, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.855, "f_precision": 0.7473, "f_coverage": 0.7473, "f_balanced": 0.6662, "anchor_diag": { "content_chars": 2792, "noise_chars": 319, "content_ngrams": 359, "noise_ngrams": 39, "ambiguous_ngrams_removed": 0, "content_sentences": 19 }, "notes": "" } }, "scoreable": true }, "docker-engine": { "meta": { "id": "docker-engine", "url": "https://docs.docker.com/engine/", "requested_url": "https://docs.docker.com/engine/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 513982 } }, "anchors": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 388, "chars": 1554, "content_recall": 0.4502, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5058, "f_coverage": 0.5058, "f_balanced": 0.6209, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 404, "chars": 1618, "content_recall": 0.4545, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5102, "f_coverage": 0.5102, "f_balanced": 0.625, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 332, "chars": 1329, "content_recall": 0.3333, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3846, "f_coverage": 0.3846, "f_balanced": 0.5, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 245, "chars": 980, "content_recall": 0.4978, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5534, "f_coverage": 0.5534, "f_balanced": 0.6647, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" }, "readability": { "method": "readability", "tokens": 37, "chars": 149, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 22162, "chars": 88651, "content_recall": 0.619, "noise_retention": 0.3617, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.045, "f_precision": 0.6228, "f_coverage": 0.6228, "f_balanced": 0.6285, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 22642, "chars": 90568, "content_recall": 0.5108, "noise_retention": 0.3617, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.044, "f_precision": 0.5321, "f_coverage": 0.5321, "f_balanced": 0.5675, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4198, "chars": 16794, "content_recall": 0.7922, "noise_retention": 0.6596, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.238, "f_precision": 0.626, "f_coverage": 0.626, "f_balanced": 0.4762, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 22153, "chars": 88612, "content_recall": 0.619, "noise_retention": 0.3617, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.045, "f_precision": 0.6228, "f_coverage": 0.6228, "f_balanced": 0.6285, "anchor_diag": { "content_chars": 1947, "noise_chars": 409, "content_ngrams": 231, "noise_ngrams": 47, "ambiguous_ngrams_removed": 4, "content_sentences": 26 }, "notes": "" } }, "scoreable": true }, "docker-get-started": { "meta": { "id": "docker-get-started", "url": "https://docs.docker.com/get-started/", "requested_url": "https://docs.docker.com/get-started/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 177448 } }, "anchors": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 224, "chars": 899, "content_recall": 0.5508, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6052, "f_coverage": 0.6052, "f_balanced": 0.7104, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 224, "chars": 899, "content_recall": 0.5508, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6052, "f_coverage": 0.6052, "f_balanced": 0.7104, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 224, "chars": 899, "content_recall": 0.5508, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6052, "f_coverage": 0.6052, "f_balanced": 0.7104, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 149, "chars": 597, "content_recall": 0.4831, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5388, "f_coverage": 0.5388, "f_balanced": 0.6514, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" }, "readability": { "method": "readability", "tokens": 36, "chars": 147, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1432, "chars": 5731, "content_recall": 0.6186, "noise_retention": 0.5172, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.698, "f_precision": 0.5857, "f_coverage": 0.5857, "f_balanced": 0.5423, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1494, "chars": 5979, "content_recall": 0.2966, "noise_retention": 0.5172, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.669, "f_precision": 0.3214, "f_coverage": 0.3214, "f_balanced": 0.3675, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 476, "chars": 1905, "content_recall": 0.7627, "noise_retention": 0.8621, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.101, "f_precision": 0.4002, "f_coverage": 0.4002, "f_balanced": 0.2336, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1424, "chars": 5697, "content_recall": 0.6186, "noise_retention": 0.5172, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.702, "f_precision": 0.5857, "f_coverage": 0.5857, "f_balanced": 0.5423, "anchor_diag": { "content_chars": 1915, "noise_chars": 1016, "content_ngrams": 118, "noise_ngrams": 116, "ambiguous_ngrams_removed": 12, "content_sentences": 17 }, "notes": "" } }, "scoreable": true }, "dotnet-docs": { "meta": { "id": "dotnet-docs", "url": "https://learn.microsoft.com/en-us/dotnet/", "requested_url": "https://learn.microsoft.com/en-us/dotnet/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 70666 } }, "anchors": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 477, "chars": 1911, "content_recall": 0.1602, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1926, "f_coverage": 0.1926, "f_balanced": 0.2762, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 486, "chars": 1947, "content_recall": 0.1813, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2168, "f_coverage": 0.2168, "f_balanced": 0.307, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 299, "chars": 1198, "content_recall": 0.0827, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1013, "f_coverage": 0.1013, "f_balanced": 0.1528, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 320, "chars": 1283, "content_recall": 0.1514, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1824, "f_coverage": 0.1824, "f_balanced": 0.263, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "readability": { "method": "readability", "tokens": 52, "chars": 211, "content_recall": 0.0264, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0328, "f_coverage": 0.0328, "f_balanced": 0.0515, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2314, "chars": 9259, "content_recall": 0.3504, "noise_retention": 0.449, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3779, "f_coverage": 0.3779, "f_balanced": 0.4283, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2382, "chars": 9531, "content_recall": 0.3504, "noise_retention": 0.5102, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3715, "f_coverage": 0.3715, "f_balanced": 0.4085, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1075, "chars": 4301, "content_recall": 0.7799, "noise_retention": 0.9184, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2877, "f_coverage": 0.2877, "f_balanced": 0.1478, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2296, "chars": 9185, "content_recall": 0.3504, "noise_retention": 0.449, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3779, "f_coverage": 0.3779, "f_balanced": 0.4283, "anchor_diag": { "content_chars": 5034, "noise_chars": 422, "content_ngrams": 568, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" } }, "scoreable": true }, "dropbox-api": { "meta": { "id": "dropbox-api", "url": "https://docs.dropboxapi.com/dropbox-api/docs/get-started/welcome", "requested_url": "https://www.dropbox.com/developers/documentation", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 502867 } }, "anchors": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 352, "chars": 1411, "content_recall": 0.7472, "noise_retention": 0.012, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7855, "f_coverage": 0.7855, "f_balanced": 0.8509, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 352, "chars": 1411, "content_recall": 0.7472, "noise_retention": 0.012, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7855, "f_coverage": 0.7855, "f_balanced": 0.8509, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 145, "chars": 581, "content_recall": 0.1292, "noise_retention": 0.0161, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1564, "f_coverage": 0.1564, "f_balanced": 0.2284, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 151, "chars": 605, "content_recall": 0.3764, "noise_retention": 0.0161, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4294, "f_coverage": 0.4294, "f_balanced": 0.5445, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 199, "chars": 799, "content_recall": 0.5449, "noise_retention": 0.012, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5986, "f_coverage": 0.5986, "f_balanced": 0.7024, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2611, "chars": 10446, "content_recall": 0.5787, "noise_retention": 0.253, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.606, "f_coverage": 0.606, "f_balanced": 0.6521, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2645, "chars": 10583, "content_recall": 0.4438, "noise_retention": 0.245, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4837, "f_coverage": 0.4837, "f_balanced": 0.559, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 867, "chars": 3470, "content_recall": 0.764, "noise_retention": 0.8956, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3376, "f_coverage": 0.3376, "f_balanced": 0.1837, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2602, "chars": 10409, "content_recall": 0.5787, "noise_retention": 0.253, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.606, "f_coverage": 0.606, "f_balanced": 0.6521, "anchor_diag": { "content_chars": 1757, "noise_chars": 3142, "content_ngrams": 178, "noise_ngrams": 249, "ambiguous_ngrams_removed": 1, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "elastic-cloud": { "meta": { "id": "elastic-cloud", "url": "https://www.elastic.co/cloud", "requested_url": "https://www.elastic.co/cloud", "category": "marketing", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 620676 } }, "anchors": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1654, "chars": 6616, "content_recall": 0.779, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.815, "f_coverage": 0.815, "f_balanced": 0.8758, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1654, "chars": 6616, "content_recall": 0.779, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.815, "f_coverage": 0.815, "f_balanced": 0.8758, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1492, "chars": 5968, "content_recall": 0.6769, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7237, "f_coverage": 0.7237, "f_balanced": 0.8073, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1429, "chars": 5718, "content_recall": 0.765, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8028, "f_coverage": 0.8028, "f_balanced": 0.8669, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1414, "chars": 5658, "content_recall": 0.772, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8089, "f_coverage": 0.8089, "f_balanced": 0.8713, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 7156, "chars": 28624, "content_recall": 0.7301, "noise_retention": 0.5775, "noise_keyword_total": 8, "noise_per_1k_tokens": 1.118, "f_precision": 0.6373, "f_coverage": 0.6373, "f_balanced": 0.5353, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 7094, "chars": 28376, "content_recall": 0.7301, "noise_retention": 0.5775, "noise_keyword_total": 8, "noise_per_1k_tokens": 1.128, "f_precision": 0.6373, "f_coverage": 0.6373, "f_balanced": 0.5353, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3371, "chars": 13486, "content_recall": 0.8322, "noise_retention": 1.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.187, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 6713, "chars": 26854, "content_recall": 0.7301, "noise_retention": 0.5775, "noise_keyword_total": 8, "noise_per_1k_tokens": 1.192, "f_precision": 0.6373, "f_coverage": 0.6373, "f_balanced": 0.5353, "anchor_diag": { "content_chars": 8937, "noise_chars": 1568, "content_ngrams": 715, "noise_ngrams": 142, "ambiguous_ngrams_removed": 0, "content_sentences": 84 }, "notes": "" } }, "scoreable": true }, "elasticsearch-docs": { "meta": { "id": "elasticsearch-docs", "url": "https://www.elastic.co/docs/reference/elasticsearch", "requested_url": "https://www.elastic.co/guide/en/elasticsearch/reference/current/index.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 1874366 } }, "anchors": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 297, "chars": 1188, "content_recall": 0.866, "noise_retention": 0.1019, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8722, "f_coverage": 0.8722, "f_balanced": 0.8818, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 297, "chars": 1188, "content_recall": 0.866, "noise_retention": 0.1019, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8722, "f_coverage": 0.8722, "f_balanced": 0.8818, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 262, "chars": 1049, "content_recall": 0.6186, "noise_retention": 0.1019, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6596, "f_coverage": 0.6596, "f_balanced": 0.7326, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 168, "chars": 674, "content_recall": 0.4948, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5505, "f_coverage": 0.5505, "f_balanced": 0.6621, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "readability": { "method": "readability", "tokens": 128, "chars": 512, "content_recall": 0.0, "noise_retention": 0.4722, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 171236, "chars": 684944, "content_recall": 0.6907, "noise_retention": 0.6296, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5889, "f_coverage": 0.5889, "f_balanced": 0.4822, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 173556, "chars": 694225, "content_recall": 0.6907, "noise_retention": 0.6759, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5633, "f_coverage": 0.5633, "f_balanced": 0.4412, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 35916, "chars": 143665, "content_recall": 0.8351, "noise_retention": 0.8519, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4333, "f_coverage": 0.4333, "f_balanced": 0.2517, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 173403, "chars": 693613, "content_recall": 0.6907, "noise_retention": 0.6296, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5889, "f_coverage": 0.5889, "f_balanced": 0.4822, "anchor_diag": { "content_chars": 939, "noise_chars": 1112, "content_ngrams": 97, "noise_ngrams": 108, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" } }, "scoreable": true }, "envoy-docs": { "meta": { "id": "envoy-docs", "url": "https://www.envoyproxy.io/docs", "requested_url": "https://www.envoyproxy.io/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 169022 } }, "anchors": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 54, "chars": 216, "content_recall": 0.15, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1807, "f_coverage": 0.1807, "f_balanced": 0.2609, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 54, "chars": 216, "content_recall": 0.15, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1807, "f_coverage": 0.1807, "f_balanced": 0.2609, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 54, "chars": 216, "content_recall": 0.15, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1807, "f_coverage": 0.1807, "f_balanced": 0.2609, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1282, "chars": 5128, "content_recall": 0.35, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4023, "f_coverage": 0.4023, "f_balanced": 0.5185, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" }, "readability": { "method": "readability", "tokens": 73, "chars": 293, "content_recall": 0.0, "noise_retention": 0.75, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 14214, "chars": 56859, "content_recall": 0.15, "noise_retention": 0.775, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1607, "f_coverage": 0.1607, "f_balanced": 0.18, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 12740, "chars": 50963, "content_recall": 0.15, "noise_retention": 0.775, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1607, "f_coverage": 0.1607, "f_balanced": 0.18, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1360, "chars": 5442, "content_recall": 0.35, "noise_retention": 0.825, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2917, "f_coverage": 0.2917, "f_balanced": 0.2333, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 14206, "chars": 56824, "content_recall": 0.15, "noise_retention": 0.775, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1607, "f_coverage": 0.1607, "f_balanced": 0.18, "anchor_diag": { "content_chars": 4047, "noise_chars": 349, "content_ngrams": 20, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 29 }, "notes": "" } }, "scoreable": false }, "fastapi-docs": { "meta": { "id": "fastapi-docs", "url": "https://fastapi.tiangolo.com/", "requested_url": "https://fastapi.tiangolo.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 153352 } }, "anchors": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 3732, "chars": 14928, "content_recall": 0.7549, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.268, "f_precision": 0.7938, "f_coverage": 0.7938, "f_balanced": 0.8603, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 3967, "chars": 15868, "content_recall": 0.8127, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.252, "f_precision": 0.8443, "f_coverage": 0.8443, "f_balanced": 0.8967, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 3028, "chars": 12115, "content_recall": 0.6025, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.33, "f_precision": 0.6546, "f_coverage": 0.6546, "f_balanced": 0.752, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 3750, "chars": 15001, "content_recall": 0.8622, "noise_retention": 0.0, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.8, "f_precision": 0.8867, "f_coverage": 0.8867, "f_balanced": 0.926, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" }, "readability": { "method": "readability", "tokens": 3356, "chars": 13426, "content_recall": 0.8495, "noise_retention": 0.0, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.894, "f_precision": 0.8759, "f_coverage": 0.8759, "f_balanced": 0.9186, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9401, "chars": 37604, "content_recall": 0.8, "noise_retention": 0.2328, "noise_keyword_total": 14, "noise_per_1k_tokens": 1.489, "f_precision": 0.7932, "f_coverage": 0.7932, "f_balanced": 0.7833, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9290, "chars": 37163, "content_recall": 0.8146, "noise_retention": 0.2346, "noise_keyword_total": 14, "noise_per_1k_tokens": 1.507, "f_precision": 0.8043, "f_coverage": 0.8043, "f_balanced": 0.7893, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4934, "chars": 19737, "content_recall": 0.8692, "noise_retention": 0.8466, "noise_keyword_total": 9, "noise_per_1k_tokens": 1.824, "f_precision": 0.4497, "f_coverage": 0.4497, "f_balanced": 0.2608, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9420, "chars": 37681, "content_recall": 0.8, "noise_retention": 0.2328, "noise_keyword_total": 14, "noise_per_1k_tokens": 1.486, "f_precision": 0.7932, "f_coverage": 0.7932, "f_balanced": 0.7833, "anchor_diag": { "content_chars": 15570, "noise_chars": 12819, "content_ngrams": 1575, "noise_ngrams": 567, "ambiguous_ngrams_removed": 62, "content_sentences": 160 }, "notes": "" } }, "scoreable": true }, "figma-api": { "meta": { "id": "figma-api", "url": "https://developers.figma.com/docs/rest-api/", "requested_url": "https://www.figma.com/developers/api", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 37752 } }, "anchors": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 999, "chars": 3996, "content_recall": 0.8161, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.001, "f_precision": 0.8473, "f_coverage": 0.8473, "f_balanced": 0.8987, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1024, "chars": 4099, "content_recall": 0.8299, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.977, "f_precision": 0.8591, "f_coverage": 0.8591, "f_balanced": 0.907, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 848, "chars": 3392, "content_recall": 0.6437, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.179, "f_precision": 0.6931, "f_coverage": 0.6931, "f_balanced": 0.7832, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 793, "chars": 3175, "content_recall": 0.8966, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.261, "f_precision": 0.9155, "f_coverage": 0.9155, "f_balanced": 0.9455, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "readability": { "method": "readability", "tokens": 751, "chars": 3004, "content_recall": 0.8828, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.332, "f_precision": 0.904, "f_coverage": 0.904, "f_balanced": 0.9377, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1860, "chars": 7441, "content_recall": 0.8391, "noise_retention": 0.1268, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.613, "f_precision": 0.8457, "f_coverage": 0.8457, "f_balanced": 0.8558, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1822, "chars": 7288, "content_recall": 0.8391, "noise_retention": 0.1268, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.647, "f_precision": 0.8457, "f_coverage": 0.8457, "f_balanced": 0.8558, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1026, "chars": 4106, "content_recall": 0.9287, "noise_retention": 0.8873, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.949, "f_precision": 0.3793, "f_coverage": 0.3793, "f_balanced": 0.201, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1851, "chars": 7404, "content_recall": 0.8391, "noise_retention": 0.1268, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.621, "f_precision": 0.8457, "f_coverage": 0.8457, "f_balanced": 0.8558, "anchor_diag": { "content_chars": 3125, "noise_chars": 931, "content_ngrams": 435, "noise_ngrams": 71, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" } }, "scoreable": true }, "firebase-docs": { "meta": { "id": "firebase-docs", "url": "https://firebase.google.com/docs", "requested_url": "https://firebase.google.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 193182 } }, "anchors": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 716, "chars": 2866, "content_recall": 0.7736, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8103, "f_coverage": 0.8103, "f_balanced": 0.8724, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 735, "chars": 2943, "content_recall": 0.8345, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.863, "f_coverage": 0.863, "f_balanced": 0.9098, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 671, "chars": 2687, "content_recall": 0.7027, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7471, "f_coverage": 0.7471, "f_balanced": 0.8254, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 599, "chars": 2396, "content_recall": 0.875, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8974, "f_coverage": 0.8974, "f_balanced": 0.9333, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" }, "readability": { "method": "readability", "tokens": 93, "chars": 375, "content_recall": 0.0507, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0626, "f_coverage": 0.0626, "f_balanced": 0.0965, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4420, "chars": 17681, "content_recall": 0.8041, "noise_retention": 0.4117, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.452, "f_precision": 0.7491, "f_coverage": 0.7491, "f_balanced": 0.6795, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4689, "chars": 18757, "content_recall": 0.8041, "noise_retention": 0.4117, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.427, "f_precision": 0.7491, "f_coverage": 0.7491, "f_balanced": 0.6795, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2140, "chars": 8561, "content_recall": 0.8919, "noise_retention": 0.9124, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.935, "f_precision": 0.3144, "f_coverage": 0.3144, "f_balanced": 0.1595, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4404, "chars": 17617, "content_recall": 0.8041, "noise_retention": 0.4117, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.454, "f_precision": 0.7491, "f_coverage": 0.7491, "f_balanced": 0.6795, "anchor_diag": { "content_chars": 2425, "noise_chars": 11340, "content_ngrams": 296, "noise_ngrams": 685, "ambiguous_ngrams_removed": 37, "content_sentences": 26 }, "notes": "" } }, "scoreable": true }, "flask-docs": { "meta": { "id": "flask-docs", "url": "https://flask.palletsprojects.com/en/stable/", "requested_url": "https://flask.palletsprojects.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 39704 } }, "anchors": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 397, "chars": 1590, "content_recall": 0.1481, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1785, "f_coverage": 0.1785, "f_balanced": 0.258, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 408, "chars": 1635, "content_recall": 0.1481, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1785, "f_coverage": 0.1785, "f_balanced": 0.258, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 342, "chars": 1369, "content_recall": 0.1193, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1448, "f_coverage": 0.1448, "f_balanced": 0.2131, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 309, "chars": 1237, "content_recall": 0.1848, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2208, "f_coverage": 0.2208, "f_balanced": 0.3119, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "readability": { "method": "readability", "tokens": 319, "chars": 1277, "content_recall": 0.1848, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2208, "f_coverage": 0.2208, "f_balanced": 0.3119, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4252, "chars": 17008, "content_recall": 0.443, "noise_retention": 0.2258, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4844, "f_coverage": 0.4844, "f_balanced": 0.5635, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4336, "chars": 17346, "content_recall": 0.443, "noise_retention": 0.4194, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.465, "f_coverage": 0.465, "f_balanced": 0.5026, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1745, "chars": 6982, "content_recall": 0.8873, "noise_retention": 0.871, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4079, "f_coverage": 0.4079, "f_balanced": 0.2253, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4237, "chars": 16950, "content_recall": 0.443, "noise_retention": 0.2258, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4844, "f_coverage": 0.4844, "f_balanced": 0.5635, "anchor_diag": { "content_chars": 7148, "noise_chars": 283, "content_ngrams": 763, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" } }, "scoreable": true }, "flux-docs": { "meta": { "id": "flux-docs", "url": "https://fluxcd.io/flux/", "requested_url": "https://fluxcd.io/flux/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": true, "bytes": 175525 } }, "anchors": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1976, "chars": 7907, "content_recall": 0.7666, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8041, "f_coverage": 0.8041, "f_balanced": 0.8679, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2058, "chars": 8234, "content_recall": 0.7898, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8245, "f_coverage": 0.8245, "f_balanced": 0.8826, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1822, "chars": 7290, "content_recall": 0.7013, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7459, "f_coverage": 0.7459, "f_balanced": 0.8244, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1377, "chars": 5510, "content_recall": 0.6969, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7419, "f_coverage": 0.7419, "f_balanced": 0.8214, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1773, "chars": 7092, "content_recall": 0.8606, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8853, "f_coverage": 0.8853, "f_balanced": 0.9251, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8934, "chars": 35739, "content_recall": 0.7865, "noise_retention": 0.1857, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7919, "f_coverage": 0.7919, "f_balanced": 0.8002, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9125, "chars": 36501, "content_recall": 0.7865, "noise_retention": 0.3143, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.764, "f_coverage": 0.764, "f_balanced": 0.7327, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3740, "chars": 14961, "content_recall": 0.8584, "noise_retention": 0.7714, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5534, "f_coverage": 0.5534, "f_balanced": 0.361, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9766, "chars": 39067, "content_recall": 0.7865, "noise_retention": 0.1857, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7919, "f_coverage": 0.7919, "f_balanced": 0.8002, "anchor_diag": { "content_chars": 7485, "noise_chars": 867, "content_ngrams": 904, "noise_ngrams": 70, "ambiguous_ngrams_removed": 0, "content_sentences": 78 }, "notes": "" } }, "scoreable": true }, "fly-docs": { "meta": { "id": "fly-docs", "url": "https://fly.io/docs/", "requested_url": "https://fly.io/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 151669 } }, "anchors": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1026, "chars": 4107, "content_recall": 0.5362, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5911, "f_coverage": 0.5911, "f_balanced": 0.6981, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1071, "chars": 4286, "content_recall": 0.5942, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6467, "f_coverage": 0.6467, "f_balanced": 0.7455, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 966, "chars": 3865, "content_recall": 0.4638, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5195, "f_coverage": 0.5195, "f_balanced": 0.6337, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 159, "chars": 636, "content_recall": 0.2899, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3378, "f_coverage": 0.3378, "f_balanced": 0.4494, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" }, "readability": { "method": "readability", "tokens": 44, "chars": 176, "content_recall": 0.1739, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2083, "f_coverage": 0.2083, "f_balanced": 0.2963, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3532, "chars": 14129, "content_recall": 0.4783, "noise_retention": 0.2216, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.699, "f_precision": 0.5182, "f_coverage": 0.5182, "f_balanced": 0.5925, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3403, "chars": 13612, "content_recall": 0.4783, "noise_retention": 0.2216, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.882, "f_precision": 0.5182, "f_coverage": 0.5182, "f_balanced": 0.5925, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1961, "chars": 7845, "content_recall": 0.5507, "noise_retention": 0.9778, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.53, "f_precision": 0.0954, "f_coverage": 0.0954, "f_balanced": 0.0426, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3416, "chars": 13667, "content_recall": 0.4783, "noise_retention": 0.2216, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.878, "f_precision": 0.5182, "f_coverage": 0.5182, "f_balanced": 0.5925, "anchor_diag": { "content_chars": 515, "noise_chars": 5433, "content_ngrams": 69, "noise_ngrams": 361, "ambiguous_ngrams_removed": 0, "content_sentences": 4 }, "notes": "" } }, "scoreable": true }, "gcp-bigquery": { "meta": { "id": "gcp-bigquery", "url": "https://docs.cloud.google.com/bigquery/docs", "requested_url": "https://cloud.google.com/bigquery/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 305208 } }, "anchors": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1055, "chars": 4222, "content_recall": 0.5823, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6353, "f_coverage": 0.6353, "f_balanced": 0.736, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1106, "chars": 4426, "content_recall": 0.6063, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6581, "f_coverage": 0.6581, "f_balanced": 0.7549, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1040, "chars": 4163, "content_recall": 0.5675, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6212, "f_coverage": 0.6212, "f_balanced": 0.7241, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 778, "chars": 3115, "content_recall": 0.5878, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6406, "f_coverage": 0.6406, "f_balanced": 0.7404, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" }, "readability": { "method": "readability", "tokens": 818, "chars": 3274, "content_recall": 0.5305, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5855, "f_coverage": 0.5855, "f_balanced": 0.6932, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9549, "chars": 38198, "content_recall": 0.5749, "noise_retention": 0.2222, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.361, "f_precision": 0.6065, "f_coverage": 0.6065, "f_balanced": 0.6611, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9980, "chars": 39922, "content_recall": 0.5749, "noise_retention": 0.2222, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.303, "f_precision": 0.6065, "f_coverage": 0.6065, "f_balanced": 0.6611, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4306, "chars": 17224, "content_recall": 0.6932, "noise_retention": 0.6762, "noise_keyword_total": 11, "noise_per_1k_tokens": 2.555, "f_precision": 0.5644, "f_coverage": 0.5644, "f_balanced": 0.4414, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9531, "chars": 38125, "content_recall": 0.5749, "noise_retention": 0.2222, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.364, "f_precision": 0.6065, "f_coverage": 0.6065, "f_balanced": 0.6611, "anchor_diag": { "content_chars": 4665, "noise_chars": 5427, "content_ngrams": 541, "noise_ngrams": 315, "ambiguous_ngrams_removed": 0, "content_sentences": 45 }, "notes": "" } }, "scoreable": true }, "gcp-compute": { "meta": { "id": "gcp-compute", "url": "https://docs.cloud.google.com/compute/docs", "requested_url": "https://cloud.google.com/compute/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 289406 } }, "anchors": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1028, "chars": 4112, "content_recall": 0.6578, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7062, "f_coverage": 0.7062, "f_balanced": 0.7936, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1054, "chars": 4218, "content_recall": 0.6795, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7261, "f_coverage": 0.7261, "f_balanced": 0.8092, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1016, "chars": 4065, "content_recall": 0.653, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7017, "f_coverage": 0.7017, "f_balanced": 0.7901, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 675, "chars": 2702, "content_recall": 0.6217, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6726, "f_coverage": 0.6726, "f_balanced": 0.7667, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "readability": { "method": "readability", "tokens": 835, "chars": 3341, "content_recall": 0.6578, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7062, "f_coverage": 0.7062, "f_balanced": 0.7936, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9144, "chars": 36576, "content_recall": 0.6843, "noise_retention": 0.2208, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.422, "f_precision": 0.7014, "f_coverage": 0.7014, "f_balanced": 0.7287, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9555, "chars": 38221, "content_recall": 0.6843, "noise_retention": 0.2208, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.361, "f_precision": 0.7014, "f_coverage": 0.7014, "f_balanced": 0.7287, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4117, "chars": 16470, "content_recall": 0.7542, "noise_retention": 0.6782, "noise_keyword_total": 11, "noise_per_1k_tokens": 2.672, "f_precision": 0.5944, "f_coverage": 0.5944, "f_balanced": 0.4511, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9124, "chars": 36497, "content_recall": 0.6843, "noise_retention": 0.2208, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.425, "f_precision": 0.7014, "f_coverage": 0.7014, "f_balanced": 0.7287, "anchor_diag": { "content_chars": 3639, "noise_chars": 5446, "content_ngrams": 415, "noise_ngrams": 317, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" } }, "scoreable": true }, "gcp-functions": { "meta": { "id": "gcp-functions", "url": "https://docs.cloud.google.com/functions/docs", "requested_url": "https://cloud.google.com/functions/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 266093 } }, "anchors": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 356, "chars": 1424, "content_recall": 0.5167, "noise_retention": 0.0031, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5718, "f_coverage": 0.5718, "f_balanced": 0.6806, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 406, "chars": 1624, "content_recall": 0.6111, "noise_retention": 0.0031, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6624, "f_coverage": 0.6624, "f_balanced": 0.7577, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 301, "chars": 1205, "content_recall": 0.3944, "noise_retention": 0.0031, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4487, "f_coverage": 0.4487, "f_balanced": 0.5652, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 207, "chars": 830, "content_recall": 0.4444, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5, "f_coverage": 0.5, "f_balanced": 0.6154, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" }, "readability": { "method": "readability", "tokens": 204, "chars": 816, "content_recall": 0.4833, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.539, "f_coverage": 0.539, "f_balanced": 0.6517, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8304, "chars": 33219, "content_recall": 0.5667, "noise_retention": 0.2215, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.566, "f_precision": 0.5993, "f_coverage": 0.5993, "f_balanced": 0.6559, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 8692, "chars": 34769, "content_recall": 0.5667, "noise_retention": 0.2215, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.496, "f_precision": 0.5993, "f_coverage": 0.5993, "f_balanced": 0.6559, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3472, "chars": 13888, "content_recall": 0.7389, "noise_retention": 0.6985, "noise_keyword_total": 11, "noise_per_1k_tokens": 3.168, "f_precision": 0.5727, "f_coverage": 0.5727, "f_balanced": 0.4283, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8281, "chars": 33126, "content_recall": 0.5667, "noise_retention": 0.2215, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.57, "f_precision": 0.5993, "f_coverage": 0.5993, "f_balanced": 0.6559, "anchor_diag": { "content_chars": 1861, "noise_chars": 5813, "content_ngrams": 180, "noise_ngrams": 325, "ambiguous_ngrams_removed": 5, "content_sentences": 19 }, "notes": "" } }, "scoreable": true }, "gcp-gke": { "meta": { "id": "gcp-gke", "url": "https://docs.cloud.google.com/kubernetes-engine/docs", "requested_url": "https://cloud.google.com/kubernetes-engine/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 292287 } }, "anchors": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 892, "chars": 3568, "content_recall": 0.557, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6111, "f_coverage": 0.6111, "f_balanced": 0.7154, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 908, "chars": 3635, "content_recall": 0.5717, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6253, "f_coverage": 0.6253, "f_balanced": 0.7275, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 845, "chars": 3382, "content_recall": 0.5084, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5639, "f_coverage": 0.5639, "f_balanced": 0.6741, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 651, "chars": 2604, "content_recall": 0.5781, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6313, "f_coverage": 0.6313, "f_balanced": 0.7326, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" }, "readability": { "method": "readability", "tokens": 620, "chars": 2481, "content_recall": 0.4388, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4943, "f_coverage": 0.4943, "f_balanced": 0.61, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9251, "chars": 37005, "content_recall": 0.6013, "noise_retention": 0.2194, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.405, "f_precision": 0.6302, "f_coverage": 0.6302, "f_balanced": 0.6793, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9656, "chars": 38626, "content_recall": 0.6013, "noise_retention": 0.2194, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.346, "f_precision": 0.6302, "f_coverage": 0.6302, "f_balanced": 0.6793, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4095, "chars": 16381, "content_recall": 0.7447, "noise_retention": 0.6803, "noise_keyword_total": 11, "noise_per_1k_tokens": 2.686, "f_precision": 0.5883, "f_coverage": 0.5883, "f_balanced": 0.4474, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9219, "chars": 36877, "content_recall": 0.6013, "noise_retention": 0.2194, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.41, "f_precision": 0.6302, "f_coverage": 0.6302, "f_balanced": 0.6793, "anchor_diag": { "content_chars": 4209, "noise_chars": 5463, "content_ngrams": 474, "noise_ngrams": 319, "ambiguous_ngrams_removed": 0, "content_sentences": 43 }, "notes": "" } }, "scoreable": true }, "gcp-pricing": { "meta": { "id": "gcp-pricing", "url": "https://cloud.google.com/pricing", "requested_url": "https://cloud.google.com/pricing", "category": "pricing", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 1982194 } }, "anchors": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 912, "chars": 3651, "content_recall": 0.6049, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6568, "f_coverage": 0.6568, "f_balanced": 0.7538, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1036, "chars": 4144, "content_recall": 0.6049, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6568, "f_coverage": 0.6568, "f_balanced": 0.7538, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 627, "chars": 2508, "content_recall": 0.466, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5218, "f_coverage": 0.5218, "f_balanced": 0.6358, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 444, "chars": 1777, "content_recall": 0.6543, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7029, "f_coverage": 0.7029, "f_balanced": 0.791, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "readability": { "method": "readability", "tokens": 9, "chars": 36, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 20462, "chars": 81850, "content_recall": 0.6975, "noise_retention": 0.1943, "noise_keyword_total": 10, "noise_per_1k_tokens": 0.489, "f_precision": 0.7168, "f_coverage": 0.7168, "f_balanced": 0.7477, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 20704, "chars": 82816, "content_recall": 0.6975, "noise_retention": 0.1714, "noise_keyword_total": 11, "noise_per_1k_tokens": 0.531, "f_precision": 0.7203, "f_coverage": 0.7203, "f_balanced": 0.7574, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 9335, "chars": 37343, "content_recall": 0.8395, "noise_retention": 0.9371, "noise_keyword_total": 7, "noise_per_1k_tokens": 0.75, "f_precision": 0.2419, "f_coverage": 0.2419, "f_balanced": 0.117, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 19359, "chars": 77436, "content_recall": 0.6975, "noise_retention": 0.0, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.258, "f_precision": 0.7424, "f_coverage": 0.7424, "f_balanced": 0.8218, "anchor_diag": { "content_chars": 2634, "noise_chars": 2817, "content_ngrams": 324, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" } }, "scoreable": true }, "gcp-storage": { "meta": { "id": "gcp-storage", "url": "https://docs.cloud.google.com/storage/docs", "requested_url": "https://cloud.google.com/storage/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 280777 } }, "anchors": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 785, "chars": 3143, "content_recall": 0.6013, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6534, "f_coverage": 0.6534, "f_balanced": 0.751, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 812, "chars": 3248, "content_recall": 0.6246, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6753, "f_coverage": 0.6753, "f_balanced": 0.7689, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 689, "chars": 2756, "content_recall": 0.588, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6408, "f_coverage": 0.6408, "f_balanced": 0.7406, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2114, "chars": 8457, "content_recall": 0.5847, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6377, "f_coverage": 0.6377, "f_balanced": 0.7379, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" }, "readability": { "method": "readability", "tokens": 611, "chars": 2447, "content_recall": 0.598, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6503, "f_coverage": 0.6503, "f_balanced": 0.7484, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8827, "chars": 35308, "content_recall": 0.6279, "noise_retention": 0.2215, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.473, "f_precision": 0.6532, "f_coverage": 0.6532, "f_balanced": 0.6951, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9228, "chars": 36915, "content_recall": 0.6279, "noise_retention": 0.2215, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.409, "f_precision": 0.6532, "f_coverage": 0.6532, "f_balanced": 0.6951, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3859, "chars": 15439, "content_recall": 0.7342, "noise_retention": 0.6772, "noise_keyword_total": 11, "noise_per_1k_tokens": 2.85, "f_precision": 0.5851, "f_coverage": 0.5851, "f_balanced": 0.4484, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8807, "chars": 35230, "content_recall": 0.6279, "noise_retention": 0.2215, "noise_keyword_total": 13, "noise_per_1k_tokens": 1.476, "f_precision": 0.6532, "f_coverage": 0.6532, "f_balanced": 0.6951, "anchor_diag": { "content_chars": 2908, "noise_chars": 5430, "content_ngrams": 301, "noise_ngrams": 316, "ambiguous_ngrams_removed": 0, "content_sentences": 35 }, "notes": "" } }, "scoreable": true }, "gensim-docs": { "meta": { "id": "gensim-docs", "url": "https://radimrehurek.com/gensim/", "requested_url": "https://radimrehurek.com/gensim/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 39646 } }, "anchors": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1433, "chars": 5734, "content_recall": 0.6494, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6984, "f_coverage": 0.6984, "f_balanced": 0.7874, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1493, "chars": 5972, "content_recall": 0.6594, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7076, "f_coverage": 0.7076, "f_balanced": 0.7948, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1316, "chars": 5265, "content_recall": 0.6411, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6906, "f_coverage": 0.6906, "f_balanced": 0.7813, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 528, "chars": 2113, "content_recall": 0.2538, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2983, "f_coverage": 0.2983, "f_balanced": 0.4048, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" }, "readability": { "method": "readability", "tokens": 112, "chars": 449, "content_recall": 0.0551, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0679, "f_coverage": 0.0679, "f_balanced": 0.1044, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2067, "chars": 8269, "content_recall": 0.7346, "noise_retention": 0.1111, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.761, "f_coverage": 0.761, "f_balanced": 0.8044, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2140, "chars": 8563, "content_recall": 0.7346, "noise_retention": 0.1111, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.761, "f_coverage": 0.761, "f_balanced": 0.8044, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1475, "chars": 5902, "content_recall": 0.803, "noise_retention": 0.5556, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6914, "f_coverage": 0.6914, "f_balanced": 0.5722, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2111, "chars": 8445, "content_recall": 0.7346, "noise_retention": 0.1111, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.761, "f_coverage": 0.761, "f_balanced": 0.8044, "anchor_diag": { "content_chars": 6501, "noise_chars": 254, "content_ngrams": 599, "noise_ngrams": 27, "ambiguous_ngrams_removed": 0, "content_sentences": 58 }, "notes": "" } }, "scoreable": true }, "github-actions-about": { "meta": { "id": "github-actions-about", "url": "https://docs.github.com/en/actions/get-started/understand-github-actions", "requested_url": "https://docs.github.com/en/actions/learn-github-actions/understanding-github-actions", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 311857 } }, "anchors": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1759, "chars": 7038, "content_recall": 0.8865, "noise_retention": 0.0303, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.902, "f_coverage": 0.902, "f_balanced": 0.9262, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1895, "chars": 7582, "content_recall": 0.9444, "noise_retention": 0.0303, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9494, "f_coverage": 0.9494, "f_balanced": 0.9569, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1527, "chars": 6110, "content_recall": 0.744, "noise_retention": 0.0303, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7803, "f_coverage": 0.7803, "f_balanced": 0.842, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1613, "chars": 6453, "content_recall": 0.9541, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9629, "f_coverage": 0.9629, "f_balanced": 0.9765, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1497, "chars": 5990, "content_recall": 0.9372, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9491, "f_coverage": 0.9491, "f_balanced": 0.9676, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 7588, "chars": 30355, "content_recall": 0.9191, "noise_retention": 0.4848, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7945, "f_coverage": 0.7945, "f_balanced": 0.6602, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 7721, "chars": 30885, "content_recall": 0.9191, "noise_retention": 0.4848, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7945, "f_coverage": 0.7945, "f_balanced": 0.6602, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3023, "chars": 12094, "content_recall": 0.9614, "noise_retention": 0.8182, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5176, "f_coverage": 0.5176, "f_balanced": 0.3058, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 7577, "chars": 30311, "content_recall": 0.9191, "noise_retention": 0.4848, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7945, "f_coverage": 0.7945, "f_balanced": 0.6602, "anchor_diag": { "content_chars": 6323, "noise_chars": 476, "content_ngrams": 828, "noise_ngrams": 66, "ambiguous_ngrams_removed": 0, "content_sentences": 61 }, "notes": "" } }, "scoreable": true }, "github-actions-quickstart": { "meta": { "id": "github-actions-quickstart", "url": "https://docs.github.com/en/actions/get-started/quickstart", "requested_url": "https://docs.github.com/en/actions/quickstart", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 355525 } }, "anchors": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1858, "chars": 7432, "content_recall": 0.8639, "noise_retention": 0.0132, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.886, "f_coverage": 0.886, "f_balanced": 0.9213, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1895, "chars": 7580, "content_recall": 0.887, "noise_retention": 0.0132, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9053, "f_coverage": 0.9053, "f_balanced": 0.9342, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1756, "chars": 7024, "content_recall": 0.7889, "noise_retention": 0.0132, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8219, "f_coverage": 0.8219, "f_balanced": 0.8769, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2032, "chars": 8131, "content_recall": 0.8962, "noise_retention": 0.0132, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.913, "f_coverage": 0.913, "f_balanced": 0.9393, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1637, "chars": 6548, "content_recall": 0.8547, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8803, "f_coverage": 0.8803, "f_balanced": 0.9216, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8396, "chars": 33585, "content_recall": 0.8247, "noise_retention": 0.4474, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7508, "f_coverage": 0.7508, "f_balanced": 0.6618, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 8562, "chars": 34251, "content_recall": 0.8247, "noise_retention": 0.5, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7299, "f_coverage": 0.7299, "f_balanced": 0.6226, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3424, "chars": 13698, "content_recall": 0.9008, "noise_retention": 0.7895, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.544, "f_coverage": 0.544, "f_balanced": 0.3413, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8385, "chars": 33540, "content_recall": 0.8247, "noise_retention": 0.4474, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7508, "f_coverage": 0.7508, "f_balanced": 0.6618, "anchor_diag": { "content_chars": 11738, "noise_chars": 1330, "content_ngrams": 867, "noise_ngrams": 76, "ambiguous_ngrams_removed": 97, "content_sentences": 86 }, "notes": "" } }, "scoreable": true }, "github-actions": { "meta": { "id": "github-actions", "url": "https://docs.github.com/en/actions", "requested_url": "https://docs.github.com/en/actions", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 432047 } }, "anchors": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 595, "chars": 2381, "content_recall": 0.7391, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7798, "f_coverage": 0.7798, "f_balanced": 0.85, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 595, "chars": 2381, "content_recall": 0.7391, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7798, "f_coverage": 0.7798, "f_balanced": 0.85, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 549, "chars": 2197, "content_recall": 0.6467, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6959, "f_coverage": 0.6959, "f_balanced": 0.7855, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 426, "chars": 1707, "content_recall": 0.7283, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7701, "f_coverage": 0.7701, "f_balanced": 0.8428, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" }, "readability": { "method": "readability", "tokens": 77, "chars": 310, "content_recall": 0.1576, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1895, "f_coverage": 0.1895, "f_balanced": 0.2723, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 6226, "chars": 24907, "content_recall": 0.7065, "noise_retention": 0.5472, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6353, "f_coverage": 0.6353, "f_balanced": 0.5519, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6381, "chars": 25526, "content_recall": 0.7065, "noise_retention": 0.5094, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6494, "f_coverage": 0.6494, "f_balanced": 0.5791, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1885, "chars": 7540, "content_recall": 0.7391, "noise_retention": 0.9245, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2679, "f_coverage": 0.2679, "f_balanced": 0.137, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 6217, "chars": 24869, "content_recall": 0.7065, "noise_retention": 0.5472, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6353, "f_coverage": 0.6353, "f_balanced": 0.5519, "anchor_diag": { "content_chars": 1413, "noise_chars": 396, "content_ngrams": 184, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 15 }, "notes": "" } }, "scoreable": true }, "github-codespaces": { "meta": { "id": "github-codespaces", "url": "https://docs.github.com/en/codespaces", "requested_url": "https://docs.github.com/en/codespaces", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 229637 } }, "anchors": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 643, "chars": 2573, "content_recall": 0.7831, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8186, "f_coverage": 0.8186, "f_balanced": 0.8784, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 653, "chars": 2614, "content_recall": 0.8072, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8396, "f_coverage": 0.8396, "f_balanced": 0.8933, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 577, "chars": 2310, "content_recall": 0.7108, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7545, "f_coverage": 0.7545, "f_balanced": 0.831, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 508, "chars": 2032, "content_recall": 0.9157, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9314, "f_coverage": 0.9314, "f_balanced": 0.956, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 46, "chars": 187, "content_recall": 0.0522, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0644, "f_coverage": 0.0644, "f_balanced": 0.0992, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3714, "chars": 14857, "content_recall": 0.7631, "noise_retention": 0.2444, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7616, "f_coverage": 0.7616, "f_balanced": 0.7593, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3766, "chars": 15066, "content_recall": 0.7631, "noise_retention": 0.2379, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7629, "f_coverage": 0.7629, "f_balanced": 0.7626, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1259, "chars": 5038, "content_recall": 0.7912, "noise_retention": 0.9614, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1614, "f_coverage": 0.1614, "f_balanced": 0.0736, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3705, "chars": 14823, "content_recall": 0.7631, "noise_retention": 0.2444, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7616, "f_coverage": 0.7616, "f_balanced": 0.7593, "anchor_diag": { "content_chars": 1961, "noise_chars": 4678, "content_ngrams": 249, "noise_ngrams": 311, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "github-copilot": { "meta": { "id": "github-copilot", "url": "https://docs.github.com/en/copilot", "requested_url": "https://docs.github.com/en/copilot", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 943846 } }, "anchors": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 447, "chars": 1789, "content_recall": 0.7248, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.767, "f_coverage": 0.767, "f_balanced": 0.8405, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 447, "chars": 1789, "content_recall": 0.7248, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.767, "f_coverage": 0.767, "f_balanced": 0.8405, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 420, "chars": 1680, "content_recall": 0.6711, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7184, "f_coverage": 0.7184, "f_balanced": 0.8032, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 313, "chars": 1254, "content_recall": 0.6644, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7122, "f_coverage": 0.7122, "f_balanced": 0.7984, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "readability": { "method": "readability", "tokens": 259, "chars": 1037, "content_recall": 0.5436, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5982, "f_coverage": 0.5982, "f_balanced": 0.7043, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 12836, "chars": 51346, "content_recall": 0.6376, "noise_retention": 0.5472, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.312, "f_precision": 0.5895, "f_coverage": 0.5895, "f_balanced": 0.5296, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 13218, "chars": 52872, "content_recall": 0.6376, "noise_retention": 0.5094, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.303, "f_precision": 0.6015, "f_coverage": 0.6015, "f_balanced": 0.5545, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3394, "chars": 13578, "content_recall": 0.7248, "noise_retention": 0.9245, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.589, "f_precision": 0.2664, "f_coverage": 0.2664, "f_balanced": 0.1367, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 12825, "chars": 51302, "content_recall": 0.6376, "noise_retention": 0.5472, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.312, "f_precision": 0.5895, "f_coverage": 0.5895, "f_balanced": 0.5296, "anchor_diag": { "content_chars": 1186, "noise_chars": 396, "content_ngrams": 149, "noise_ngrams": 53, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" } }, "scoreable": true }, "github-packages": { "meta": { "id": "github-packages", "url": "https://docs.github.com/en/packages", "requested_url": "https://docs.github.com/en/packages", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 115180 } }, "anchors": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 642, "chars": 2568, "content_recall": 0.8291, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8585, "f_coverage": 0.8585, "f_balanced": 0.9066, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 642, "chars": 2568, "content_recall": 0.8291, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8585, "f_coverage": 0.8585, "f_balanced": 0.9066, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 605, "chars": 2422, "content_recall": 0.7286, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7705, "f_coverage": 0.7705, "f_balanced": 0.843, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 488, "chars": 1953, "content_recall": 0.9397, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9512, "f_coverage": 0.9512, "f_balanced": 0.9689, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "readability": { "method": "readability", "tokens": 71, "chars": 284, "content_recall": 0.1558, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1874, "f_coverage": 0.1874, "f_balanced": 0.2696, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1689, "chars": 6756, "content_recall": 0.7889, "noise_retention": 0.3761, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7493, "f_coverage": 0.7493, "f_balanced": 0.6968, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1694, "chars": 6779, "content_recall": 0.7889, "noise_retention": 0.3761, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7493, "f_coverage": 0.7493, "f_balanced": 0.6968, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 815, "chars": 3262, "content_recall": 0.8141, "noise_retention": 0.8718, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3933, "f_coverage": 0.3933, "f_balanced": 0.2215, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1679, "chars": 6717, "content_recall": 0.7889, "noise_retention": 0.3761, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7493, "f_coverage": 0.7493, "f_balanced": 0.6968, "anchor_diag": { "content_chars": 1798, "noise_chars": 1398, "content_ngrams": 199, "noise_ngrams": 117, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" } }, "scoreable": true }, "gitlab-ci": { "meta": { "id": "gitlab-ci", "url": "https://docs.gitlab.com/ci/", "requested_url": "https://docs.gitlab.com/ee/ci/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 39830 } }, "anchors": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1269, "chars": 5079, "content_recall": 0.8754, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8978, "f_coverage": 0.8978, "f_balanced": 0.9336, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1333, "chars": 5332, "content_recall": 0.9054, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9228, "f_coverage": 0.9228, "f_balanced": 0.9503, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1053, "chars": 4214, "content_recall": 0.7098, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7535, "f_coverage": 0.7535, "f_balanced": 0.8303, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1293, "chars": 5174, "content_recall": 0.9369, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9489, "f_coverage": 0.9489, "f_balanced": 0.9674, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1235, "chars": 4940, "content_recall": 0.9243, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9385, "f_coverage": 0.9385, "f_balanced": 0.9607, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2507, "chars": 10031, "content_recall": 0.9322, "noise_retention": 0.1354, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.399, "f_precision": 0.9178, "f_coverage": 0.9178, "f_balanced": 0.8971, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2495, "chars": 9980, "content_recall": 0.9322, "noise_retention": 0.2188, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.401, "f_precision": 0.8975, "f_coverage": 0.8975, "f_balanced": 0.8501, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1661, "chars": 6644, "content_recall": 0.9495, "noise_retention": 0.875, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.602, "f_precision": 0.4094, "f_coverage": 0.4094, "f_balanced": 0.2209, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2496, "chars": 9986, "content_recall": 0.9322, "noise_retention": 0.1354, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.401, "f_precision": 0.9178, "f_coverage": 0.9178, "f_balanced": 0.8971, "anchor_diag": { "content_chars": 5780, "noise_chars": 2355, "content_ngrams": 634, "noise_ngrams": 96, "ambiguous_ngrams_removed": 92, "content_sentences": 55 }, "notes": "" } }, "scoreable": true }, "gitlab-docs": { "meta": { "id": "gitlab-docs", "url": "https://docs.gitlab.com/", "requested_url": "https://docs.gitlab.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 28405 } }, "anchors": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 672, "chars": 2688, "content_recall": 0.662, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.488, "f_precision": 0.71, "f_coverage": 0.71, "f_balanced": 0.7966, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 733, "chars": 2934, "content_recall": 0.7718, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.364, "f_precision": 0.8087, "f_coverage": 0.8087, "f_balanced": 0.8712, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 555, "chars": 2221, "content_recall": 0.4254, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4806, "f_coverage": 0.4806, "f_balanced": 0.5968, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 188, "chars": 754, "content_recall": 0.1296, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1569, "f_coverage": 0.1569, "f_balanced": 0.2294, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "readability": { "method": "readability", "tokens": 578, "chars": 2315, "content_recall": 0.7408, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.73, "f_precision": 0.7813, "f_coverage": 0.7813, "f_balanced": 0.8511, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1496, "chars": 5987, "content_recall": 0.5775, "noise_retention": 0.1087, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.668, "f_precision": 0.6212, "f_coverage": 0.6212, "f_balanced": 0.7009, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1488, "chars": 5953, "content_recall": 0.3183, "noise_retention": 0.1087, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.672, "f_precision": 0.3653, "f_coverage": 0.3653, "f_balanced": 0.4691, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 780, "chars": 3121, "content_recall": 0.7718, "noise_retention": 0.913, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.282, "f_precision": 0.2997, "f_coverage": 0.2997, "f_balanced": 0.1563, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1493, "chars": 5974, "content_recall": 0.5775, "noise_retention": 0.1087, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.67, "f_precision": 0.6212, "f_coverage": 0.6212, "f_balanced": 0.7009, "anchor_diag": { "content_chars": 3686, "noise_chars": 366, "content_ngrams": 355, "noise_ngrams": 46, "ambiguous_ngrams_removed": 0, "content_sentences": 48 }, "notes": "" } }, "scoreable": true }, "go-docs": { "meta": { "id": "go-docs", "url": "https://go.dev/doc/", "requested_url": "https://go.dev/doc/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 47871 } }, "anchors": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2659, "chars": 10637, "content_recall": 0.8258, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8556, "f_coverage": 0.8556, "f_balanced": 0.9046, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2715, "chars": 10861, "content_recall": 0.8317, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8606, "f_coverage": 0.8606, "f_balanced": 0.9081, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2360, "chars": 9443, "content_recall": 0.725, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7672, "f_coverage": 0.7672, "f_balanced": 0.8406, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2684, "chars": 10738, "content_recall": 0.8508, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.877, "f_coverage": 0.877, "f_balanced": 0.9194, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1922, "chars": 7690, "content_recall": 0.72, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7627, "f_coverage": 0.7627, "f_balanced": 0.8372, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4718, "chars": 18874, "content_recall": 0.73, "noise_retention": 0.3906, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.636, "f_precision": 0.7022, "f_coverage": 0.7022, "f_balanced": 0.6643, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4747, "chars": 18990, "content_recall": 0.73, "noise_retention": 0.3945, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.632, "f_precision": 0.7012, "f_coverage": 0.7012, "f_balanced": 0.6619, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3143, "chars": 12574, "content_recall": 0.8583, "noise_retention": 0.9062, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.636, "f_precision": 0.3262, "f_coverage": 0.3262, "f_balanced": 0.169, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4694, "chars": 18779, "content_recall": 0.73, "noise_retention": 0.3906, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.639, "f_precision": 0.7022, "f_coverage": 0.7022, "f_balanced": 0.6643, "anchor_diag": { "content_chars": 9418, "noise_chars": 3559, "content_ngrams": 1200, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 95 }, "notes": "" } }, "scoreable": true }, "go-effective": { "meta": { "id": "go-effective", "url": "https://go.dev/doc/effective_go", "requested_url": "https://go.dev/doc/effective_go", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 142913 } }, "anchors": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 25188, "chars": 100753, "content_recall": 0.9587, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9667, "f_coverage": 0.9667, "f_balanced": 0.9789, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 25417, "chars": 101668, "content_recall": 0.9692, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9752, "f_coverage": 0.9752, "f_balanced": 0.9844, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 21867, "chars": 87468, "content_recall": 0.8091, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8412, "f_coverage": 0.8412, "f_balanced": 0.8945, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 25351, "chars": 101407, "content_recall": 0.9749, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9798, "f_coverage": 0.9798, "f_balanced": 0.9873, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" }, "readability": { "method": "readability", "tokens": 24713, "chars": 98854, "content_recall": 0.9749, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9798, "f_coverage": 0.9798, "f_balanced": 0.9873, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 26892, "chars": 107571, "content_recall": 0.9696, "noise_retention": 0.3906, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.112, "f_precision": 0.8671, "f_coverage": 0.8671, "f_balanced": 0.7484, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 28161, "chars": 112645, "content_recall": 0.9714, "noise_retention": 0.3945, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.107, "f_precision": 0.8667, "f_coverage": 0.8667, "f_balanced": 0.746, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 25190, "chars": 100761, "content_recall": 0.9749, "noise_retention": 0.9062, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.079, "f_precision": 0.3385, "f_coverage": 0.3385, "f_balanced": 0.1711, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 26910, "chars": 107643, "content_recall": 0.9686, "noise_retention": 0.3906, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.111, "f_precision": 0.8664, "f_coverage": 0.8664, "f_balanced": 0.7481, "anchor_diag": { "content_chars": 96529, "noise_chars": 3559, "content_ngrams": 11943, "noise_ngrams": 256, "ambiguous_ngrams_removed": 0, "content_sentences": 821 }, "notes": "" } }, "scoreable": true }, "gradle-docs": { "meta": { "id": "gradle-docs", "url": "https://docs.gradle.org/current/userguide/userguide.html", "requested_url": "https://docs.gradle.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 169972 } }, "anchors": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1033, "chars": 4134, "content_recall": 0.727, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.769, "f_coverage": 0.769, "f_balanced": 0.8419, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1033, "chars": 4134, "content_recall": 0.727, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.769, "f_coverage": 0.769, "f_balanced": 0.8419, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 925, "chars": 3700, "content_recall": 0.6258, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6764, "f_coverage": 0.6764, "f_balanced": 0.7698, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 572, "chars": 2289, "content_recall": 0.6871, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.733, "f_coverage": 0.733, "f_balanced": 0.8145, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" }, "readability": { "method": "readability", "tokens": 327, "chars": 1311, "content_recall": 0.454, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5096, "f_coverage": 0.5096, "f_balanced": 0.6245, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 6585, "chars": 26343, "content_recall": 0.7086, "noise_retention": 0.1644, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.607, "f_precision": 0.7308, "f_coverage": 0.7308, "f_balanced": 0.7669, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6362, "chars": 25451, "content_recall": 0.7301, "noise_retention": 0.1644, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.629, "f_precision": 0.749, "f_coverage": 0.749, "f_balanced": 0.7793, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2724, "chars": 10898, "content_recall": 0.7791, "noise_retention": 0.6849, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.101, "f_precision": 0.6018, "f_coverage": 0.6018, "f_balanced": 0.4487, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 6568, "chars": 26273, "content_recall": 0.7086, "noise_retention": 0.1644, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.609, "f_precision": 0.7308, "f_coverage": 0.7308, "f_balanced": 0.7669, "anchor_diag": { "content_chars": 2725, "noise_chars": 1601, "content_ngrams": 326, "noise_ngrams": 73, "ambiguous_ngrams_removed": 11, "content_sentences": 23 }, "notes": "" } }, "scoreable": true }, "grafana-docs": { "meta": { "id": "grafana-docs", "url": "https://grafana.com/docs/", "requested_url": "https://grafana.com/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 126071 } }, "anchors": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1157, "chars": 4628, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1157, "chars": 4628, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 925, "chars": 3703, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 332, "chars": 1328, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 33, "chars": 133, "content_recall": 0.0, "noise_retention": 0.04, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4161, "chars": 16646, "content_recall": 0.0, "noise_retention": 0.2222, "noise_keyword_total": 11, "noise_per_1k_tokens": 2.644, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4189, "chars": 16758, "content_recall": 0.0, "noise_retention": 0.2222, "noise_keyword_total": 11, "noise_per_1k_tokens": 2.626, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1637, "chars": 6549, "content_recall": 0.0, "noise_retention": 0.92, "noise_keyword_total": 8, "noise_per_1k_tokens": 4.887, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3861, "chars": 15447, "content_recall": 0.0, "noise_retention": 0.2222, "noise_keyword_total": 11, "noise_per_1k_tokens": 2.849, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 3534, "content_ngrams": 0, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "grafana-loki": { "meta": { "id": "grafana-loki", "url": "https://grafana.com/docs/loki/latest/", "requested_url": "https://grafana.com/docs/loki/latest/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 194270 } }, "anchors": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 3352, "chars": 13411, "content_recall": 0.901, "noise_retention": 0.0013, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.919, "f_coverage": 0.919, "f_balanced": 0.9473, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 3362, "chars": 13448, "content_recall": 0.9028, "noise_retention": 0.0013, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9205, "f_coverage": 0.9205, "f_balanced": 0.9483, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2952, "chars": 11809, "content_recall": 0.7696, "noise_retention": 0.0064, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8059, "f_coverage": 0.8059, "f_balanced": 0.8674, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2927, "chars": 11708, "content_recall": 0.8073, "noise_retention": 0.0013, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8395, "f_coverage": 0.8395, "f_balanced": 0.8929, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2725, "chars": 10902, "content_recall": 0.7661, "noise_retention": 0.0026, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8033, "f_coverage": 0.8033, "f_balanced": 0.8666, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9671, "chars": 38687, "content_recall": 0.8586, "noise_retention": 0.2138, "noise_keyword_total": 11, "noise_per_1k_tokens": 1.137, "f_precision": 0.843, "f_coverage": 0.843, "f_balanced": 0.8208, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9833, "chars": 39334, "content_recall": 0.835, "noise_retention": 0.2177, "noise_keyword_total": 11, "noise_per_1k_tokens": 1.119, "f_precision": 0.8239, "f_coverage": 0.8239, "f_balanced": 0.8078, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 5111, "chars": 20445, "content_recall": 0.9116, "noise_retention": 0.9616, "noise_keyword_total": 8, "noise_per_1k_tokens": 1.565, "f_precision": 0.1644, "f_coverage": 0.1644, "f_balanced": 0.0737, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9661, "chars": 38646, "content_recall": 0.8592, "noise_retention": 0.2138, "noise_keyword_total": 11, "noise_per_1k_tokens": 1.139, "f_precision": 0.8435, "f_coverage": 0.8435, "f_balanced": 0.821, "anchor_diag": { "content_chars": 15270, "noise_chars": 8822, "content_ngrams": 1697, "noise_ngrams": 781, "ambiguous_ngrams_removed": 40, "content_sentences": 139 }, "notes": "" } }, "scoreable": true }, "grafana-tempo": { "meta": { "id": "grafana-tempo", "url": "https://grafana.com/docs/tempo/latest/", "requested_url": "https://grafana.com/docs/tempo/latest/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 173156 } }, "anchors": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 761, "chars": 3044, "content_recall": 0.8647, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8888, "f_coverage": 0.8888, "f_balanced": 0.9275, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 761, "chars": 3044, "content_recall": 0.8647, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8888, "f_coverage": 0.8888, "f_balanced": 0.9275, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 579, "chars": 2318, "content_recall": 0.6329, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.683, "f_coverage": 0.683, "f_balanced": 0.7751, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 510, "chars": 2043, "content_recall": 0.6256, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6762, "f_coverage": 0.6762, "f_balanced": 0.7697, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "readability": { "method": "readability", "tokens": 315, "chars": 1262, "content_recall": 0.4082, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.463, "f_coverage": 0.463, "f_balanced": 0.5798, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 6503, "chars": 26012, "content_recall": 0.7415, "noise_retention": 0.1864, "noise_keyword_total": 11, "noise_per_1k_tokens": 1.692, "f_precision": 0.7549, "f_coverage": 0.7549, "f_balanced": 0.7759, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6705, "chars": 26822, "content_recall": 0.6353, "noise_retention": 0.1908, "noise_keyword_total": 11, "noise_per_1k_tokens": 1.641, "f_precision": 0.6638, "f_coverage": 0.6638, "f_balanced": 0.7118, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2299, "chars": 9197, "content_recall": 0.8647, "noise_retention": 0.9624, "noise_keyword_total": 8, "noise_per_1k_tokens": 3.48, "f_precision": 0.16, "f_coverage": 0.16, "f_balanced": 0.072, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 6504, "chars": 26017, "content_recall": 0.744, "noise_retention": 0.1864, "noise_keyword_total": 11, "noise_per_1k_tokens": 1.691, "f_precision": 0.7569, "f_coverage": 0.7569, "f_balanced": 0.7772, "anchor_diag": { "content_chars": 4256, "noise_chars": 7225, "content_ngrams": 414, "noise_ngrams": 692, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" } }, "scoreable": true }, "graphql-spec": { "meta": { "id": "graphql-spec", "url": "https://graphql.org/learn/", "requested_url": "https://graphql.org/learn/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 125500 } }, "anchors": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 132, "chars": 530, "content_recall": 0.0533, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0658, "f_coverage": 0.0658, "f_balanced": 0.1013, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 132, "chars": 530, "content_recall": 0.0533, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0658, "f_coverage": 0.0658, "f_balanced": 0.1013, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 132, "chars": 530, "content_recall": 0.0533, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0658, "f_coverage": 0.0658, "f_balanced": 0.1013, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1091, "chars": 4364, "content_recall": 0.512, "noise_retention": 0.4487, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5194, "f_coverage": 0.5194, "f_balanced": 0.5309, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" }, "readability": { "method": "readability", "tokens": 12, "chars": 49, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2399, "chars": 9599, "content_recall": 0.576, "noise_retention": 0.5962, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5307, "f_coverage": 0.5307, "f_balanced": 0.4748, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2414, "chars": 9658, "content_recall": 0.4787, "noise_retention": 0.5833, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4648, "f_coverage": 0.4648, "f_balanced": 0.4455, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1577, "chars": 6310, "content_recall": 0.7947, "noise_retention": 0.8846, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.365, "f_coverage": 0.365, "f_balanced": 0.2015, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2394, "chars": 9578, "content_recall": 0.576, "noise_retention": 0.5962, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5307, "f_coverage": 0.5307, "f_balanced": 0.4748, "anchor_diag": { "content_chars": 8192, "noise_chars": 1293, "content_ngrams": 750, "noise_ngrams": 156, "ambiguous_ngrams_removed": 1, "content_sentences": 75 }, "notes": "" } }, "scoreable": true }, "grpc-docs": { "meta": { "id": "grpc-docs", "url": "https://grpc.io/docs/", "requested_url": "https://grpc.io/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": true, "bytes": 67897 } }, "anchors": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 445, "chars": 1783, "content_recall": 0.3269, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3778, "f_coverage": 0.3778, "f_balanced": 0.4928, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 480, "chars": 1921, "content_recall": 0.4808, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5365, "f_coverage": 0.5365, "f_balanced": 0.6494, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 398, "chars": 1595, "content_recall": 0.3269, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3778, "f_coverage": 0.3778, "f_balanced": 0.4928, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 307, "chars": 1231, "content_recall": 0.4615, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5172, "f_coverage": 0.5172, "f_balanced": 0.6316, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" }, "readability": { "method": "readability", "tokens": 276, "chars": 1104, "content_recall": 0.4615, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5172, "f_coverage": 0.5172, "f_balanced": 0.6316, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2731, "chars": 10925, "content_recall": 0.4423, "noise_retention": 0.09, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.493, "f_coverage": 0.493, "f_balanced": 0.5953, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2832, "chars": 11330, "content_recall": 0.4423, "noise_retention": 0.09, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.493, "f_coverage": 0.493, "f_balanced": 0.5953, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 731, "chars": 2926, "content_recall": 0.6154, "noise_retention": 0.94, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2158, "f_coverage": 0.2158, "f_balanced": 0.1093, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2726, "chars": 10904, "content_recall": 0.4423, "noise_retention": 0.09, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.493, "f_coverage": 0.493, "f_balanced": 0.5953, "anchor_diag": { "content_chars": 1044, "noise_chars": 2887, "content_ngrams": 104, "noise_ngrams": 200, "ambiguous_ngrams_removed": 11, "content_sentences": 11 }, "notes": "" } }, "scoreable": true }, "hashicorp-consul": { "meta": { "id": "hashicorp-consul", "url": "https://developer.hashicorp.com/consul/docs", "requested_url": "https://developer.hashicorp.com/consul/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 259595 } }, "anchors": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1178, "chars": 4714, "content_recall": 0.8169, "noise_retention": 0.0095, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8465, "f_coverage": 0.8465, "f_balanced": 0.8953, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1222, "chars": 4890, "content_recall": 0.825, "noise_retention": 0.0095, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8535, "f_coverage": 0.8535, "f_balanced": 0.9002, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1013, "chars": 4053, "content_recall": 0.6532, "noise_retention": 0.0095, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7009, "f_coverage": 0.7009, "f_balanced": 0.7872, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 380, "chars": 1522, "content_recall": 0.1313, "noise_retention": 0.1804, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1578, "f_coverage": 0.1578, "f_balanced": 0.2263, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1081, "chars": 4324, "content_recall": 0.8314, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8604, "f_coverage": 0.8604, "f_balanced": 0.908, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2449, "chars": 9797, "content_recall": 0.825, "noise_retention": 0.5253, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.817, "f_precision": 0.7189, "f_coverage": 0.7189, "f_balanced": 0.6026, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2928, "chars": 11713, "content_recall": 0.6742, "noise_retention": 0.4905, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.683, "f_precision": 0.6333, "f_coverage": 0.6333, "f_balanced": 0.5804, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1878, "chars": 7515, "content_recall": 0.825, "noise_retention": 0.9367, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.065, "f_precision": 0.2421, "f_coverage": 0.2421, "f_balanced": 0.1176, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2436, "chars": 9744, "content_recall": 0.825, "noise_retention": 0.5253, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.821, "f_precision": 0.7189, "f_coverage": 0.7189, "f_balanced": 0.6026, "anchor_diag": { "content_chars": 6987, "noise_chars": 3647, "content_ngrams": 617, "noise_ngrams": 316, "ambiguous_ngrams_removed": 2, "content_sentences": 56 }, "notes": "" } }, "scoreable": true }, "hashicorp-nomad": { "meta": { "id": "hashicorp-nomad", "url": "https://developer.hashicorp.com/nomad/docs", "requested_url": "https://developer.hashicorp.com/nomad/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 186128 } }, "anchors": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 685, "chars": 2740, "content_recall": 0.7825, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8181, "f_coverage": 0.8181, "f_balanced": 0.878, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 693, "chars": 2774, "content_recall": 0.7825, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8181, "f_coverage": 0.8181, "f_balanced": 0.878, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 506, "chars": 2025, "content_recall": 0.4924, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5481, "f_coverage": 0.5481, "f_balanced": 0.6599, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 156, "chars": 626, "content_recall": 0.0725, "noise_retention": 0.0862, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0889, "f_coverage": 0.0889, "f_balanced": 0.1344, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "readability": { "method": "readability", "tokens": 548, "chars": 2194, "content_recall": 0.8308, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8599, "f_coverage": 0.8599, "f_balanced": 0.9076, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1818, "chars": 7275, "content_recall": 0.7825, "noise_retention": 0.4138, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.1, "f_precision": 0.7334, "f_coverage": 0.7334, "f_balanced": 0.6703, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2110, "chars": 8443, "content_recall": 0.6042, "noise_retention": 0.369, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.948, "f_precision": 0.6094, "f_coverage": 0.6094, "f_balanced": 0.6173, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1197, "chars": 4789, "content_recall": 0.7825, "noise_retention": 0.931, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.671, "f_precision": 0.2549, "f_coverage": 0.2549, "f_balanced": 0.1268, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1807, "chars": 7230, "content_recall": 0.7825, "noise_retention": 0.4138, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.107, "f_precision": 0.7334, "f_coverage": 0.7334, "f_balanced": 0.6703, "anchor_diag": { "content_chars": 3458, "noise_chars": 3327, "content_ngrams": 331, "noise_ngrams": 290, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" } }, "scoreable": true }, "hashicorp-terraform": { "meta": { "id": "hashicorp-terraform", "url": "https://developer.hashicorp.com/terraform/docs", "requested_url": "https://developer.hashicorp.com/terraform/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 103980 } }, "anchors": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 381, "chars": 1524, "content_recall": 0.6235, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6742, "f_coverage": 0.6742, "f_balanced": 0.7681, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 402, "chars": 1610, "content_recall": 0.679, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7256, "f_coverage": 0.7256, "f_balanced": 0.8088, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 325, "chars": 1302, "content_recall": 0.463, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5187, "f_coverage": 0.5187, "f_balanced": 0.6329, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 363, "chars": 1453, "content_recall": 0.679, "noise_retention": 0.1328, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7098, "f_coverage": 0.7098, "f_balanced": 0.7617, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" }, "readability": { "method": "readability", "tokens": 360, "chars": 1443, "content_recall": 0.7531, "noise_retention": 0.1411, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7721, "f_coverage": 0.7721, "f_balanced": 0.8025, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1435, "chars": 5743, "content_recall": 0.679, "noise_retention": 0.278, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.394, "f_precision": 0.6872, "f_coverage": 0.6872, "f_balanced": 0.6998, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1556, "chars": 6226, "content_recall": 0.5494, "noise_retention": 0.2365, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.285, "f_precision": 0.582, "f_coverage": 0.582, "f_balanced": 0.639, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 842, "chars": 3370, "content_recall": 0.679, "noise_retention": 0.9212, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.375, "f_precision": 0.2692, "f_coverage": 0.2692, "f_balanced": 0.1413, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1422, "chars": 5689, "content_recall": 0.679, "noise_retention": 0.278, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.406, "f_precision": 0.6872, "f_coverage": 0.6872, "f_balanced": 0.6998, "anchor_diag": { "content_chars": 1967, "noise_chars": 3071, "content_ngrams": 162, "noise_ngrams": 241, "ambiguous_ngrams_removed": 1, "content_sentences": 22 }, "notes": "" } }, "scoreable": true }, "hashicorp-vault": { "meta": { "id": "hashicorp-vault", "url": "https://developer.hashicorp.com/vault/docs", "requested_url": "https://developer.hashicorp.com/vault/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 241834 } }, "anchors": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 301, "chars": 1205, "content_recall": 0.7586, "noise_retention": 0.0446, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7912, "f_coverage": 0.7912, "f_balanced": 0.8457, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 301, "chars": 1205, "content_recall": 0.7586, "noise_retention": 0.0446, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7912, "f_coverage": 0.7912, "f_balanced": 0.8457, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 266, "chars": 1067, "content_recall": 0.5776, "noise_retention": 0.0446, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6272, "f_coverage": 0.6272, "f_balanced": 0.7199, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 115, "chars": 462, "content_recall": 0.0, "noise_retention": 0.1078, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" }, "readability": { "method": "readability", "tokens": 242, "chars": 968, "content_recall": 0.7586, "noise_retention": 0.052, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7902, "f_coverage": 0.7902, "f_balanced": 0.8428, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1440, "chars": 5763, "content_recall": 0.7586, "noise_retention": 0.4201, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.389, "f_precision": 0.7146, "f_coverage": 0.7146, "f_balanced": 0.6573, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1707, "chars": 6829, "content_recall": 0.5862, "noise_retention": 0.3532, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.172, "f_precision": 0.5974, "f_coverage": 0.5974, "f_balanced": 0.615, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 843, "chars": 3375, "content_recall": 0.7586, "noise_retention": 0.9257, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.372, "f_precision": 0.2671, "f_coverage": 0.2671, "f_balanced": 0.1354, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1426, "chars": 5704, "content_recall": 0.7586, "noise_retention": 0.4201, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.403, "f_precision": 0.7146, "f_coverage": 0.7146, "f_balanced": 0.6573, "anchor_diag": { "content_chars": 1363, "noise_chars": 3268, "content_ngrams": 116, "noise_ngrams": 269, "ambiguous_ngrams_removed": 2, "content_sentences": 13 }, "notes": "" } }, "scoreable": true }, "helm-docs": { "meta": { "id": "helm-docs", "url": "https://helm.sh/docs/", "requested_url": "https://helm.sh/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 30151 } }, "anchors": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 243, "chars": 975, "content_recall": 0.475, "noise_retention": 0.0687, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5266, "f_coverage": 0.5266, "f_balanced": 0.6291, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 243, "chars": 975, "content_recall": 0.475, "noise_retention": 0.0687, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5266, "f_coverage": 0.5266, "f_balanced": 0.6291, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 171, "chars": 686, "content_recall": 0.2833, "noise_retention": 0.084, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3287, "f_coverage": 0.3287, "f_balanced": 0.4328, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 204, "chars": 816, "content_recall": 0.725, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7672, "f_coverage": 0.7672, "f_balanced": 0.8406, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "readability": { "method": "readability", "tokens": 5, "chars": 21, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1024, "chars": 4096, "content_recall": 0.4417, "noise_retention": 0.2519, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4811, "f_coverage": 0.4811, "f_balanced": 0.5554, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 998, "chars": 3995, "content_recall": 0.35, "noise_retention": 0.2519, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3917, "f_coverage": 0.3917, "f_balanced": 0.4769, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 490, "chars": 1960, "content_recall": 0.8083, "noise_retention": 0.9084, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3152, "f_coverage": 0.3152, "f_balanced": 0.1646, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1017, "chars": 4070, "content_recall": 0.4417, "noise_retention": 0.2519, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4811, "f_coverage": 0.4811, "f_balanced": 0.5554, "anchor_diag": { "content_chars": 1991, "noise_chars": 1236, "content_ngrams": 120, "noise_ngrams": 131, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" } }, "scoreable": true }, "heroku-docs": { "meta": { "id": "heroku-docs", "url": "https://devcenter.heroku.com/", "requested_url": "https://devcenter.heroku.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 173699 } }, "anchors": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 47, "chars": 189, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 21.277, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 47, "chars": 189, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 21.277, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 47, "chars": 189, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 21.277, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 224, "chars": 897, "content_recall": 0.6, "noise_retention": 0.3419, "noise_keyword_total": 3, "noise_per_1k_tokens": 13.393, "f_precision": 0.6108, "f_coverage": 0.6108, "f_balanced": 0.6277, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "readability": { "method": "readability", "tokens": 22, "chars": 89, "content_recall": 0.0, "noise_retention": 0.0516, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1400, "chars": 5603, "content_recall": 0.5, "noise_retention": 0.2065, "noise_keyword_total": 7, "noise_per_1k_tokens": 5.0, "f_precision": 0.5399, "f_coverage": 0.5399, "f_balanced": 0.6135, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1434, "chars": 5739, "content_recall": 0.5, "noise_retention": 0.2065, "noise_keyword_total": 7, "noise_per_1k_tokens": 4.881, "f_precision": 0.5399, "f_coverage": 0.5399, "f_balanced": 0.6135, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 418, "chars": 1672, "content_recall": 0.6, "noise_retention": 0.9226, "noise_keyword_total": 5, "noise_per_1k_tokens": 11.962, "f_precision": 0.2553, "f_coverage": 0.2553, "f_balanced": 0.1371, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1390, "chars": 5563, "content_recall": 0.5, "noise_retention": 0.2065, "noise_keyword_total": 7, "noise_per_1k_tokens": 5.036, "f_precision": 0.5399, "f_coverage": 0.5399, "f_balanced": 0.6135, "anchor_diag": { "content_chars": 101, "noise_chars": 1783, "content_ngrams": 10, "noise_ngrams": 155, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" } }, "scoreable": false }, "hetzner-docs": { "meta": { "id": "hetzner-docs", "url": "https://docs.hetzner.com/", "requested_url": "https://docs.hetzner.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 349381 } }, "anchors": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 309, "chars": 1238, "content_recall": 0.5745, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6279, "f_coverage": 0.6279, "f_balanced": 0.7297, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 319, "chars": 1277, "content_recall": 0.5904, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6431, "f_coverage": 0.6431, "f_balanced": 0.7425, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 298, "chars": 1195, "content_recall": 0.5319, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5869, "f_coverage": 0.5869, "f_balanced": 0.6944, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 108, "chars": 434, "content_recall": 0.2394, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2823, "f_coverage": 0.2823, "f_balanced": 0.3863, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 86, "chars": 345, "content_recall": 0.2021, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2405, "f_coverage": 0.2405, "f_balanced": 0.3363, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2138, "chars": 8554, "content_recall": 0.5745, "noise_retention": 0.4118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5772, "f_coverage": 0.5772, "f_balanced": 0.5813, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2144, "chars": 8579, "content_recall": 0.5745, "noise_retention": 0.4118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5772, "f_coverage": 0.5772, "f_balanced": 0.5813, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 357, "chars": 1428, "content_recall": 0.7234, "noise_retention": 0.7647, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5113, "f_coverage": 0.5113, "f_balanced": 0.3551, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 570, "chars": 2282, "content_recall": 0.5745, "noise_retention": 0.4118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5772, "f_coverage": 0.5772, "f_balanced": 0.5813, "anchor_diag": { "content_chars": 1818, "noise_chars": 151, "content_ngrams": 188, "noise_ngrams": 17, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "hubspot-docs": { "meta": { "id": "hubspot-docs", "url": "https://developers.hubspot.com/docs/api-reference/latest/overview", "requested_url": "https://developers.hubspot.com/docs/api/overview", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 1417783 } }, "anchors": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 85, "chars": 342, "content_recall": 1.0, "noise_retention": 0.0714, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9848, "f_coverage": 0.9848, "f_balanced": 0.963, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 85, "chars": 342, "content_recall": 1.0, "noise_retention": 0.0714, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9848, "f_coverage": 0.9848, "f_balanced": 0.963, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 65, "chars": 262, "content_recall": 0.0, "noise_retention": 0.0714, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 186, "chars": 745, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 239, "chars": 958, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 682, "chars": 2729, "content_recall": 1.0, "noise_retention": 0.2143, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.933, "f_precision": 0.9483, "f_coverage": 0.9483, "f_balanced": 0.88, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 782, "chars": 3131, "content_recall": 1.0, "noise_retention": 0.2143, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.558, "f_precision": 0.9483, "f_coverage": 0.9483, "f_balanced": 0.88, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 392, "chars": 1568, "content_recall": 1.0, "noise_retention": 0.6071, "noise_keyword_total": 2, "noise_per_1k_tokens": 5.102, "f_precision": 0.7639, "f_coverage": 0.7639, "f_balanced": 0.5641, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 673, "chars": 2694, "content_recall": 1.0, "noise_retention": 0.2143, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.972, "f_precision": 0.9483, "f_coverage": 0.9483, "f_balanced": 0.88, "anchor_diag": { "content_chars": 33, "noise_chars": 267, "content_ngrams": 1, "noise_ngrams": 28, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "huggingface-docs": { "meta": { "id": "huggingface-docs", "url": "https://huggingface.co/docs", "requested_url": "https://huggingface.co/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 143537 } }, "anchors": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 588, "chars": 2352, "content_recall": 0.886, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9067, "f_coverage": 0.9067, "f_balanced": 0.9396, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 651, "chars": 2605, "content_recall": 0.9479, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9579, "f_coverage": 0.9579, "f_balanced": 0.9732, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 258, "chars": 1035, "content_recall": 0.2866, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3343, "f_coverage": 0.3343, "f_balanced": 0.4456, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 764, "chars": 3059, "content_recall": 0.4723, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.528, "f_coverage": 0.528, "f_balanced": 0.6416, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" }, "readability": { "method": "readability", "tokens": 27, "chars": 111, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1329, "chars": 5317, "content_recall": 0.4528, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.505, "f_precision": 0.5084, "f_coverage": 0.5084, "f_balanced": 0.6233, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1346, "chars": 5385, "content_recall": 0.4528, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.486, "f_precision": 0.5084, "f_coverage": 0.5084, "f_balanced": 0.6233, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 868, "chars": 3472, "content_recall": 0.4723, "noise_retention": 0.7612, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.304, "f_precision": 0.3951, "f_coverage": 0.3951, "f_balanced": 0.3172, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1318, "chars": 5272, "content_recall": 0.4528, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.517, "f_precision": 0.5084, "f_coverage": 0.5084, "f_balanced": 0.6233, "anchor_diag": { "content_chars": 2340, "noise_chars": 1177, "content_ngrams": 307, "noise_ngrams": 67, "ambiguous_ngrams_removed": 7, "content_sentences": 40 }, "notes": "" } }, "scoreable": true }, "huggingface-transformers": { "meta": { "id": "huggingface-transformers", "url": "https://huggingface.co/docs/transformers/index", "requested_url": "https://huggingface.co/docs/transformers/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 231424 } }, "anchors": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 934, "chars": 3736, "content_recall": 0.9051, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9226, "f_coverage": 0.9226, "f_balanced": 0.9502, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 941, "chars": 3764, "content_recall": 0.9051, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9226, "f_coverage": 0.9226, "f_balanced": 0.9502, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 812, "chars": 3251, "content_recall": 0.8205, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8511, "f_coverage": 0.8511, "f_balanced": 0.9014, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 778, "chars": 3114, "content_recall": 0.9256, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9396, "f_coverage": 0.9396, "f_balanced": 0.9614, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "readability": { "method": "readability", "tokens": 766, "chars": 3066, "content_recall": 0.9256, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9396, "f_coverage": 0.9396, "f_balanced": 0.9614, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1751, "chars": 7007, "content_recall": 0.859, "noise_retention": 0.2674, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.142, "f_precision": 0.8303, "f_coverage": 0.8303, "f_balanced": 0.7907, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1803, "chars": 7214, "content_recall": 0.859, "noise_retention": 0.2674, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.109, "f_precision": 0.8303, "f_coverage": 0.8303, "f_balanced": 0.7907, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1352, "chars": 5408, "content_recall": 0.9487, "noise_retention": 0.814, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.479, "f_precision": 0.5213, "f_coverage": 0.5213, "f_balanced": 0.3111, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1773, "chars": 7093, "content_recall": 0.859, "noise_retention": 0.2674, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.128, "f_precision": 0.8303, "f_coverage": 0.8303, "f_balanced": 0.7907, "anchor_diag": { "content_chars": 3125, "noise_chars": 1267, "content_ngrams": 390, "noise_ngrams": 86, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" } }, "scoreable": true }, "ibm-cloud-docs": { "meta": { "id": "ibm-cloud-docs", "url": "https://cloud.ibm.com/docs", "requested_url": "https://cloud.ibm.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 2158107 } }, "anchors": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 52, "chars": 209, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 52, "chars": 209, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 52, "chars": 209, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 31, "chars": 125, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" }, "readability": { "method": "readability", "tokens": 31, "chars": 124, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 144, "chars": 576, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 6.944, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 143, "chars": 572, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 6.993, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 68, "chars": 272, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 14.706, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 139, "chars": 559, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 7.194, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 257, "noise_chars": 860, "content_ngrams": 0, "noise_ngrams": 8, "ambiguous_ngrams_removed": 33, "content_sentences": 1 }, "notes": "" } }, "scoreable": false }, "ietf-http": { "meta": { "id": "ietf-http", "url": "https://www.rfc-editor.org/rfc/rfc9110.html", "requested_url": "https://www.rfc-editor.org/rfc/rfc9110.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 1187554 } }, "anchors": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 119163, "chars": 476653, "content_recall": 0.8082, "noise_retention": 0.0, "noise_keyword_total": 18, "noise_per_1k_tokens": 0.151, "f_precision": 0.8405, "f_coverage": 0.8405, "f_balanced": 0.8939, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 120371, "chars": 481485, "content_recall": 0.8135, "noise_retention": 0.0, "noise_keyword_total": 18, "noise_per_1k_tokens": 0.15, "f_precision": 0.8451, "f_coverage": 0.8451, "f_balanced": 0.8972, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 96372, "chars": 385490, "content_recall": 0.649, "noise_retention": 0.0, "noise_keyword_total": 18, "noise_per_1k_tokens": 0.187, "f_precision": 0.698, "f_coverage": 0.698, "f_balanced": 0.7871, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1314, "chars": 5259, "content_recall": 0.0117, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0146, "f_coverage": 0.0146, "f_balanced": 0.0231, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" }, "readability": { "method": "readability", "tokens": 694, "chars": 2779, "content_recall": 0.0069, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0087, "f_coverage": 0.0087, "f_balanced": 0.0138, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 146561, "chars": 586247, "content_recall": 0.7893, "noise_retention": 0.8088, "noise_keyword_total": 24, "noise_per_1k_tokens": 0.164, "f_precision": 0.4855, "f_coverage": 0.4855, "f_balanced": 0.3078, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 119507, "chars": 478029, "content_recall": 0.957, "noise_retention": 0.8765, "noise_keyword_total": 20, "noise_per_1k_tokens": 0.167, "f_precision": 0.4073, "f_coverage": 0.4073, "f_balanced": 0.2188, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 116648, "chars": 466592, "content_recall": 0.9625, "noise_retention": 0.8936, "noise_keyword_total": 20, "noise_per_1k_tokens": 0.171, "f_precision": 0.3689, "f_coverage": 0.3689, "f_balanced": 0.1916, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 146339, "chars": 585357, "content_recall": 0.7893, "noise_retention": 0.8088, "noise_keyword_total": 24, "noise_per_1k_tokens": 0.164, "f_precision": 0.4855, "f_coverage": 0.4855, "f_balanced": 0.3078, "anchor_diag": { "content_chars": 436288, "noise_chars": 9206, "content_ngrams": 46806, "noise_ngrams": 1109, "ambiguous_ngrams_removed": 34, "content_sentences": 2547 }, "notes": "" } }, "scoreable": true }, "intercom-docs": { "meta": { "id": "intercom-docs", "url": "https://developers.intercom.com/", "requested_url": "https://developers.intercom.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 385181 } }, "anchors": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 717, "chars": 2869, "content_recall": 0.6537, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.395, "f_precision": 0.7023, "f_coverage": 0.7023, "f_balanced": 0.7906, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 717, "chars": 2869, "content_recall": 0.6537, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.395, "f_precision": 0.7023, "f_coverage": 0.7023, "f_balanced": 0.7906, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 681, "chars": 2726, "content_recall": 0.639, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.468, "f_precision": 0.6887, "f_coverage": 0.6887, "f_balanced": 0.7798, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 155, "chars": 623, "content_recall": 0.2488, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2928, "f_coverage": 0.2928, "f_balanced": 0.3984, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 160, "chars": 641, "content_recall": 0.2341, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2765, "f_coverage": 0.2765, "f_balanced": 0.3794, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1116, "chars": 4465, "content_recall": 0.6585, "noise_retention": 0.0769, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.792, "f_precision": 0.6986, "f_coverage": 0.6986, "f_balanced": 0.7687, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1101, "chars": 4406, "content_recall": 0.6585, "noise_retention": 0.0769, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.817, "f_precision": 0.6986, "f_coverage": 0.6986, "f_balanced": 0.7687, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 559, "chars": 2236, "content_recall": 0.7463, "noise_retention": 0.6923, "noise_keyword_total": 2, "noise_per_1k_tokens": 3.578, "f_precision": 0.5808, "f_coverage": 0.5808, "f_balanced": 0.4357, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1099, "chars": 4398, "content_recall": 0.6585, "noise_retention": 0.0769, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.82, "f_precision": 0.6986, "f_coverage": 0.6986, "f_balanced": 0.7687, "anchor_diag": { "content_chars": 1601, "noise_chars": 120, "content_ngrams": 205, "noise_ngrams": 13, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "istio-docs": { "meta": { "id": "istio-docs", "url": "https://istio.io/latest/docs/", "requested_url": "https://istio.io/latest/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 102183 } }, "anchors": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 334, "chars": 1338, "content_recall": 0.6449, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6942, "f_coverage": 0.6942, "f_balanced": 0.7841, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 378, "chars": 1513, "content_recall": 0.6449, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6942, "f_coverage": 0.6942, "f_balanced": 0.7841, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 298, "chars": 1194, "content_recall": 0.6168, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.668, "f_coverage": 0.668, "f_balanced": 0.763, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 203, "chars": 814, "content_recall": 0.8411, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8687, "f_coverage": 0.8687, "f_balanced": 0.9137, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "readability": { "method": "readability", "tokens": 170, "chars": 682, "content_recall": 0.7477, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7874, "f_coverage": 0.7874, "f_balanced": 0.8556, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 15140, "chars": 60563, "content_recall": 0.6168, "noise_retention": 0.1463, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.066, "f_precision": 0.6531, "f_coverage": 0.6531, "f_balanced": 0.7162, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 15569, "chars": 62279, "content_recall": 0.6168, "noise_retention": 0.1707, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.321, "f_precision": 0.6501, "f_coverage": 0.6501, "f_balanced": 0.7074, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2486, "chars": 9947, "content_recall": 0.6449, "noise_retention": 0.8049, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.402, "f_precision": 0.4414, "f_coverage": 0.4414, "f_balanced": 0.2996, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 15135, "chars": 60540, "content_recall": 0.6168, "noise_retention": 0.1463, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.066, "f_precision": 0.6531, "f_coverage": 0.6531, "f_balanced": 0.7162, "anchor_diag": { "content_chars": 878, "noise_chars": 530, "content_ngrams": 107, "noise_ngrams": 41, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" } }, "scoreable": true }, "jaeger-docs": { "meta": { "id": "jaeger-docs", "url": "https://www.jaegertracing.io/docs/", "requested_url": "https://www.jaegertracing.io/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 288751 } }, "anchors": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 110, "chars": 440, "content_recall": 0.0, "noise_retention": 0.0135, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 110, "chars": 440, "content_recall": 0.0, "noise_retention": 0.0135, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 80, "chars": 320, "content_recall": 0.0, "noise_retention": 0.0135, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 147, "chars": 588, "content_recall": 0.0, "noise_retention": 0.4595, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 6, "chars": 27, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 10476, "chars": 41905, "content_recall": 0.0, "noise_retention": 0.1351, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 10918, "chars": 43672, "content_recall": 0.0, "noise_retention": 0.1216, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2713, "chars": 10853, "content_recall": 0.0, "noise_retention": 0.8378, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 12430, "chars": 49721, "content_recall": 0.0, "noise_retention": 0.1351, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 852, "content_ngrams": 0, "noise_ngrams": 74, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "jax-docs": { "meta": { "id": "jax-docs", "url": "https://docs.jax.dev/en/latest/", "requested_url": "https://docs.jax.dev/en/latest/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 77317 } }, "anchors": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 703, "chars": 2814, "content_recall": 0.8394, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8673, "f_coverage": 0.8673, "f_balanced": 0.9127, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 711, "chars": 2845, "content_recall": 0.8394, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8673, "f_coverage": 0.8673, "f_balanced": 0.9127, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 692, "chars": 2768, "content_recall": 0.8394, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8673, "f_coverage": 0.8673, "f_balanced": 0.9127, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 633, "chars": 2535, "content_recall": 0.897, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9158, "f_coverage": 0.9158, "f_balanced": 0.9457, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "readability": { "method": "readability", "tokens": 97, "chars": 389, "content_recall": 0.0727, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0893, "f_coverage": 0.0893, "f_balanced": 0.1356, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5945, "chars": 23782, "content_recall": 0.7424, "noise_retention": 0.625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6208, "f_coverage": 0.6208, "f_balanced": 0.4983, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6080, "chars": 24320, "content_recall": 0.7333, "noise_retention": 0.75, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5288, "f_coverage": 0.5288, "f_balanced": 0.3729, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2674, "chars": 10697, "content_recall": 0.8485, "noise_retention": 0.75, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5738, "f_coverage": 0.5738, "f_balanced": 0.3862, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5928, "chars": 23712, "content_recall": 0.7424, "noise_retention": 0.625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6208, "f_coverage": 0.6208, "f_balanced": 0.4983, "anchor_diag": { "content_chars": 3563, "noise_chars": 101, "content_ngrams": 330, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 23 }, "notes": "" } }, "scoreable": true }, "jenkins-docs": { "meta": { "id": "jenkins-docs", "url": "https://www.jenkins.io/doc/", "requested_url": "https://www.jenkins.io/doc/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 12088 } }, "anchors": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 630, "chars": 2521, "content_recall": 0.8312, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8602, "f_coverage": 0.8602, "f_balanced": 0.9078, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 659, "chars": 2637, "content_recall": 0.8312, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8602, "f_coverage": 0.8602, "f_balanced": 0.9078, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 564, "chars": 2258, "content_recall": 0.697, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7419, "f_coverage": 0.7419, "f_balanced": 0.8214, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 463, "chars": 1852, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "readability": { "method": "readability", "tokens": 318, "chars": 1273, "content_recall": 0.6234, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6742, "f_coverage": 0.6742, "f_balanced": 0.768, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 862, "chars": 3449, "content_recall": 0.8009, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8341, "f_coverage": 0.8341, "f_balanced": 0.8894, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 861, "chars": 3446, "content_recall": 0.8009, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8341, "f_coverage": 0.8341, "f_balanced": 0.8894, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 594, "chars": 2377, "content_recall": 0.9307, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9438, "f_coverage": 0.9438, "f_balanced": 0.9641, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 849, "chars": 3397, "content_recall": 0.8009, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8341, "f_coverage": 0.8341, "f_balanced": 0.8894, "anchor_diag": { "content_chars": 1816, "noise_chars": 0, "content_ngrams": 231, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" } }, "scoreable": true }, "jest-docs": { "meta": { "id": "jest-docs", "url": "https://jestjs.io/docs/getting-started", "requested_url": "https://jestjs.io/docs/getting-started", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 101580 } }, "anchors": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2314, "chars": 9259, "content_recall": 0.6566, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.705, "f_coverage": 0.705, "f_balanced": 0.7927, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2384, "chars": 9539, "content_recall": 0.6691, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7165, "f_coverage": 0.7165, "f_balanced": 0.8017, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1165, "chars": 4662, "content_recall": 0.3746, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4282, "f_coverage": 0.4282, "f_balanced": 0.545, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1998, "chars": 7992, "content_recall": 0.8096, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8416, "f_coverage": 0.8416, "f_balanced": 0.8948, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1664, "chars": 6656, "content_recall": 0.7523, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7915, "f_coverage": 0.7915, "f_balanced": 0.8587, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3750, "chars": 15000, "content_recall": 0.7222, "noise_retention": 0.2692, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.8, "f_precision": 0.7239, "f_coverage": 0.7239, "f_balanced": 0.7264, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3914, "chars": 15658, "content_recall": 0.7284, "noise_retention": 0.2692, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.766, "f_precision": 0.7289, "f_coverage": 0.7289, "f_balanced": 0.7296, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2290, "chars": 9160, "content_recall": 0.796, "noise_retention": 0.8974, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.873, "f_precision": 0.3384, "f_coverage": 0.3384, "f_balanced": 0.1817, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3713, "chars": 14853, "content_recall": 0.7211, "noise_retention": 0.2692, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.808, "f_precision": 0.723, "f_coverage": 0.723, "f_balanced": 0.7259, "anchor_diag": { "content_chars": 9320, "noise_chars": 1511, "content_ngrams": 961, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 99 }, "notes": "" } }, "scoreable": true }, "json-schema": { "meta": { "id": "json-schema", "url": "https://json-schema.org/learn/getting-started-step-by-step", "requested_url": "https://json-schema.org/learn/getting-started-step-by-step", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 616688 } }, "anchors": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 4430, "chars": 17721, "content_recall": 0.8133, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8449, "f_coverage": 0.8449, "f_balanced": 0.897, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 4489, "chars": 17956, "content_recall": 0.8379, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8659, "f_coverage": 0.8659, "f_balanced": 0.9118, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 3062, "chars": 12251, "content_recall": 0.6292, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6796, "f_coverage": 0.6796, "f_balanced": 0.7724, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2907, "chars": 11629, "content_recall": 0.7797, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8157, "f_coverage": 0.8157, "f_balanced": 0.8762, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" }, "readability": { "method": "readability", "tokens": 3892, "chars": 15569, "content_recall": 0.7597, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.798, "f_coverage": 0.798, "f_balanced": 0.8634, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5452, "chars": 21811, "content_recall": 0.7526, "noise_retention": 0.2581, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7504, "f_coverage": 0.7504, "f_balanced": 0.7472, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5271, "chars": 21086, "content_recall": 0.7526, "noise_retention": 0.2581, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7504, "f_coverage": 0.7504, "f_balanced": 0.7472, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4387, "chars": 17549, "content_recall": 0.8159, "noise_retention": 0.871, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3952, "f_coverage": 0.3952, "f_balanced": 0.2228, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5444, "chars": 21778, "content_recall": 0.7526, "noise_retention": 0.2581, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7504, "f_coverage": 0.7504, "f_balanced": 0.7472, "anchor_diag": { "content_chars": 20269, "noise_chars": 251, "content_ngrams": 1548, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 156 }, "notes": "" } }, "scoreable": true }, "junit-docs": { "meta": { "id": "junit-docs", "url": "https://docs.junit.org/6.1.3/overview.html", "requested_url": "https://junit.org/junit5/docs/current/user-guide/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 28196 } }, "anchors": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1051, "chars": 4204, "content_recall": 0.7673, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8048, "f_coverage": 0.8048, "f_balanced": 0.8684, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1051, "chars": 4204, "content_recall": 0.7673, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8048, "f_coverage": 0.8048, "f_balanced": 0.8684, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 445, "chars": 1783, "content_recall": 0.3848, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4388, "f_coverage": 0.4388, "f_balanced": 0.5557, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 819, "chars": 3279, "content_recall": 0.8434, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8707, "f_coverage": 0.8707, "f_balanced": 0.915, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" }, "readability": { "method": "readability", "tokens": 272, "chars": 1088, "content_recall": 0.2886, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3365, "f_coverage": 0.3365, "f_balanced": 0.4479, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2808, "chars": 11232, "content_recall": 0.7629, "noise_retention": 0.2151, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7672, "f_coverage": 0.7672, "f_balanced": 0.7737, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3029, "chars": 12119, "content_recall": 0.7562, "noise_retention": 0.2151, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7617, "f_coverage": 0.7617, "f_balanced": 0.7702, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1403, "chars": 5615, "content_recall": 0.8881, "noise_retention": 0.9522, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1967, "f_coverage": 0.1967, "f_balanced": 0.0907, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2975, "chars": 11902, "content_recall": 0.7562, "noise_retention": 0.2151, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7617, "f_coverage": 0.7617, "f_balanced": 0.7702, "anchor_diag": { "content_chars": 3905, "noise_chars": 3662, "content_ngrams": 447, "noise_ngrams": 251, "ambiguous_ngrams_removed": 0, "content_sentences": 38 }, "notes": "" } }, "scoreable": true }, "k8s-concepts": { "meta": { "id": "k8s-concepts", "url": "https://kubernetes.io/docs/concepts/", "requested_url": "https://kubernetes.io/docs/concepts/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 498824 } }, "anchors": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 550, "chars": 2201, "content_recall": 0.6119, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6634, "f_coverage": 0.6634, "f_balanced": 0.7593, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 550, "chars": 2201, "content_recall": 0.6119, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6634, "f_coverage": 0.6634, "f_balanced": 0.7593, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 405, "chars": 1620, "content_recall": 0.5323, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5873, "f_coverage": 0.5873, "f_balanced": 0.6948, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 281, "chars": 1127, "content_recall": 0.6119, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6634, "f_coverage": 0.6634, "f_balanced": 0.7593, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 285, "chars": 1141, "content_recall": 0.6119, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6634, "f_coverage": 0.6634, "f_balanced": 0.7593, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 21403, "chars": 85613, "content_recall": 0.6418, "noise_retention": 0.4032, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.093, "f_precision": 0.6323, "f_coverage": 0.6323, "f_balanced": 0.6185, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 22028, "chars": 88114, "content_recall": 0.6418, "noise_retention": 0.371, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.091, "f_precision": 0.6392, "f_coverage": 0.6392, "f_balanced": 0.6353, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 6584, "chars": 26339, "content_recall": 0.7463, "noise_retention": 0.8468, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.152, "f_precision": 0.4207, "f_coverage": 0.4207, "f_balanced": 0.2542, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 24115, "chars": 96463, "content_recall": 0.6418, "noise_retention": 0.371, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.083, "f_precision": 0.6392, "f_coverage": 0.6392, "f_balanced": 0.6353, "anchor_diag": { "content_chars": 1673, "noise_chars": 1770, "content_ngrams": 201, "noise_ngrams": 124, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "k8s-deployments": { "meta": { "id": "k8s-deployments", "url": "https://kubernetes.io/docs/concepts/workloads/controllers/deployment/", "requested_url": "https://kubernetes.io/docs/concepts/workloads/controllers/deployment/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 594275 } }, "anchors": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 12928, "chars": 51714, "content_recall": 0.7877, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8227, "f_coverage": 0.8227, "f_balanced": 0.8813, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 13344, "chars": 53379, "content_recall": 0.8187, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8495, "f_coverage": 0.8495, "f_balanced": 0.9003, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 11350, "chars": 45402, "content_recall": 0.6935, "noise_retention": 0.0096, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7377, "f_coverage": 0.7377, "f_balanced": 0.8158, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 11226, "chars": 44905, "content_recall": 0.7368, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7777, "f_coverage": 0.7777, "f_balanced": 0.8484, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" }, "readability": { "method": "readability", "tokens": 12970, "chars": 51882, "content_recall": 0.8613, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8858, "f_coverage": 0.8858, "f_balanced": 0.9255, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 36223, "chars": 144892, "content_recall": 0.86, "noise_retention": 0.4471, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.055, "f_precision": 0.774, "f_coverage": 0.774, "f_balanced": 0.6731, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 37220, "chars": 148881, "content_recall": 0.8706, "noise_retention": 0.6058, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.054, "f_precision": 0.7012, "f_coverage": 0.7012, "f_balanced": 0.5427, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 19671, "chars": 78687, "content_recall": 0.8899, "noise_retention": 0.9038, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.051, "f_precision": 0.3357, "f_coverage": 0.3357, "f_balanced": 0.1736, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 38934, "chars": 155739, "content_recall": 0.86, "noise_retention": 0.4279, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.051, "f_precision": 0.7814, "f_coverage": 0.7814, "f_balanced": 0.6871, "anchor_diag": { "content_chars": 71914, "noise_chars": 3140, "content_ngrams": 5550, "noise_ngrams": 208, "ambiguous_ngrams_removed": 2, "content_sentences": 534 }, "notes": "" } }, "scoreable": true }, "k8s-home": { "meta": { "id": "k8s-home", "url": "https://kubernetes.io/docs/home/", "requested_url": "https://kubernetes.io/docs/home/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 500305 } }, "anchors": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 370, "chars": 1480, "content_recall": 0.5038, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5593, "f_coverage": 0.5593, "f_balanced": 0.6701, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 370, "chars": 1480, "content_recall": 0.5038, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5593, "f_coverage": 0.5593, "f_balanced": 0.6701, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 340, "chars": 1360, "content_recall": 0.4427, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4983, "f_coverage": 0.4983, "f_balanced": 0.6138, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 212, "chars": 851, "content_recall": 0.626, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6766, "f_coverage": 0.6766, "f_balanced": 0.77, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "readability": { "method": "readability", "tokens": 92, "chars": 371, "content_recall": 0.1145, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1391, "f_coverage": 0.1391, "f_balanced": 0.2055, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 21641, "chars": 86564, "content_recall": 0.542, "noise_retention": 0.4202, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.092, "f_precision": 0.5492, "f_coverage": 0.5492, "f_balanced": 0.5603, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 22279, "chars": 89119, "content_recall": 0.542, "noise_retention": 0.395, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.09, "f_precision": 0.5535, "f_coverage": 0.5535, "f_balanced": 0.5718, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 6619, "chars": 26479, "content_recall": 0.5725, "noise_retention": 0.8403, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.151, "f_precision": 0.3774, "f_coverage": 0.3774, "f_balanced": 0.2497, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 24348, "chars": 97394, "content_recall": 0.542, "noise_retention": 0.395, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.082, "f_precision": 0.5535, "f_coverage": 0.5535, "f_balanced": 0.5718, "anchor_diag": { "content_chars": 1073, "noise_chars": 1758, "content_ngrams": 131, "noise_ngrams": 119, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" } }, "scoreable": true }, "k8s-pods": { "meta": { "id": "k8s-pods", "url": "https://kubernetes.io/docs/concepts/workloads/pods/", "requested_url": "https://kubernetes.io/docs/concepts/workloads/pods/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": false, "bytes": 546484 } }, "anchors": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 6157, "chars": 24628, "content_recall": 0.828, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8575, "f_coverage": 0.8575, "f_balanced": 0.9059, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 6236, "chars": 24946, "content_recall": 0.8338, "noise_retention": 0.0108, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8609, "f_coverage": 0.8609, "f_balanced": 0.9049, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 5172, "chars": 20690, "content_recall": 0.6866, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7325, "f_coverage": 0.7325, "f_balanced": 0.8142, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 4393, "chars": 17574, "content_recall": 0.7868, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8219, "f_coverage": 0.8219, "f_balanced": 0.8807, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" }, "readability": { "method": "readability", "tokens": 5277, "chars": 21109, "content_recall": 0.8757, "noise_retention": 0.0108, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8963, "f_coverage": 0.8963, "f_balanced": 0.929, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 28433, "chars": 113735, "content_recall": 0.8564, "noise_retention": 0.4301, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.07, "f_precision": 0.7782, "f_coverage": 0.7782, "f_balanced": 0.6844, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 28974, "chars": 115896, "content_recall": 0.8579, "noise_retention": 0.5484, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.069, "f_precision": 0.7271, "f_coverage": 0.7271, "f_balanced": 0.5917, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 11801, "chars": 47204, "content_recall": 0.9282, "noise_retention": 0.8925, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.085, "f_precision": 0.3674, "f_coverage": 0.3674, "f_balanced": 0.1927, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 31147, "chars": 124589, "content_recall": 0.8564, "noise_retention": 0.4086, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.064, "f_precision": 0.786, "f_coverage": 0.786, "f_balanced": 0.6997, "anchor_diag": { "content_chars": 24973, "noise_chars": 2599, "content_ngrams": 2744, "noise_ngrams": 186, "ambiguous_ngrams_removed": 1, "content_sentences": 225 }, "notes": "" } }, "scoreable": true }, "k8s-services": { "meta": { "id": "k8s-services", "url": "https://kubernetes.io/docs/concepts/services-networking/service/", "requested_url": "https://kubernetes.io/docs/concepts/services-networking/service/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": true, "has_table": true, "bytes": 592495 } }, "anchors": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 10442, "chars": 41771, "content_recall": 0.8426, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.87, "f_coverage": 0.87, "f_balanced": 0.9146, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 10798, "chars": 43193, "content_recall": 0.8727, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8955, "f_coverage": 0.8955, "f_balanced": 0.932, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 7164, "chars": 28658, "content_recall": 0.5972, "noise_retention": 0.0052, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6491, "f_coverage": 0.6491, "f_balanced": 0.7464, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 9141, "chars": 36566, "content_recall": 0.8797, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9014, "f_coverage": 0.9014, "f_balanced": 0.936, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" }, "readability": { "method": "readability", "tokens": 10046, "chars": 40184, "content_recall": 0.92, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9349, "f_coverage": 0.9349, "f_balanced": 0.9583, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 32993, "chars": 131975, "content_recall": 0.8899, "noise_retention": 0.366, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.061, "f_precision": 0.8234, "f_coverage": 0.8234, "f_balanced": 0.7405, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 33577, "chars": 134308, "content_recall": 0.8957, "noise_retention": 0.5773, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.06, "f_precision": 0.7319, "f_coverage": 0.7319, "f_balanced": 0.5743, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 16459, "chars": 65838, "content_recall": 0.9319, "noise_retention": 0.9021, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.061, "f_precision": 0.3448, "f_coverage": 0.3448, "f_balanced": 0.1772, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 35706, "chars": 142826, "content_recall": 0.8899, "noise_retention": 0.3454, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.056, "f_precision": 0.8302, "f_coverage": 0.8302, "f_balanced": 0.7543, "anchor_diag": { "content_chars": 43023, "noise_chars": 2858, "content_ngrams": 4948, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 356 }, "notes": "" } }, "scoreable": true }, "kafka-docs": { "meta": { "id": "kafka-docs", "url": "https://kafka.apache.org/documentation/", "requested_url": "https://kafka.apache.org/documentation/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 19879 } }, "anchors": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 31, "chars": 125, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 31, "chars": 125, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 31, "chars": 125, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 134, "chars": 537, "content_recall": 0.0, "noise_retention": 0.4778, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 92, "chars": 370, "content_recall": 0.0, "noise_retention": 0.4444, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 726, "chars": 2904, "content_recall": 0.0, "noise_retention": 0.3444, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 800, "chars": 3203, "content_recall": 0.0, "noise_retention": 0.3444, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 226, "chars": 904, "content_recall": 0.0, "noise_retention": 0.9111, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 715, "chars": 2860, "content_recall": 0.0, "noise_retention": 0.3444, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 1374, "content_ngrams": 0, "noise_ngrams": 90, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "keras-docs": { "meta": { "id": "keras-docs", "url": "https://keras.io/guides/", "requested_url": "https://keras.io/guides/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 22348 } }, "anchors": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 166, "chars": 667, "content_recall": 0.6351, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6851, "f_coverage": 0.6851, "f_balanced": 0.7769, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 166, "chars": 667, "content_recall": 0.6351, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6851, "f_coverage": 0.6851, "f_balanced": 0.7769, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 166, "chars": 667, "content_recall": 0.6351, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6851, "f_coverage": 0.6851, "f_balanced": 0.7769, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 96, "chars": 386, "content_recall": 0.6892, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7349, "f_coverage": 0.7349, "f_balanced": 0.816, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" }, "readability": { "method": "readability", "tokens": 115, "chars": 460, "content_recall": 0.6892, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7349, "f_coverage": 0.7349, "f_balanced": 0.816, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1961, "chars": 7844, "content_recall": 0.6351, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6851, "f_coverage": 0.6851, "f_balanced": 0.7769, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1969, "chars": 7877, "content_recall": 0.6351, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6851, "f_coverage": 0.6851, "f_balanced": 0.7769, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 934, "chars": 3738, "content_recall": 0.6892, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1954, "chars": 7819, "content_recall": 0.6351, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6851, "f_coverage": 0.6851, "f_balanced": 0.7769, "anchor_diag": { "content_chars": 2121, "noise_chars": 1223, "content_ngrams": 74, "noise_ngrams": 29, "ambiguous_ngrams_removed": 114, "content_sentences": 10 }, "notes": "" } }, "scoreable": true }, "knative-docs": { "meta": { "id": "knative-docs", "url": "https://knative.dev/docs/", "requested_url": "https://knative.dev/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 205068 } }, "anchors": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 4657, "chars": 18630, "content_recall": 0.8794, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9011, "f_coverage": 0.9011, "f_balanced": 0.9358, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 4708, "chars": 18834, "content_recall": 0.8847, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9056, "f_coverage": 0.9056, "f_balanced": 0.9388, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 4400, "chars": 17600, "content_recall": 0.8239, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.854, "f_coverage": 0.854, "f_balanced": 0.9035, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 4605, "chars": 18420, "content_recall": 0.9033, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9211, "f_coverage": 0.9211, "f_balanced": 0.9492, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" }, "readability": { "method": "readability", "tokens": 4363, "chars": 17452, "content_recall": 0.8865, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9071, "f_coverage": 0.9071, "f_balanced": 0.9398, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 11107, "chars": 44429, "content_recall": 0.859, "noise_retention": 0.2724, "noise_keyword_total": 9, "noise_per_1k_tokens": 0.81, "f_precision": 0.829, "f_coverage": 0.829, "f_balanced": 0.7879, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 10895, "chars": 43580, "content_recall": 0.8674, "noise_retention": 0.2724, "noise_keyword_total": 9, "noise_per_1k_tokens": 0.826, "f_precision": 0.8353, "f_coverage": 0.8353, "f_balanced": 0.7914, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 6699, "chars": 26797, "content_recall": 0.9033, "noise_retention": 0.787, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.746, "f_precision": 0.548, "f_coverage": 0.548, "f_balanced": 0.3447, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 11244, "chars": 44978, "content_recall": 0.859, "noise_retention": 0.2724, "noise_keyword_total": 9, "noise_per_1k_tokens": 0.8, "f_precision": 0.829, "f_coverage": 0.829, "f_balanced": 0.7879, "anchor_diag": { "content_chars": 20124, "noise_chars": 21659, "content_ngrams": 2255, "noise_ngrams": 1094, "ambiguous_ngrams_removed": 69, "content_sentences": 177 }, "notes": "" } }, "scoreable": true }, "langchain-docs": { "meta": { "id": "langchain-docs", "url": "https://docs.langchain.com/oss/python/langchain/overview", "requested_url": "https://python.langchain.com/docs/introduction/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 1017319 } }, "anchors": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2102, "chars": 8408, "content_recall": 0.9036, "noise_retention": 0.1059, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9017, "f_coverage": 0.9017, "f_balanced": 0.8989, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2102, "chars": 8408, "content_recall": 0.9036, "noise_retention": 0.1059, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9017, "f_coverage": 0.9017, "f_balanced": 0.8989, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 886, "chars": 3546, "content_recall": 0.6531, "noise_retention": 0.1059, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6903, "f_coverage": 0.6903, "f_balanced": 0.7548, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1850, "chars": 7403, "content_recall": 0.7709, "noise_retention": 0.1118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7918, "f_coverage": 0.7918, "f_balanced": 0.8254, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" }, "readability": { "method": "readability", "tokens": 573, "chars": 2294, "content_recall": 0.4004, "noise_retention": 0.0176, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4542, "f_coverage": 0.4542, "f_balanced": 0.5689, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3408, "chars": 13635, "content_recall": 0.8608, "noise_retention": 0.2941, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.587, "f_precision": 0.8246, "f_coverage": 0.8246, "f_balanced": 0.7757, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3598, "chars": 14394, "content_recall": 0.863, "noise_retention": 0.2941, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.556, "f_precision": 0.8262, "f_coverage": 0.8262, "f_balanced": 0.7766, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2412, "chars": 9648, "content_recall": 0.9251, "noise_retention": 0.9059, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.415, "f_precision": 0.3345, "f_coverage": 0.3345, "f_balanced": 0.1709, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3399, "chars": 13598, "content_recall": 0.8608, "noise_retention": 0.2941, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.588, "f_precision": 0.8246, "f_coverage": 0.8246, "f_balanced": 0.7757, "anchor_diag": { "content_chars": 12964, "noise_chars": 1369, "content_ngrams": 467, "noise_ngrams": 170, "ambiguous_ngrams_removed": 3, "content_sentences": 87 }, "notes": "" } }, "scoreable": true }, "laravel-docs": { "meta": { "id": "laravel-docs", "url": "https://laravel.com/framework/docs", "requested_url": "https://laravel.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 179706 } }, "anchors": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 5220, "chars": 20880, "content_recall": 0.819, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8497, "f_coverage": 0.8497, "f_balanced": 0.9005, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 5220, "chars": 20880, "content_recall": 0.819, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8497, "f_coverage": 0.8497, "f_balanced": 0.9005, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 4418, "chars": 17675, "content_recall": 0.7039, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7482, "f_coverage": 0.7482, "f_balanced": 0.8262, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 4306, "chars": 17227, "content_recall": 0.8513, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8774, "f_coverage": 0.8774, "f_balanced": 0.9197, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" }, "readability": { "method": "readability", "tokens": 4169, "chars": 16676, "content_recall": 0.8897, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9097, "f_coverage": 0.9097, "f_balanced": 0.9416, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 7541, "chars": 30164, "content_recall": 0.8349, "noise_retention": 0.0181, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.265, "f_precision": 0.8607, "f_coverage": 0.8607, "f_balanced": 0.9025, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 7400, "chars": 29601, "content_recall": 0.8466, "noise_retention": 0.0181, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.27, "f_precision": 0.8706, "f_coverage": 0.8706, "f_balanced": 0.9092, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 5373, "chars": 21492, "content_recall": 0.9272, "noise_retention": 0.9518, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.186, "f_precision": 0.1995, "f_coverage": 0.1995, "f_balanced": 0.0916, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 7504, "chars": 30016, "content_recall": 0.8349, "noise_retention": 0.0181, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.267, "f_precision": 0.8607, "f_coverage": 0.8607, "f_balanced": 0.9025, "anchor_diag": { "content_chars": 22815, "noise_chars": 2974, "content_ngrams": 2320, "noise_ngrams": 166, "ambiguous_ngrams_removed": 0, "content_sentences": 191 }, "notes": "" } }, "scoreable": true }, "linkerd-docs": { "meta": { "id": "linkerd-docs", "url": "https://linkerd.io/docs/overview/", "requested_url": "https://linkerd.io/2/overview/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 25137 } }, "anchors": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 632, "chars": 2530, "content_recall": 0.7259, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.768, "f_coverage": 0.768, "f_balanced": 0.8412, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 684, "chars": 2738, "content_recall": 0.8185, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8493, "f_coverage": 0.8493, "f_balanced": 0.9002, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 610, "chars": 2442, "content_recall": 0.7037, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.748, "f_coverage": 0.748, "f_balanced": 0.8261, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 520, "chars": 2083, "content_recall": 0.9296, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9429, "f_coverage": 0.9429, "f_balanced": 0.9635, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "readability": { "method": "readability", "tokens": 518, "chars": 2074, "content_recall": 0.9296, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9429, "f_coverage": 0.9429, "f_balanced": 0.9635, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3192, "chars": 12771, "content_recall": 0.8222, "noise_retention": 0.2779, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8, "f_coverage": 0.8, "f_balanced": 0.7689, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3269, "chars": 13076, "content_recall": 0.8222, "noise_retention": 0.2779, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8, "f_coverage": 0.8, "f_balanced": 0.7689, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1474, "chars": 5896, "content_recall": 0.9444, "noise_retention": 0.9727, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1225, "f_coverage": 0.1225, "f_balanced": 0.0531, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3190, "chars": 12763, "content_recall": 0.8222, "noise_retention": 0.2779, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8, "f_coverage": 0.8, "f_balanced": 0.7689, "anchor_diag": { "content_chars": 2167, "noise_chars": 3703, "content_ngrams": 270, "noise_ngrams": 439, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" } }, "scoreable": true }, "llama-index": { "meta": { "id": "llama-index", "url": "https://developers.llamaindex.ai/python/framework/", "requested_url": "https://docs.llamaindex.ai/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 261436 } }, "anchors": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2337, "chars": 9348, "content_recall": 0.8224, "noise_retention": 0.4909, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.856, "f_precision": 0.7323, "f_coverage": 0.7323, "f_balanced": 0.6289, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2351, "chars": 9406, "content_recall": 0.8285, "noise_retention": 0.4909, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.851, "f_precision": 0.7361, "f_coverage": 0.7361, "f_balanced": 0.6307, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2078, "chars": 8314, "content_recall": 0.7113, "noise_retention": 0.4909, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.962, "f_precision": 0.6589, "f_coverage": 0.6589, "f_balanced": 0.5934, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1996, "chars": 7987, "content_recall": 0.7594, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.002, "f_precision": 0.7978, "f_coverage": 0.7978, "f_balanced": 0.8633, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1968, "chars": 7873, "content_recall": 0.8749, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.016, "f_precision": 0.8973, "f_coverage": 0.8973, "f_balanced": 0.9333, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 13363, "chars": 53454, "content_recall": 0.797, "noise_retention": 0.2545, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.15, "f_precision": 0.7861, "f_coverage": 0.7861, "f_balanced": 0.7704, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 13531, "chars": 54126, "content_recall": 0.8058, "noise_retention": 0.6, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.148, "f_precision": 0.6699, "f_coverage": 0.6699, "f_balanced": 0.5346, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 5231, "chars": 20926, "content_recall": 0.9055, "noise_retention": 0.8182, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.382, "f_precision": 0.5042, "f_coverage": 0.5042, "f_balanced": 0.3028, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 13268, "chars": 53075, "content_recall": 0.797, "noise_retention": 0.2545, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.151, "f_precision": 0.7861, "f_coverage": 0.7861, "f_balanced": 0.7704, "anchor_diag": { "content_chars": 9799, "noise_chars": 543, "content_ngrams": 1143, "noise_ngrams": 55, "ambiguous_ngrams_removed": 4, "content_sentences": 92 }, "notes": "" } }, "scoreable": true }, "lxml-docs": { "meta": { "id": "lxml-docs", "url": "https://lxml.de/", "requested_url": "https://lxml.de/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 37252 } }, "anchors": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2382, "chars": 9528, "content_recall": 0.4554, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.511, "f_coverage": 0.511, "f_balanced": 0.6258, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2763, "chars": 11053, "content_recall": 0.5006, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5562, "f_coverage": 0.5562, "f_balanced": 0.6672, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1913, "chars": 7654, "content_recall": 0.3912, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4454, "f_coverage": 0.4454, "f_balanced": 0.5624, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1595, "chars": 6382, "content_recall": 0.5189, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5742, "f_coverage": 0.5742, "f_balanced": 0.6833, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2037, "chars": 8148, "content_recall": 0.5862, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6391, "f_coverage": 0.6391, "f_balanced": 0.7391, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5511, "chars": 22047, "content_recall": 0.6229, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6737, "f_coverage": 0.6737, "f_balanced": 0.7676, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5604, "chars": 22418, "content_recall": 0.6253, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.676, "f_coverage": 0.676, "f_balanced": 0.7695, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3065, "chars": 12260, "content_recall": 0.8985, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9171, "f_coverage": 0.9171, "f_balanced": 0.9466, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5499, "chars": 21999, "content_recall": 0.6229, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6737, "f_coverage": 0.6737, "f_balanced": 0.7676, "anchor_diag": { "content_chars": 16060, "noise_chars": 0, "content_ngrams": 1636, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" } }, "scoreable": true }, "mailgun-docs": { "meta": { "id": "mailgun-docs", "url": "https://documentation.mailgun.com/", "requested_url": "https://documentation.mailgun.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 273652 } }, "anchors": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 153, "chars": 613, "content_recall": 0.3793, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4331, "f_coverage": 0.4331, "f_balanced": 0.55, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 204, "chars": 819, "content_recall": 0.4483, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5039, "f_coverage": 0.5039, "f_balanced": 0.619, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 58, "chars": 232, "content_recall": 0.0172, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0215, "f_coverage": 0.0215, "f_balanced": 0.0339, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 214, "chars": 858, "content_recall": 0.3017, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3507, "f_coverage": 0.3507, "f_balanced": 0.4636, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "readability": { "method": "readability", "tokens": 94, "chars": 379, "content_recall": 0.3621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.415, "f_coverage": 0.415, "f_balanced": 0.5316, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 800, "chars": 3201, "content_recall": 0.4483, "noise_retention": 0.1875, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.5, "f_precision": 0.4924, "f_coverage": 0.4924, "f_balanced": 0.5778, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 795, "chars": 3181, "content_recall": 0.4483, "noise_retention": 0.1875, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.516, "f_precision": 0.4924, "f_coverage": 0.4924, "f_balanced": 0.5778, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 274, "chars": 1096, "content_recall": 0.5517, "noise_retention": 0.75, "noise_keyword_total": 1, "noise_per_1k_tokens": 3.65, "f_precision": 0.4444, "f_coverage": 0.4444, "f_balanced": 0.3441, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 789, "chars": 3158, "content_recall": 0.4483, "noise_retention": 0.1875, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.535, "f_precision": 0.4924, "f_coverage": 0.4924, "f_balanced": 0.5778, "anchor_diag": { "content_chars": 1554, "noise_chars": 150, "content_ngrams": 116, "noise_ngrams": 16, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" } }, "scoreable": true }, "maven-docs": { "meta": { "id": "maven-docs", "url": "https://maven.apache.org/guides/", "requested_url": "https://maven.apache.org/guides/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 15379 } }, "anchors": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 143, "chars": 573, "content_recall": 0.1364, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1648, "f_coverage": 0.1648, "f_balanced": 0.24, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 143, "chars": 573, "content_recall": 0.1364, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1648, "f_coverage": 0.1648, "f_balanced": 0.24, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 114, "chars": 458, "content_recall": 0.0545, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0673, "f_coverage": 0.0673, "f_balanced": 0.1034, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 118, "chars": 473, "content_recall": 0.1727, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.207, "f_coverage": 0.207, "f_balanced": 0.2946, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "readability": { "method": "readability", "tokens": 8, "chars": 32, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2056, "chars": 8227, "content_recall": 0.2273, "noise_retention": 0.0254, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2684, "f_coverage": 0.2684, "f_balanced": 0.3686, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2148, "chars": 8595, "content_recall": 0.2273, "noise_retention": 0.0254, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2684, "f_coverage": 0.2684, "f_balanced": 0.3686, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 775, "chars": 3103, "content_recall": 0.4545, "noise_retention": 0.9322, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2123, "f_coverage": 0.2123, "f_balanced": 0.118, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2073, "chars": 8292, "content_recall": 0.2273, "noise_retention": 0.0254, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2684, "f_coverage": 0.2684, "f_balanced": 0.3686, "anchor_diag": { "content_chars": 934, "noise_chars": 1704, "content_ngrams": 110, "noise_ngrams": 118, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" } }, "scoreable": true }, "mdn-css": { "meta": { "id": "mdn-css", "url": "https://developer.mozilla.org/en-US/docs/Web/CSS", "requested_url": "https://developer.mozilla.org/en-US/docs/Web/CSS", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 321882 } }, "anchors": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 833, "chars": 3335, "content_recall": 0.5423, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.597, "f_coverage": 0.597, "f_balanced": 0.7032, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 927, "chars": 3708, "content_recall": 0.5942, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6467, "f_coverage": 0.6467, "f_balanced": 0.7455, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 674, "chars": 2697, "content_recall": 0.4558, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5114, "f_coverage": 0.5114, "f_balanced": 0.6262, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1079, "chars": 4317, "content_recall": 0.7885, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8233, "f_coverage": 0.8233, "f_balanced": 0.8817, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" }, "readability": { "method": "readability", "tokens": 558, "chars": 2234, "content_recall": 0.3923, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4466, "f_coverage": 0.4466, "f_balanced": 0.5635, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 31402, "chars": 125608, "content_recall": 0.6404, "noise_retention": 0.2905, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.064, "f_precision": 0.6531, "f_coverage": 0.6531, "f_balanced": 0.6732, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 31651, "chars": 126606, "content_recall": 0.6404, "noise_retention": 0.3028, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.063, "f_precision": 0.651, "f_coverage": 0.651, "f_balanced": 0.6676, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 6791, "chars": 27164, "content_recall": 0.8231, "noise_retention": 0.9266, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.147, "f_precision": 0.2705, "f_coverage": 0.2705, "f_balanced": 0.1348, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 31538, "chars": 126155, "content_recall": 0.6404, "noise_retention": 0.2905, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.063, "f_precision": 0.6531, "f_coverage": 0.6531, "f_balanced": 0.6732, "anchor_diag": { "content_chars": 3884, "noise_chars": 5767, "content_ngrams": 520, "noise_ngrams": 327, "ambiguous_ngrams_removed": 0, "content_sentences": 37 }, "notes": "" } }, "scoreable": true }, "mdn-fetch": { "meta": { "id": "mdn-fetch", "url": "https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API", "requested_url": "https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 153352 } }, "anchors": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 790, "chars": 3161, "content_recall": 0.7173, "noise_retention": 0.0056, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7596, "f_coverage": 0.7596, "f_balanced": 0.8334, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 818, "chars": 3272, "content_recall": 0.7845, "noise_retention": 0.0056, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.819, "f_coverage": 0.819, "f_balanced": 0.877, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 525, "chars": 2103, "content_recall": 0.424, "noise_retention": 0.0028, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4791, "f_coverage": 0.4791, "f_balanced": 0.595, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 646, "chars": 2585, "content_recall": 0.8269, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8565, "f_coverage": 0.8565, "f_balanced": 0.9052, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "readability": { "method": "readability", "tokens": 364, "chars": 1456, "content_recall": 0.6608, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7089, "f_coverage": 0.7089, "f_balanced": 0.7957, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3771, "chars": 15084, "content_recall": 0.7032, "noise_retention": 0.2857, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.53, "f_precision": 0.7054, "f_coverage": 0.7054, "f_balanced": 0.7087, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3785, "chars": 15142, "content_recall": 0.7032, "noise_retention": 0.3025, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.528, "f_precision": 0.702, "f_coverage": 0.702, "f_balanced": 0.7003, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1342, "chars": 5370, "content_recall": 0.8445, "noise_retention": 0.9216, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.745, "f_precision": 0.2859, "f_coverage": 0.2859, "f_balanced": 0.1435, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3757, "chars": 15030, "content_recall": 0.7032, "noise_retention": 0.2857, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.532, "f_precision": 0.7054, "f_coverage": 0.7054, "f_balanced": 0.7087, "anchor_diag": { "content_chars": 2188, "noise_chars": 6270, "content_ngrams": 283, "noise_ngrams": 357, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" } }, "scoreable": true }, "mdn-html": { "meta": { "id": "mdn-html", "url": "https://developer.mozilla.org/en-US/docs/Web/HTML", "requested_url": "https://developer.mozilla.org/en-US/docs/Web/HTML", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 186517 } }, "anchors": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1318, "chars": 5275, "content_recall": 0.7391, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7798, "f_coverage": 0.7798, "f_balanced": 0.85, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1335, "chars": 5341, "content_recall": 0.7404, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7809, "f_coverage": 0.7809, "f_balanced": 0.8508, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1210, "chars": 4840, "content_recall": 0.6594, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7076, "f_coverage": 0.7076, "f_balanced": 0.7947, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1736, "chars": 6946, "content_recall": 0.8419, "noise_retention": 0.0015, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8692, "f_coverage": 0.8692, "f_balanced": 0.9135, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1287, "chars": 5149, "content_recall": 0.6234, "noise_retention": 0.0015, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.674, "f_coverage": 0.674, "f_balanced": 0.7676, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9589, "chars": 38358, "content_recall": 0.7841, "noise_retention": 0.1932, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.209, "f_precision": 0.7885, "f_coverage": 0.7885, "f_balanced": 0.7953, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9689, "chars": 38758, "content_recall": 0.7841, "noise_retention": 0.1978, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.206, "f_precision": 0.7876, "f_coverage": 0.7876, "f_balanced": 0.793, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3006, "chars": 12026, "content_recall": 0.8432, "noise_retention": 0.9583, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.333, "f_precision": 0.1742, "f_coverage": 0.1742, "f_balanced": 0.0795, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9574, "chars": 38299, "content_recall": 0.7841, "noise_retention": 0.1932, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.209, "f_precision": 0.7885, "f_coverage": 0.7885, "f_balanced": 0.7953, "anchor_diag": { "content_chars": 5966, "noise_chars": 11238, "content_ngrams": 778, "noise_ngrams": 647, "ambiguous_ngrams_removed": 0, "content_sentences": 57 }, "notes": "" } }, "scoreable": true }, "mdn-http": { "meta": { "id": "mdn-http", "url": "https://developer.mozilla.org/en-US/docs/Web/HTTP", "requested_url": "https://developer.mozilla.org/en-US/docs/Web/HTTP", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 222158 } }, "anchors": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2435, "chars": 9743, "content_recall": 0.8472, "noise_retention": 0.0, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.053, "f_precision": 0.8739, "f_coverage": 0.8739, "f_balanced": 0.9173, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2540, "chars": 10163, "content_recall": 0.8979, "noise_retention": 0.0, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.969, "f_precision": 0.9166, "f_coverage": 0.9166, "f_balanced": 0.9462, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1925, "chars": 7700, "content_recall": 0.6708, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.718, "f_coverage": 0.718, "f_balanced": 0.8029, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2660, "chars": 10640, "content_recall": 0.8709, "noise_retention": 0.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.504, "f_precision": 0.894, "f_coverage": 0.894, "f_balanced": 0.931, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2421, "chars": 9684, "content_recall": 0.8129, "noise_retention": 0.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.652, "f_precision": 0.8445, "f_coverage": 0.8445, "f_balanced": 0.8968, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 14181, "chars": 56727, "content_recall": 0.8333, "noise_retention": 0.2941, "noise_keyword_total": 17, "noise_per_1k_tokens": 1.199, "f_precision": 0.8043, "f_coverage": 0.8043, "f_balanced": 0.7643, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 14311, "chars": 57244, "content_recall": 0.8333, "noise_retention": 0.2941, "noise_keyword_total": 17, "noise_per_1k_tokens": 1.188, "f_precision": 0.8043, "f_coverage": 0.8043, "f_balanced": 0.7643, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 5029, "chars": 20117, "content_recall": 0.8717, "noise_retention": 0.9257, "noise_keyword_total": 9, "noise_per_1k_tokens": 1.79, "f_precision": 0.2771, "f_coverage": 0.2771, "f_balanced": 0.1369, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 14166, "chars": 56664, "content_recall": 0.8333, "noise_retention": 0.2941, "noise_keyword_total": 17, "noise_per_1k_tokens": 1.2, "f_precision": 0.8043, "f_coverage": 0.8043, "f_balanced": 0.7643, "anchor_diag": { "content_chars": 9550, "noise_chars": 5718, "content_ngrams": 1224, "noise_ngrams": 323, "ambiguous_ngrams_removed": 0, "content_sentences": 77 }, "notes": "" } }, "scoreable": true }, "mdn-js": { "meta": { "id": "mdn-js", "url": "https://developer.mozilla.org/en-US/docs/Web/JavaScript", "requested_url": "https://developer.mozilla.org/en-US/docs/Web/JavaScript", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 203818 } }, "anchors": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1357, "chars": 5428, "content_recall": 0.5518, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6061, "f_coverage": 0.6061, "f_balanced": 0.7112, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1357, "chars": 5428, "content_recall": 0.5518, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6061, "f_coverage": 0.6061, "f_balanced": 0.7112, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 917, "chars": 3670, "content_recall": 0.5113, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5667, "f_coverage": 0.5667, "f_balanced": 0.6767, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1440, "chars": 5763, "content_recall": 0.8479, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8745, "f_coverage": 0.8745, "f_balanced": 0.9177, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "readability": { "method": "readability", "tokens": 846, "chars": 3386, "content_recall": 0.4531, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5087, "f_coverage": 0.5087, "f_balanced": 0.6236, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 15132, "chars": 60528, "content_recall": 0.6683, "noise_retention": 0.2932, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.132, "f_precision": 0.6756, "f_coverage": 0.6756, "f_balanced": 0.687, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 15323, "chars": 61295, "content_recall": 0.6683, "noise_retention": 0.2963, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.131, "f_precision": 0.6751, "f_coverage": 0.6751, "f_balanced": 0.6855, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4903, "chars": 19614, "content_recall": 0.856, "noise_retention": 0.9259, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.204, "f_precision": 0.2751, "f_coverage": 0.2751, "f_balanced": 0.1363, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 15125, "chars": 60502, "content_recall": 0.6683, "noise_retention": 0.2932, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.132, "f_precision": 0.6756, "f_coverage": 0.6756, "f_balanced": 0.687, "anchor_diag": { "content_chars": 5005, "noise_chars": 5752, "content_ngrams": 618, "noise_ngrams": 324, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" } }, "scoreable": true }, "milvus-docs": { "meta": { "id": "milvus-docs", "url": "https://milvus.io/docs", "requested_url": "https://milvus.io/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 232351 } }, "anchors": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 281, "chars": 1125, "content_recall": 0.7153, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7585, "f_coverage": 0.7585, "f_balanced": 0.834, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 336, "chars": 1346, "content_recall": 0.9167, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9322, "f_coverage": 0.9322, "f_balanced": 0.9565, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 249, "chars": 997, "content_recall": 0.5694, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6231, "f_coverage": 0.6231, "f_balanced": 0.7257, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 274, "chars": 1096, "content_recall": 0.6667, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7143, "f_coverage": 0.7143, "f_balanced": 0.8, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "readability": { "method": "readability", "tokens": 67, "chars": 268, "content_recall": 0.1667, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2, "f_coverage": 0.2, "f_balanced": 0.2857, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2343, "chars": 9375, "content_recall": 0.6944, "noise_retention": 0.1875, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.854, "f_precision": 0.7152, "f_coverage": 0.7152, "f_balanced": 0.7488, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2447, "chars": 9789, "content_recall": 0.6944, "noise_retention": 0.1607, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.817, "f_precision": 0.7193, "f_coverage": 0.7193, "f_balanced": 0.76, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 651, "chars": 2604, "content_recall": 0.8333, "noise_retention": 0.8929, "noise_keyword_total": 2, "noise_per_1k_tokens": 3.072, "f_precision": 0.3538, "f_coverage": 0.3538, "f_balanced": 0.1899, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2334, "chars": 9337, "content_recall": 0.6944, "noise_retention": 0.1875, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.857, "f_precision": 0.7152, "f_coverage": 0.7152, "f_balanced": 0.7488, "anchor_diag": { "content_chars": 1124, "noise_chars": 1021, "content_ngrams": 144, "noise_ngrams": 112, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" } }, "scoreable": true }, "mixpanel-docs": { "meta": { "id": "mixpanel-docs", "url": "https://docs.mixpanel.com/docs/what-is-mixpanel", "requested_url": "https://docs.mixpanel.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 373360 } }, "anchors": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 147, "chars": 591, "content_recall": 0.7037, "noise_retention": 0.0732, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7393, "f_coverage": 0.7393, "f_balanced": 0.8, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 147, "chars": 591, "content_recall": 0.7037, "noise_retention": 0.0732, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7393, "f_coverage": 0.7393, "f_balanced": 0.8, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 117, "chars": 471, "content_recall": 0.1481, "noise_retention": 0.0732, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1781, "f_coverage": 0.1781, "f_balanced": 0.2555, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 380, "chars": 1522, "content_recall": 0.7037, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.748, "f_coverage": 0.748, "f_balanced": 0.8261, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" }, "readability": { "method": "readability", "tokens": 533, "chars": 2134, "content_recall": 0.7037, "noise_retention": 0.0081, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7471, "f_coverage": 0.7471, "f_balanced": 0.8233, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1788, "chars": 7155, "content_recall": 0.7037, "noise_retention": 0.2358, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.715, "f_coverage": 0.715, "f_balanced": 0.7327, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1758, "chars": 7032, "content_recall": 0.7037, "noise_retention": 0.2358, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.715, "f_coverage": 0.715, "f_balanced": 0.7327, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 900, "chars": 3600, "content_recall": 0.7037, "noise_retention": 0.9024, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3138, "f_coverage": 0.3138, "f_balanced": 0.1714, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1773, "chars": 7095, "content_recall": 0.7037, "noise_retention": 0.2358, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.715, "f_coverage": 0.715, "f_balanced": 0.7327, "anchor_diag": { "content_chars": 276, "noise_chars": 1001, "content_ngrams": 27, "noise_ngrams": 123, "ambiguous_ngrams_removed": 10, "content_sentences": 4 }, "notes": "" } }, "scoreable": false }, "mkdocs-docs": { "meta": { "id": "mkdocs-docs", "url": "https://www.mkdocs.org/", "requested_url": "https://www.mkdocs.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 14735 } }, "anchors": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 500, "chars": 2003, "content_recall": 0.6528, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7015, "f_coverage": 0.7015, "f_balanced": 0.7899, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 510, "chars": 2041, "content_recall": 0.6736, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7207, "f_coverage": 0.7207, "f_balanced": 0.805, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 500, "chars": 2003, "content_recall": 0.6528, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7015, "f_coverage": 0.7015, "f_balanced": 0.7899, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 312, "chars": 1248, "content_recall": 0.8889, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9091, "f_coverage": 0.9091, "f_balanced": 0.9412, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "readability": { "method": "readability", "tokens": 233, "chars": 932, "content_recall": 0.5139, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5692, "f_coverage": 0.5692, "f_balanced": 0.6789, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 831, "chars": 3326, "content_recall": 0.6736, "noise_retention": 0.125, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7061, "f_coverage": 0.7061, "f_balanced": 0.7612, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 830, "chars": 3323, "content_recall": 0.6736, "noise_retention": 0.125, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7061, "f_coverage": 0.7061, "f_balanced": 0.7612, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 510, "chars": 2043, "content_recall": 0.8889, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 820, "chars": 3282, "content_recall": 0.6736, "noise_retention": 0.125, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7061, "f_coverage": 0.7061, "f_balanced": 0.7612, "anchor_diag": { "content_chars": 1110, "noise_chars": 97, "content_ngrams": 144, "noise_ngrams": 8, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" } }, "scoreable": true }, "mocha-docs": { "meta": { "id": "mocha-docs", "url": "https://mochajs.org/", "requested_url": "https://mochajs.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 64600 } }, "anchors": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 379, "chars": 1517, "content_recall": 0.6903, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7358, "f_coverage": 0.7358, "f_balanced": 0.8168, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 379, "chars": 1517, "content_recall": 0.6903, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7358, "f_coverage": 0.7358, "f_balanced": 0.8168, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 345, "chars": 1382, "content_recall": 0.6283, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6788, "f_coverage": 0.6788, "f_balanced": 0.7717, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 254, "chars": 1019, "content_recall": 0.8938, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9132, "f_coverage": 0.9132, "f_balanced": 0.9439, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "readability": { "method": "readability", "tokens": 234, "chars": 939, "content_recall": 0.9646, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9715, "f_coverage": 0.9715, "f_balanced": 0.982, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3995, "chars": 15980, "content_recall": 0.6195, "noise_retention": 0.2803, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.751, "f_precision": 0.6372, "f_coverage": 0.6372, "f_balanced": 0.6658, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4025, "chars": 16100, "content_recall": 0.6195, "noise_retention": 0.3096, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.745, "f_precision": 0.6325, "f_coverage": 0.6325, "f_balanced": 0.653, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 749, "chars": 2998, "content_recall": 0.8938, "noise_retention": 0.9665, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.67, "f_precision": 0.1456, "f_coverage": 0.1456, "f_balanced": 0.0645, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3982, "chars": 15930, "content_recall": 0.6195, "noise_retention": 0.2803, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.753, "f_precision": 0.6372, "f_coverage": 0.6372, "f_balanced": 0.6658, "anchor_diag": { "content_chars": 861, "noise_chars": 1994, "content_ngrams": 113, "noise_ngrams": 239, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" } }, "scoreable": true }, "mockito-docs": { "meta": { "id": "mockito-docs", "url": "https://javadoc.io/doc/org.mockito/mockito-core/5.23.0/index.html", "requested_url": "https://javadoc.io/doc/org.mockito/mockito-core/latest/org/mockito/Mockito.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 55712 } }, "anchors": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 773, "chars": 3095, "content_recall": 0.1154, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1402, "f_coverage": 0.1402, "f_balanced": 0.2069, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 773, "chars": 3095, "content_recall": 0.1154, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1402, "f_coverage": 0.1402, "f_balanced": 0.2069, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 773, "chars": 3095, "content_recall": 0.1154, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1402, "f_coverage": 0.1402, "f_balanced": 0.2069, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 126, "chars": 505, "content_recall": 0.5385, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5932, "f_coverage": 0.5932, "f_balanced": 0.7, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "readability": { "method": "readability", "tokens": 103, "chars": 412, "content_recall": 0.5385, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5932, "f_coverage": 0.5932, "f_balanced": 0.7, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 6311, "chars": 25247, "content_recall": 0.5385, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5932, "f_coverage": 0.5932, "f_balanced": 0.7, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6386, "chars": 25544, "content_recall": 0.5385, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5932, "f_coverage": 0.5932, "f_balanced": 0.7, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1137, "chars": 4550, "content_recall": 0.5385, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5932, "f_coverage": 0.5932, "f_balanced": 0.7, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 6296, "chars": 25187, "content_recall": 0.5385, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5932, "f_coverage": 0.5932, "f_balanced": 0.7, "anchor_diag": { "content_chars": 265, "noise_chars": 0, "content_ngrams": 26, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" } }, "scoreable": false }, "mongodb-atlas": { "meta": { "id": "mongodb-atlas", "url": "https://www.mongodb.com/products/platform", "requested_url": "https://www.mongodb.com/atlas", "category": "marketing", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 526511 } }, "anchors": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1029, "chars": 4119, "content_recall": 0.6688, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7162, "f_coverage": 0.7162, "f_balanced": 0.8015, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1029, "chars": 4119, "content_recall": 0.6688, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7162, "f_coverage": 0.7162, "f_balanced": 0.8015, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 744, "chars": 2977, "content_recall": 0.5597, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6138, "f_coverage": 0.6138, "f_balanced": 0.7177, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 585, "chars": 2342, "content_recall": 0.3774, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.709, "f_precision": 0.431, "f_coverage": 0.431, "f_balanced": 0.5479, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "readability": { "method": "readability", "tokens": 97, "chars": 389, "content_recall": 0.0566, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0698, "f_coverage": 0.0698, "f_balanced": 0.1071, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5618, "chars": 22473, "content_recall": 0.6897, "noise_retention": 0.1851, "noise_keyword_total": 10, "noise_per_1k_tokens": 1.78, "f_precision": 0.7116, "f_coverage": 0.7116, "f_balanced": 0.7471, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5570, "chars": 22282, "content_recall": 0.6855, "noise_retention": 0.1851, "noise_keyword_total": 10, "noise_per_1k_tokens": 1.795, "f_precision": 0.708, "f_coverage": 0.708, "f_balanced": 0.7446, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2208, "chars": 8832, "content_recall": 0.7086, "noise_retention": 0.884, "noise_keyword_total": 8, "noise_per_1k_tokens": 3.623, "f_precision": 0.3505, "f_coverage": 0.3505, "f_balanced": 0.1994, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5671, "chars": 22684, "content_recall": 0.6897, "noise_retention": 0.1851, "noise_keyword_total": 10, "noise_per_1k_tokens": 1.763, "f_precision": 0.7116, "f_coverage": 0.7116, "f_balanced": 0.7471, "anchor_diag": { "content_chars": 4796, "noise_chars": 2804, "content_ngrams": 477, "noise_ngrams": 362, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" } }, "scoreable": true }, "mongodb-docs": { "meta": { "id": "mongodb-docs", "url": "https://www.mongodb.com/docs/", "requested_url": "https://www.mongodb.com/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": true, "bytes": 723722 } }, "anchors": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 677, "chars": 2711, "content_recall": 0.7782, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8143, "f_coverage": 0.8143, "f_balanced": 0.8752, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 684, "chars": 2738, "content_recall": 0.7641, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8019, "f_coverage": 0.8019, "f_balanced": 0.8663, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 489, "chars": 1958, "content_recall": 0.6127, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6641, "f_coverage": 0.6641, "f_balanced": 0.7598, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 602, "chars": 2411, "content_recall": 0.7887, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8235, "f_coverage": 0.8235, "f_balanced": 0.8819, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "readability": { "method": "readability", "tokens": 585, "chars": 2341, "content_recall": 0.7746, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8112, "f_coverage": 0.8112, "f_balanced": 0.873, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4806, "chars": 19227, "content_recall": 0.7746, "noise_retention": 0.157, "noise_keyword_total": 9, "noise_per_1k_tokens": 1.873, "f_precision": 0.7874, "f_coverage": 0.7874, "f_balanced": 0.8074, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4800, "chars": 19203, "content_recall": 0.7746, "noise_retention": 0.157, "noise_keyword_total": 9, "noise_per_1k_tokens": 1.875, "f_precision": 0.7874, "f_coverage": 0.7874, "f_balanced": 0.8074, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1973, "chars": 7895, "content_recall": 0.7887, "noise_retention": 0.8788, "noise_keyword_total": 6, "noise_per_1k_tokens": 3.041, "f_precision": 0.3753, "f_coverage": 0.3753, "f_balanced": 0.2101, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4788, "chars": 19155, "content_recall": 0.7746, "noise_retention": 0.157, "noise_keyword_total": 9, "noise_per_1k_tokens": 1.88, "f_precision": 0.7874, "f_coverage": 0.7874, "f_balanced": 0.8074, "anchor_diag": { "content_chars": 2821, "noise_chars": 5052, "content_ngrams": 284, "noise_ngrams": 363, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" } }, "scoreable": true }, "mypy-docs": { "meta": { "id": "mypy-docs", "url": "https://mypy.readthedocs.io/en/stable/", "requested_url": "https://mypy.readthedocs.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 77473 } }, "anchors": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 494, "chars": 1978, "content_recall": 0.1119, "noise_retention": 0.0556, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1359, "f_coverage": 0.1359, "f_balanced": 0.2001, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 537, "chars": 2149, "content_recall": 0.1119, "noise_retention": 0.0903, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1357, "f_coverage": 0.1357, "f_balanced": 0.1993, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 450, "chars": 1803, "content_recall": 0.1036, "noise_retention": 0.0278, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1262, "f_coverage": 0.1262, "f_balanced": 0.1873, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 405, "chars": 1622, "content_recall": 0.1185, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1439, "f_coverage": 0.1439, "f_balanced": 0.2119, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" }, "readability": { "method": "readability", "tokens": 7, "chars": 29, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8918, "chars": 35673, "content_recall": 0.7111, "noise_retention": 0.1319, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7378, "f_coverage": 0.7378, "f_balanced": 0.7818, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9062, "chars": 36251, "content_recall": 0.7128, "noise_retention": 0.1528, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7362, "f_coverage": 0.7362, "f_balanced": 0.7742, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3610, "chars": 14440, "content_recall": 0.8556, "noise_retention": 0.9444, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2205, "f_coverage": 0.2205, "f_balanced": 0.1043, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8904, "chars": 35616, "content_recall": 0.7111, "noise_retention": 0.1319, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7378, "f_coverage": 0.7378, "f_balanced": 0.7818, "anchor_diag": { "content_chars": 20028, "noise_chars": 1191, "content_ngrams": 1814, "noise_ngrams": 144, "ambiguous_ngrams_removed": 9, "content_sentences": 151 }, "notes": "" } }, "scoreable": true }, "netlify-docs": { "meta": { "id": "netlify-docs", "url": "https://docs.netlify.com/", "requested_url": "https://docs.netlify.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 165982 } }, "anchors": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 973, "chars": 3894, "content_recall": 0.6813, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7277, "f_coverage": 0.7277, "f_balanced": 0.8104, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 973, "chars": 3894, "content_recall": 0.6813, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7277, "f_coverage": 0.7277, "f_balanced": 0.8104, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 851, "chars": 3404, "content_recall": 0.605, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6569, "f_coverage": 0.6569, "f_balanced": 0.7539, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 355, "chars": 1421, "content_recall": 0.2004, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2385, "f_coverage": 0.2385, "f_balanced": 0.3339, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "readability": { "method": "readability", "tokens": 848, "chars": 3394, "content_recall": 0.542, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5966, "f_coverage": 0.5966, "f_balanced": 0.703, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2786, "chars": 11147, "content_recall": 0.7233, "noise_retention": 0.1634, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.718, "f_precision": 0.7434, "f_coverage": 0.7434, "f_balanced": 0.7758, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2912, "chars": 11649, "content_recall": 0.7233, "noise_retention": 0.1569, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.687, "f_precision": 0.7444, "f_coverage": 0.7444, "f_balanced": 0.7786, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1569, "chars": 6277, "content_recall": 0.7424, "noise_retention": 0.9216, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.637, "f_precision": 0.2757, "f_coverage": 0.2757, "f_balanced": 0.1419, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2768, "chars": 11072, "content_recall": 0.7233, "noise_retention": 0.1634, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.723, "f_precision": 0.7434, "f_coverage": 0.7434, "f_balanced": 0.7758, "anchor_diag": { "content_chars": 3943, "noise_chars": 2095, "content_ngrams": 524, "noise_ngrams": 153, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" } }, "scoreable": true }, "newrelic-docs": { "meta": { "id": "newrelic-docs", "url": "https://docs.newrelic.com/", "requested_url": "https://docs.newrelic.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 349803 } }, "anchors": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1262, "chars": 5049, "content_recall": 0.7879, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8228, "f_coverage": 0.8228, "f_balanced": 0.8814, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1262, "chars": 5049, "content_recall": 0.7879, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8228, "f_coverage": 0.8228, "f_balanced": 0.8814, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1196, "chars": 4784, "content_recall": 0.7273, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7692, "f_coverage": 0.7692, "f_balanced": 0.8421, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 106, "chars": 424, "content_recall": 0.0224, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0278, "f_coverage": 0.0278, "f_balanced": 0.0438, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" }, "readability": { "method": "readability", "tokens": 47, "chars": 189, "content_recall": 0.0211, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0262, "f_coverage": 0.0262, "f_balanced": 0.0413, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2205, "chars": 8822, "content_recall": 0.61, "noise_retention": 0.3333, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.814, "f_precision": 0.6206, "f_coverage": 0.6206, "f_balanced": 0.6371, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2189, "chars": 8758, "content_recall": 0.4651, "noise_retention": 0.3333, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.827, "f_precision": 0.495, "f_coverage": 0.495, "f_balanced": 0.5479, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1326, "chars": 5307, "content_recall": 0.7813, "noise_retention": 0.8788, "noise_keyword_total": 3, "noise_per_1k_tokens": 2.262, "f_precision": 0.374, "f_coverage": 0.374, "f_balanced": 0.2099, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2200, "chars": 8801, "content_recall": 0.61, "noise_retention": 0.3333, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.818, "f_precision": 0.6206, "f_coverage": 0.6206, "f_balanced": 0.6371, "anchor_diag": { "content_chars": 8517, "noise_chars": 259, "content_ngrams": 759, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 88 }, "notes": "" } }, "scoreable": true }, "nextjs-app": { "meta": { "id": "nextjs-app", "url": "https://nextjs.org/docs/app", "requested_url": "https://nextjs.org/docs/app", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 466225 } }, "anchors": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 404, "chars": 1618, "content_recall": 0.7826, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8182, "f_coverage": 0.8182, "f_balanced": 0.878, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 410, "chars": 1643, "content_recall": 0.7826, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8182, "f_coverage": 0.8182, "f_balanced": 0.878, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 389, "chars": 1556, "content_recall": 0.7826, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8182, "f_coverage": 0.8182, "f_balanced": 0.878, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 317, "chars": 1270, "content_recall": 0.8012, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8344, "f_coverage": 0.8344, "f_balanced": 0.8897, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "readability": { "method": "readability", "tokens": 20, "chars": 82, "content_recall": 0.0124, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0155, "f_coverage": 0.0155, "f_balanced": 0.0245, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 7629, "chars": 30516, "content_recall": 0.7019, "noise_retention": 0.1824, "noise_keyword_total": 12, "noise_per_1k_tokens": 1.573, "f_precision": 0.7223, "f_coverage": 0.7223, "f_balanced": 0.7553, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 7791, "chars": 31165, "content_recall": 0.5652, "noise_retention": 0.1941, "noise_keyword_total": 12, "noise_per_1k_tokens": 1.54, "f_precision": 0.6011, "f_coverage": 0.6011, "f_balanced": 0.6644, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1824, "chars": 7297, "content_recall": 0.8261, "noise_retention": 0.8118, "noise_keyword_total": 11, "noise_per_1k_tokens": 6.031, "f_precision": 0.4924, "f_coverage": 0.4924, "f_balanced": 0.3066, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 7620, "chars": 30480, "content_recall": 0.7019, "noise_retention": 0.1824, "noise_keyword_total": 12, "noise_per_1k_tokens": 1.575, "f_precision": 0.7223, "f_coverage": 0.7223, "f_balanced": 0.7553, "anchor_diag": { "content_chars": 1687, "noise_chars": 2264, "content_ngrams": 161, "noise_ngrams": 170, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" } }, "scoreable": true }, "nextjs-docs": { "meta": { "id": "nextjs-docs", "url": "https://nextjs.org/docs", "requested_url": "https://nextjs.org/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 475683 } }, "anchors": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 745, "chars": 2983, "content_recall": 0.7683, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8057, "f_coverage": 0.8057, "f_balanced": 0.869, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 774, "chars": 3099, "content_recall": 0.8006, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8338, "f_coverage": 0.8338, "f_balanced": 0.8893, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 745, "chars": 2983, "content_recall": 0.7683, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8057, "f_coverage": 0.8057, "f_balanced": 0.869, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 652, "chars": 2609, "content_recall": 0.7859, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8211, "f_coverage": 0.8211, "f_balanced": 0.8801, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" }, "readability": { "method": "readability", "tokens": 624, "chars": 2499, "content_recall": 0.7977, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8313, "f_coverage": 0.8313, "f_balanced": 0.8874, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8067, "chars": 32268, "content_recall": 0.7683, "noise_retention": 0.2216, "noise_keyword_total": 12, "noise_per_1k_tokens": 1.488, "f_precision": 0.7703, "f_coverage": 0.7703, "f_balanced": 0.7733, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 8204, "chars": 32816, "content_recall": 0.7507, "noise_retention": 0.2865, "noise_keyword_total": 12, "noise_per_1k_tokens": 1.463, "f_precision": 0.743, "f_coverage": 0.743, "f_balanced": 0.7317, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2224, "chars": 8899, "content_recall": 0.8475, "noise_retention": 0.8703, "noise_keyword_total": 11, "noise_per_1k_tokens": 4.946, "f_precision": 0.4023, "f_coverage": 0.4023, "f_balanced": 0.225, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8061, "chars": 32244, "content_recall": 0.7683, "noise_retention": 0.2216, "noise_keyword_total": 12, "noise_per_1k_tokens": 1.489, "f_precision": 0.7703, "f_coverage": 0.7703, "f_balanced": 0.7733, "anchor_diag": { "content_chars": 2875, "noise_chars": 2374, "content_ngrams": 341, "noise_ngrams": 185, "ambiguous_ngrams_removed": 1, "content_sentences": 27 }, "notes": "" } }, "scoreable": true }, "nginx-docs": { "meta": { "id": "nginx-docs", "url": "https://nginx.org/en/docs/", "requested_url": "https://nginx.org/en/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 13950 } }, "anchors": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 41, "chars": 165, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 41, "chars": 165, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 41, "chars": 165, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 89, "chars": 359, "content_recall": 0.1905, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2273, "f_coverage": 0.2273, "f_balanced": 0.32, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" }, "readability": { "method": "readability", "tokens": 32, "chars": 131, "content_recall": 0.0476, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0588, "f_coverage": 0.0588, "f_balanced": 0.0909, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2340, "chars": 9363, "content_recall": 0.2857, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3333, "f_coverage": 0.3333, "f_balanced": 0.4444, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2380, "chars": 9523, "content_recall": 0.2857, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3333, "f_coverage": 0.3333, "f_balanced": 0.4444, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 906, "chars": 3627, "content_recall": 0.5714, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.625, "f_coverage": 0.625, "f_balanced": 0.7273, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2350, "chars": 9400, "content_recall": 0.2857, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3333, "f_coverage": 0.3333, "f_balanced": 0.4444, "anchor_diag": { "content_chars": 795, "noise_chars": 160, "content_ngrams": 84, "noise_ngrams": 0, "ambiguous_ngrams_removed": 16, "content_sentences": 6 }, "notes": "" } }, "scoreable": true }, "nist-cyber": { "meta": { "id": "nist-cyber", "url": "https://www.nist.gov/cyberframework", "requested_url": "https://www.nist.gov/cyberframework", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 90351 } }, "anchors": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 567, "chars": 2271, "content_recall": 0.7245, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7667, "f_coverage": 0.7667, "f_balanced": 0.8402, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 584, "chars": 2339, "content_recall": 0.7313, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7728, "f_coverage": 0.7728, "f_balanced": 0.8448, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 469, "chars": 1876, "content_recall": 0.6156, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6669, "f_coverage": 0.6669, "f_balanced": 0.7621, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 416, "chars": 1665, "content_recall": 0.6463, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6955, "f_coverage": 0.6955, "f_balanced": 0.7851, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "readability": { "method": "readability", "tokens": 56, "chars": 224, "content_recall": 0.0442, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0547, "f_coverage": 0.0547, "f_balanced": 0.0847, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3017, "chars": 12069, "content_recall": 0.7585, "noise_retention": 0.1429, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.994, "f_precision": 0.7764, "f_coverage": 0.7764, "f_balanced": 0.8048, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3082, "chars": 12328, "content_recall": 0.7585, "noise_retention": 0.1429, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.973, "f_precision": 0.7764, "f_coverage": 0.7764, "f_balanced": 0.8048, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1345, "chars": 5381, "content_recall": 0.8401, "noise_retention": 0.9379, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.743, "f_precision": 0.2397, "f_coverage": 0.2397, "f_balanced": 0.1157, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2998, "chars": 11993, "content_recall": 0.7585, "noise_retention": 0.146, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.001, "f_precision": 0.7759, "f_coverage": 0.7759, "f_balanced": 0.8034, "anchor_diag": { "content_chars": 2362, "noise_chars": 5066, "content_ngrams": 294, "noise_ngrams": 322, "ambiguous_ngrams_removed": 0, "content_sentences": 22 }, "notes": "" } }, "scoreable": true }, "nltk-docs": { "meta": { "id": "nltk-docs", "url": "https://www.nltk.org/", "requested_url": "https://www.nltk.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 11567 } }, "anchors": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 723, "chars": 2893, "content_recall": 0.8865, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9071, "f_coverage": 0.9071, "f_balanced": 0.9398, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 730, "chars": 2922, "content_recall": 0.8865, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9071, "f_coverage": 0.9071, "f_balanced": 0.9398, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 690, "chars": 2760, "content_recall": 0.844, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8712, "f_coverage": 0.8712, "f_balanced": 0.9154, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 658, "chars": 2635, "content_recall": 0.9149, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9307, "f_coverage": 0.9307, "f_balanced": 0.9556, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" }, "readability": { "method": "readability", "tokens": 656, "chars": 2624, "content_recall": 0.9149, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9307, "f_coverage": 0.9307, "f_balanced": 0.9556, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 976, "chars": 3907, "content_recall": 0.8582, "noise_retention": 0.1143, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.025, "f_precision": 0.8635, "f_coverage": 0.8635, "f_balanced": 0.8717, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 966, "chars": 3864, "content_recall": 0.8582, "noise_retention": 0.1143, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.035, "f_precision": 0.8635, "f_coverage": 0.8635, "f_balanced": 0.8717, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 747, "chars": 2991, "content_recall": 0.9149, "noise_retention": 0.8857, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.339, "f_precision": 0.381, "f_coverage": 0.381, "f_balanced": 0.2032, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 966, "chars": 3866, "content_recall": 0.8582, "noise_retention": 0.1143, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.035, "f_precision": 0.8635, "f_coverage": 0.8635, "f_balanced": 0.8717, "anchor_diag": { "content_chars": 3412, "noise_chars": 277, "content_ngrams": 282, "noise_ngrams": 35, "ambiguous_ngrams_removed": 0, "content_sentences": 27 }, "notes": "" } }, "scoreable": true }, "nodejs-docs": { "meta": { "id": "nodejs-docs", "url": "https://nodejs.org/docs/latest/api/", "requested_url": "https://nodejs.org/docs/latest/api/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 18729 } }, "anchors": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 26, "chars": 106, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 26, "chars": 106, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 26, "chars": 106, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 740, "chars": 2963, "content_recall": 0.0, "noise_retention": 0.9507, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 14, "chars": 59, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2180, "chars": 8723, "content_recall": 0.0, "noise_retention": 0.0352, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2316, "chars": 9264, "content_recall": 0.0, "noise_retention": 0.0423, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 750, "chars": 3001, "content_recall": 0.0, "noise_retention": 0.9507, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2171, "chars": 8686, "content_recall": 0.0, "noise_retention": 0.0352, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 64, "noise_chars": 2053, "content_ngrams": 3, "noise_ngrams": 142, "ambiguous_ngrams_removed": 1, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "nodejs-fs": { "meta": { "id": "nodejs-fs", "url": "https://nodejs.org/docs/latest/api/fs.html", "requested_url": "https://nodejs.org/docs/latest/api/fs.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 1105832 } }, "anchors": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 70164, "chars": 280656, "content_recall": 0.7022, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7466, "f_coverage": 0.7466, "f_balanced": 0.825, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 73393, "chars": 293574, "content_recall": 0.7368, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7777, "f_coverage": 0.7777, "f_balanced": 0.8485, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 64277, "chars": 257108, "content_recall": 0.6304, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6807, "f_coverage": 0.6807, "f_balanced": 0.7733, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 52393, "chars": 209573, "content_recall": 0.7539, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7929, "f_coverage": 0.7929, "f_balanced": 0.8597, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" }, "readability": { "method": "readability", "tokens": 43588, "chars": 174353, "content_recall": 0.7061, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7502, "f_coverage": 0.7502, "f_balanced": 0.8277, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 117990, "chars": 471961, "content_recall": 0.7102, "noise_retention": 0.0088, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7529, "f_coverage": 0.7529, "f_balanced": 0.8275, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 111856, "chars": 447425, "content_recall": 0.7261, "noise_retention": 0.0088, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7671, "f_coverage": 0.7671, "f_balanced": 0.8382, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 66244, "chars": 264976, "content_recall": 0.8655, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 117975, "chars": 471901, "content_recall": 0.7102, "noise_retention": 0.0088, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7529, "f_coverage": 0.7529, "f_balanced": 0.8275, "anchor_diag": { "content_chars": 323275, "noise_chars": 893, "content_ngrams": 18298, "noise_ngrams": 114, "ambiguous_ngrams_removed": 0, "content_sentences": 3458 }, "notes": "" } }, "scoreable": true }, "notion-api": { "meta": { "id": "notion-api", "url": "https://developers.notion.com/guides/get-started/overview", "requested_url": "https://developers.notion.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": true, "bytes": 421203 } }, "anchors": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1128, "chars": 4514, "content_recall": 0.7573, "noise_retention": 0.0763, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7856, "f_coverage": 0.7856, "f_balanced": 0.8322, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1128, "chars": 4514, "content_recall": 0.7573, "noise_retention": 0.0763, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7856, "f_coverage": 0.7856, "f_balanced": 0.8322, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1064, "chars": 4259, "content_recall": 0.7039, "noise_retention": 0.0763, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7391, "f_coverage": 0.7391, "f_balanced": 0.7989, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1271, "chars": 5085, "content_recall": 0.6456, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.787, "f_precision": 0.6949, "f_coverage": 0.6949, "f_balanced": 0.7847, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1236, "chars": 4946, "content_recall": 0.5364, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.809, "f_precision": 0.5912, "f_coverage": 0.5912, "f_balanced": 0.6983, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3296, "chars": 13186, "content_recall": 0.7816, "noise_retention": 0.458, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.303, "f_precision": 0.7181, "f_coverage": 0.7181, "f_balanced": 0.6401, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3222, "chars": 12891, "content_recall": 0.7816, "noise_retention": 0.458, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.31, "f_precision": 0.7181, "f_coverage": 0.7181, "f_balanced": 0.6401, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1915, "chars": 7661, "content_recall": 0.8277, "noise_retention": 0.9313, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.522, "f_precision": 0.2579, "f_coverage": 0.2579, "f_balanced": 0.1269, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3290, "chars": 13163, "content_recall": 0.7816, "noise_retention": 0.458, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.304, "f_precision": 0.7181, "f_coverage": 0.7181, "f_balanced": 0.6401, "anchor_diag": { "content_chars": 3383, "noise_chars": 1135, "content_ngrams": 412, "noise_ngrams": 131, "ambiguous_ngrams_removed": 16, "content_sentences": 38 }, "notes": "" } }, "scoreable": true }, "npm-docs": { "meta": { "id": "npm-docs", "url": "https://docs.npmjs.com/", "requested_url": "https://docs.npmjs.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 476396 } }, "anchors": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 55, "chars": 223, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 55, "chars": 223, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 55, "chars": 223, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1373, "chars": 5493, "content_recall": 1.0, "noise_retention": 1.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.728, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "readability": { "method": "readability", "tokens": 23, "chars": 93, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3585, "chars": 14343, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.279, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3704, "chars": 14819, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.27, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1375, "chars": 5502, "content_recall": 1.0, "noise_retention": 1.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.727, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3583, "chars": 14332, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.279, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 71, "noise_chars": 33, "content_ngrams": 6, "noise_ngrams": 2, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" } }, "scoreable": false }, "numpy-docs": { "meta": { "id": "numpy-docs", "url": "https://numpy.org/doc/", "requested_url": "https://numpy.org/doc/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 9957 } }, "anchors": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 21, "chars": 86, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 21, "chars": 86, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 21, "chars": 86, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 324, "chars": 1297, "content_recall": 0.5, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5556, "f_coverage": 0.5556, "f_balanced": 0.6667, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "readability": { "method": "readability", "tokens": 6, "chars": 24, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 819, "chars": 3277, "content_recall": 0.3, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3488, "f_coverage": 0.3488, "f_balanced": 0.4615, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 808, "chars": 3232, "content_recall": 0.3, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3488, "f_coverage": 0.3488, "f_balanced": 0.4615, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 358, "chars": 1433, "content_recall": 0.65, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6989, "f_coverage": 0.6989, "f_balanced": 0.7879, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 803, "chars": 3214, "content_recall": 0.3, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3488, "f_coverage": 0.3488, "f_balanced": 0.4615, "anchor_diag": { "content_chars": 2384, "noise_chars": 0, "content_ngrams": 20, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 34 }, "notes": "" } }, "scoreable": false }, "nvidia-cuda": { "meta": { "id": "nvidia-cuda", "url": "https://docs.nvidia.com/cuda/", "requested_url": "https://docs.nvidia.com/cuda/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 47145 } }, "anchors": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 366, "chars": 1466, "content_recall": 0.7259, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.768, "f_coverage": 0.768, "f_balanced": 0.8412, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 366, "chars": 1466, "content_recall": 0.7259, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.768, "f_coverage": 0.768, "f_balanced": 0.8412, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 355, "chars": 1420, "content_recall": 0.7111, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7547, "f_coverage": 0.7547, "f_balanced": 0.8312, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 231, "chars": 925, "content_recall": 0.7333, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7746, "f_coverage": 0.7746, "f_balanced": 0.8462, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "readability": { "method": "readability", "tokens": 81, "chars": 327, "content_recall": 0.2148, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2548, "f_coverage": 0.2548, "f_balanced": 0.3537, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3149, "chars": 12599, "content_recall": 0.6667, "noise_retention": 0.1786, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.318, "f_precision": 0.6928, "f_coverage": 0.6928, "f_balanced": 0.736, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3194, "chars": 12778, "content_recall": 0.6667, "noise_retention": 0.1786, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.313, "f_precision": 0.6928, "f_coverage": 0.6928, "f_balanced": 0.736, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 765, "chars": 3063, "content_recall": 0.8074, "noise_retention": 0.7857, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.307, "f_precision": 0.5197, "f_coverage": 0.5197, "f_balanced": 0.3387, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1883, "chars": 7533, "content_recall": 0.6667, "noise_retention": 0.2321, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.531, "f_precision": 0.6847, "f_coverage": 0.6847, "f_balanced": 0.7137, "anchor_diag": { "content_chars": 1086, "noise_chars": 470, "content_ngrams": 135, "noise_ngrams": 56, "ambiguous_ngrams_removed": 0, "content_sentences": 12 }, "notes": "" } }, "scoreable": true }, "nvidia-dgx": { "meta": { "id": "nvidia-dgx", "url": "https://www.nvidia.com/en-us/data-center/dgx-platform/", "requested_url": "https://www.nvidia.com/en-us/data-center/dgx-platform/", "category": "marketing", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 380511 } }, "anchors": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2311, "chars": 9247, "content_recall": 0.7586, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7971, "f_coverage": 0.7971, "f_balanced": 0.8627, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2357, "chars": 9428, "content_recall": 0.7691, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8063, "f_coverage": 0.8063, "f_balanced": 0.8695, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1855, "chars": 7422, "content_recall": 0.5611, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6151, "f_coverage": 0.6151, "f_balanced": 0.7189, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1123, "chars": 4492, "content_recall": 0.5099, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5653, "f_coverage": 0.5653, "f_balanced": 0.6754, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" }, "readability": { "method": "readability", "tokens": 357, "chars": 1428, "content_recall": 0.1651, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1982, "f_coverage": 0.1982, "f_balanced": 0.2834, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 9653, "chars": 38614, "content_recall": 0.7858, "noise_retention": 0.6083, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.311, "f_precision": 0.6542, "f_coverage": 0.6542, "f_balanced": 0.5228, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 9491, "chars": 37966, "content_recall": 0.7858, "noise_retention": 0.6083, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.316, "f_precision": 0.6542, "f_coverage": 0.6542, "f_balanced": 0.5228, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4764, "chars": 19059, "content_recall": 0.8527, "noise_retention": 0.9685, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.42, "f_precision": 0.1372, "f_coverage": 0.1372, "f_balanced": 0.0607, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9595, "chars": 38382, "content_recall": 0.7858, "noise_retention": 0.6083, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.313, "f_precision": 0.6542, "f_coverage": 0.6542, "f_balanced": 0.5228, "anchor_diag": { "content_chars": 7779, "noise_chars": 7894, "content_ngrams": 957, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 63 }, "notes": "" } }, "scoreable": true }, "nvidia-h100": { "meta": { "id": "nvidia-h100", "url": "https://www.nvidia.com/en-us/data-center/h100/", "requested_url": "https://www.nvidia.com/en-us/data-center/h100/", "category": "marketing", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": true, "bytes": 287758 } }, "anchors": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2823, "chars": 11295, "content_recall": 0.8321, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.861, "f_coverage": 0.861, "f_balanced": 0.9084, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2823, "chars": 11295, "content_recall": 0.8321, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.861, "f_coverage": 0.861, "f_balanced": 0.9084, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2686, "chars": 10745, "content_recall": 0.807, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8394, "f_coverage": 0.8394, "f_balanced": 0.8932, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2266, "chars": 9065, "content_recall": 0.8348, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8633, "f_coverage": 0.8633, "f_balanced": 0.91, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" }, "readability": { "method": "readability", "tokens": 209, "chars": 839, "content_recall": 0.0862, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1054, "f_coverage": 0.1054, "f_balanced": 0.1587, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8484, "chars": 33937, "content_recall": 0.8869, "noise_retention": 0.6083, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.354, "f_precision": 0.7079, "f_coverage": 0.7079, "f_balanced": 0.5434, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 8439, "chars": 33756, "content_recall": 0.8824, "noise_retention": 0.6083, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.355, "f_precision": 0.7056, "f_coverage": 0.7056, "f_balanced": 0.5426, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 5024, "chars": 20099, "content_recall": 0.9282, "noise_retention": 0.9685, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.398, "f_precision": 0.1387, "f_coverage": 0.1387, "f_balanced": 0.0609, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8410, "chars": 33641, "content_recall": 0.8869, "noise_retention": 0.6083, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.357, "f_precision": 0.7079, "f_coverage": 0.7079, "f_balanced": 0.5434, "anchor_diag": { "content_chars": 9093, "noise_chars": 7894, "content_ngrams": 1114, "noise_ngrams": 508, "ambiguous_ngrams_removed": 1, "content_sentences": 67 }, "notes": "" } }, "scoreable": true }, "nvidia-tensorrt": { "meta": { "id": "nvidia-tensorrt", "url": "https://docs.nvidia.com/deeplearning/tensorrt/latest/index.html", "requested_url": "https://docs.nvidia.com/deeplearning/tensorrt/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 59723 } }, "anchors": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1682, "chars": 6728, "content_recall": 0.8344, "noise_retention": 0.0051, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8622, "f_coverage": 0.8622, "f_balanced": 0.9076, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1682, "chars": 6728, "content_recall": 0.8344, "noise_retention": 0.0051, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8622, "f_coverage": 0.8622, "f_balanced": 0.9076, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1601, "chars": 6407, "content_recall": 0.7851, "noise_retention": 0.0051, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8197, "f_coverage": 0.8197, "f_balanced": 0.8776, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1691, "chars": 6766, "content_recall": 0.8191, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8498, "f_coverage": 0.8498, "f_balanced": 0.9005, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" }, "readability": { "method": "readability", "tokens": 799, "chars": 3199, "content_recall": 0.4057, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4604, "f_coverage": 0.4604, "f_balanced": 0.5772, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4875, "chars": 19503, "content_recall": 0.7489, "noise_retention": 0.11, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.205, "f_precision": 0.7734, "f_coverage": 0.7734, "f_balanced": 0.8134, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4900, "chars": 19602, "content_recall": 0.7544, "noise_retention": 0.11, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.204, "f_precision": 0.7781, "f_coverage": 0.7781, "f_balanced": 0.8166, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2591, "chars": 10366, "content_recall": 0.8191, "noise_retention": 0.9795, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.386, "f_precision": 0.093, "f_coverage": 0.093, "f_balanced": 0.0399, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4858, "chars": 19435, "content_recall": 0.7489, "noise_retention": 0.11, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.206, "f_precision": 0.7734, "f_coverage": 0.7734, "f_balanced": 0.8134, "anchor_diag": { "content_chars": 12251, "noise_chars": 3570, "content_ngrams": 912, "noise_ngrams": 391, "ambiguous_ngrams_removed": 1, "content_sentences": 95 }, "notes": "" } }, "scoreable": true }, "okta-docs": { "meta": { "id": "okta-docs", "url": "https://developer.okta.com/", "requested_url": "https://developer.okta.com/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 35061 } }, "anchors": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 57, "chars": 228, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 57, "chars": 228, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 57, "chars": 228, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 540, "chars": 2163, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "readability": { "method": "readability", "tokens": 63, "chars": 254, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1618, "chars": 6474, "content_recall": 1.0, "noise_retention": 0.3448, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.854, "f_precision": 0.9048, "f_coverage": 0.9048, "f_balanced": 0.7917, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1724, "chars": 6896, "content_recall": 1.0, "noise_retention": 0.3448, "noise_keyword_total": 4, "noise_per_1k_tokens": 2.32, "f_precision": 0.9048, "f_coverage": 0.9048, "f_balanced": 0.7917, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 931, "chars": 3725, "content_recall": 1.0, "noise_retention": 0.8621, "noise_keyword_total": 3, "noise_per_1k_tokens": 3.222, "f_precision": 0.4444, "f_coverage": 0.4444, "f_balanced": 0.2424, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1606, "chars": 6426, "content_recall": 1.0, "noise_retention": 0.3448, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.868, "f_precision": 0.9048, "f_coverage": 0.9048, "f_balanced": 0.7917, "anchor_diag": { "content_chars": 50, "noise_chars": 646, "content_ngrams": 3, "noise_ngrams": 87, "ambiguous_ngrams_removed": 0, "content_sentences": 1 }, "notes": "" } }, "scoreable": false }, "openai-api": { "meta": { "id": "openai-api", "url": "https://developers.openai.com/api/reference/overview", "requested_url": "https://platform.openai.com/docs/api-reference", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 359569 } }, "anchors": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1590, "chars": 6363, "content_recall": 0.8686, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.892, "f_coverage": 0.892, "f_balanced": 0.9297, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1685, "chars": 6743, "content_recall": 0.9099, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9266, "f_coverage": 0.9266, "f_balanced": 0.9528, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1486, "chars": 5947, "content_recall": 0.8085, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8407, "f_coverage": 0.8407, "f_balanced": 0.8941, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1663, "chars": 6655, "content_recall": 0.9212, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9359, "f_coverage": 0.9359, "f_balanced": 0.959, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1492, "chars": 5971, "content_recall": 0.9136, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9297, "f_coverage": 0.9297, "f_balanced": 0.9549, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 13126, "chars": 52504, "content_recall": 0.8436, "noise_retention": 0.2694, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8182, "f_coverage": 0.8182, "f_balanced": 0.783, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 13338, "chars": 53352, "content_recall": 0.8436, "noise_retention": 0.2694, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8182, "f_coverage": 0.8182, "f_balanced": 0.783, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3883, "chars": 15535, "content_recall": 0.9274, "noise_retention": 0.943, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2287, "f_coverage": 0.2287, "f_balanced": 0.1074, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 13099, "chars": 52398, "content_recall": 0.8436, "noise_retention": 0.2694, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8182, "f_coverage": 0.8182, "f_balanced": 0.783, "anchor_diag": { "content_chars": 6933, "noise_chars": 3026, "content_ngrams": 799, "noise_ngrams": 193, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" } }, "scoreable": true }, "openai-docs": { "meta": { "id": "openai-docs", "url": "https://platform.openai.com/", "requested_url": "https://platform.openai.com/docs/overview", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 4875 } }, "anchors": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 16, "chars": 67, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 16, "chars": 67, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 16, "chars": 67, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 5, "chars": 20, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3, "chars": 15, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1, "chars": 1, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3, "chars": 15, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "openapi-spec": { "meta": { "id": "openapi-spec", "url": "https://swagger.io/specification/", "requested_url": "https://swagger.io/specification/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 509508 } }, "anchors": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 55782, "chars": 223128, "content_recall": 0.8853, "noise_retention": 0.0, "noise_keyword_total": 55, "noise_per_1k_tokens": 0.986, "f_precision": 0.9061, "f_coverage": 0.9061, "f_balanced": 0.9392, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 56392, "chars": 225570, "content_recall": 0.8981, "noise_retention": 0.0, "noise_keyword_total": 55, "noise_per_1k_tokens": 0.975, "f_precision": 0.9167, "f_coverage": 0.9167, "f_balanced": 0.9463, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 51533, "chars": 206133, "content_recall": 0.8113, "noise_retention": 0.0, "noise_keyword_total": 52, "noise_per_1k_tokens": 1.009, "f_precision": 0.8431, "f_coverage": 0.8431, "f_balanced": 0.8958, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 51280, "chars": 205123, "content_recall": 0.9369, "noise_retention": 0.0, "noise_keyword_total": 52, "noise_per_1k_tokens": 1.014, "f_precision": 0.9489, "f_coverage": 0.9489, "f_balanced": 0.9674, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" }, "readability": { "method": "readability", "tokens": 48760, "chars": 195043, "content_recall": 0.9366, "noise_retention": 0.0, "noise_keyword_total": 50, "noise_per_1k_tokens": 1.025, "f_precision": 0.9487, "f_coverage": 0.9487, "f_balanced": 0.9673, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 57895, "chars": 231580, "content_recall": 0.8853, "noise_retention": 0.3699, "noise_keyword_total": 63, "noise_per_1k_tokens": 1.088, "f_precision": 0.819, "f_coverage": 0.819, "f_balanced": 0.7362, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 54641, "chars": 218565, "content_recall": 0.9171, "noise_retention": 0.3699, "noise_keyword_total": 57, "noise_per_1k_tokens": 1.043, "f_precision": 0.8405, "f_coverage": 0.8405, "f_balanced": 0.7469, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 49574, "chars": 198299, "content_recall": 0.9398, "noise_retention": 0.8728, "noise_keyword_total": 53, "noise_per_1k_tokens": 1.069, "f_precision": 0.4126, "f_coverage": 0.4126, "f_balanced": 0.224, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 57874, "chars": 231499, "content_recall": 0.8853, "noise_retention": 0.3699, "noise_keyword_total": 63, "noise_per_1k_tokens": 1.089, "f_precision": 0.8189, "f_coverage": 0.8189, "f_balanced": 0.7362, "anchor_diag": { "content_chars": 186012, "noise_chars": 2249, "content_ngrams": 22394, "noise_ngrams": 173, "ambiguous_ngrams_removed": 2, "content_sentences": 1498 }, "notes": "" } }, "scoreable": true }, "opentelemetry": { "meta": { "id": "opentelemetry", "url": "https://opentelemetry.io/docs/", "requested_url": "https://opentelemetry.io/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 405788 } }, "anchors": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 600, "chars": 2402, "content_recall": 0.7458, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7857, "f_coverage": 0.7857, "f_balanced": 0.8544, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 608, "chars": 2433, "content_recall": 0.7458, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7857, "f_coverage": 0.7857, "f_balanced": 0.8544, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 503, "chars": 2012, "content_recall": 0.7034, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7477, "f_coverage": 0.7477, "f_balanced": 0.8259, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 279, "chars": 1119, "content_recall": 0.8136, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8451, "f_coverage": 0.8451, "f_balanced": 0.8972, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "readability": { "method": "readability", "tokens": 310, "chars": 1243, "content_recall": 0.8814, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9028, "f_coverage": 0.9028, "f_balanced": 0.9369, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 17944, "chars": 71778, "content_recall": 0.5763, "noise_retention": 0.0476, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6257, "f_coverage": 0.6257, "f_balanced": 0.7181, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 18594, "chars": 74377, "content_recall": 0.5763, "noise_retention": 0.0476, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6257, "f_coverage": 0.6257, "f_balanced": 0.7181, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3053, "chars": 12214, "content_recall": 0.7712, "noise_retention": 0.7143, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5756, "f_coverage": 0.5756, "f_balanced": 0.417, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 20642, "chars": 82570, "content_recall": 0.5763, "noise_retention": 0.0476, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6257, "f_coverage": 0.6257, "f_balanced": 0.7181, "anchor_diag": { "content_chars": 1072, "noise_chars": 518, "content_ngrams": 118, "noise_ngrams": 42, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" } }, "scoreable": true }, "oracle-cloud-docs": { "meta": { "id": "oracle-cloud-docs", "url": "https://docs.oracle.com/en/cloud/", "requested_url": "https://docs.oracle.com/en/cloud/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 30591 } }, "anchors": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 407, "chars": 1628, "content_recall": 0.7182, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7611, "f_coverage": 0.7611, "f_balanced": 0.836, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 407, "chars": 1628, "content_recall": 0.7182, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7611, "f_coverage": 0.7611, "f_balanced": 0.836, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 76, "chars": 305, "content_recall": 0.0455, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0562, "f_coverage": 0.0562, "f_balanced": 0.087, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 89, "chars": 356, "content_recall": 0.0818, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1002, "f_coverage": 0.1002, "f_balanced": 0.1513, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "readability": { "method": "readability", "tokens": 39, "chars": 159, "content_recall": 0.0818, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1002, "f_coverage": 0.1002, "f_balanced": 0.1513, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1255, "chars": 5021, "content_recall": 0.4727, "noise_retention": 0.56, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4658, "f_coverage": 0.4658, "f_balanced": 0.4558, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1285, "chars": 5143, "content_recall": 0.4727, "noise_retention": 0.56, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.778, "f_precision": 0.4658, "f_coverage": 0.4658, "f_balanced": 0.4558, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 627, "chars": 2508, "content_recall": 0.7636, "noise_retention": 0.8933, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3422, "f_coverage": 0.3422, "f_balanced": 0.1872, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1239, "chars": 4957, "content_recall": 0.4727, "noise_retention": 0.56, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4658, "f_coverage": 0.4658, "f_balanced": 0.4558, "anchor_diag": { "content_chars": 931, "noise_chars": 1043, "content_ngrams": 110, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" } }, "scoreable": true }, "owasp-top10": { "meta": { "id": "owasp-top10", "url": "https://owasp.org/projects/top-ten", "requested_url": "https://owasp.org/www-project-top-ten/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 88819 } }, "anchors": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 653, "chars": 2612, "content_recall": 0.7965, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8303, "f_coverage": 0.8303, "f_balanced": 0.8867, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 653, "chars": 2612, "content_recall": 0.7965, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8303, "f_coverage": 0.8303, "f_balanced": 0.8867, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 519, "chars": 2078, "content_recall": 0.658, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7063, "f_coverage": 0.7063, "f_balanced": 0.7937, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 190, "chars": 762, "content_recall": 0.4329, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4883, "f_coverage": 0.4883, "f_balanced": 0.6042, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" }, "readability": { "method": "readability", "tokens": 74, "chars": 299, "content_recall": 0.1472, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1775, "f_coverage": 0.1775, "f_balanced": 0.2566, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1145, "chars": 4582, "content_recall": 0.7056, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7498, "f_coverage": 0.7498, "f_balanced": 0.8274, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1149, "chars": 4597, "content_recall": 0.7056, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7498, "f_coverage": 0.7498, "f_balanced": 0.8274, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 623, "chars": 2495, "content_recall": 0.8788, "noise_retention": 0.3846, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8095, "f_coverage": 0.8095, "f_balanced": 0.7239, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1113, "chars": 4453, "content_recall": 0.7056, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7498, "f_coverage": 0.7498, "f_balanced": 0.8274, "anchor_diag": { "content_chars": 1840, "noise_chars": 176, "content_ngrams": 231, "noise_ngrams": 13, "ambiguous_ngrams_removed": 5, "content_sentences": 18 }, "notes": "" } }, "scoreable": true }, "pagerduty-docs": { "meta": { "id": "pagerduty-docs", "url": "https://developer.pagerduty.com/", "requested_url": "https://developer.pagerduty.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 539128 } }, "anchors": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 12, "chars": 48, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 12, "chars": 48, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 12, "chars": 48, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 3, "chars": 15, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1, "chars": 1, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "pandas-docs": { "meta": { "id": "pandas-docs", "url": "https://pandas.pydata.org/docs/", "requested_url": "https://pandas.pydata.org/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 22046 } }, "anchors": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 258, "chars": 1032, "content_recall": 0.5736, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6271, "f_coverage": 0.6271, "f_balanced": 0.7291, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 319, "chars": 1277, "content_recall": 0.7132, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7566, "f_coverage": 0.7566, "f_balanced": 0.8326, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 253, "chars": 1015, "content_recall": 0.5736, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6271, "f_coverage": 0.6271, "f_balanced": 0.7291, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 281, "chars": 1127, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "readability": { "method": "readability", "tokens": 292, "chars": 1170, "content_recall": 0.814, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8454, "f_coverage": 0.8454, "f_balanced": 0.8974, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 836, "chars": 3345, "content_recall": 0.7519, "noise_retention": 0.1, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7775, "f_coverage": 0.7775, "f_balanced": 0.8193, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 827, "chars": 3311, "content_recall": 0.7519, "noise_retention": 0.1, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7775, "f_coverage": 0.7775, "f_balanced": 0.8193, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 430, "chars": 1722, "content_recall": 0.8915, "noise_retention": 0.7, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6394, "f_coverage": 0.6394, "f_balanced": 0.4489, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 821, "chars": 3284, "content_recall": 0.7519, "noise_retention": 0.1, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7775, "f_coverage": 0.7775, "f_balanced": 0.8193, "anchor_diag": { "content_chars": 1075, "noise_chars": 412, "content_ngrams": 129, "noise_ngrams": 40, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" } }, "scoreable": true }, "pinecone-docs": { "meta": { "id": "pinecone-docs", "url": "https://docs.pinecone.io/guides/get-started/overview", "requested_url": "https://docs.pinecone.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 564255 } }, "anchors": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 90, "chars": 361, "content_recall": 0.0, "noise_retention": 0.0743, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 90, "chars": 361, "content_recall": 0.0, "noise_retention": 0.0743, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 90, "chars": 361, "content_recall": 0.0, "noise_retention": 0.0743, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 192, "chars": 769, "content_recall": 0.6164, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6677, "f_coverage": 0.6677, "f_balanced": 0.7627, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "readability": { "method": "readability", "tokens": 46, "chars": 187, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1335, "chars": 5340, "content_recall": 0.6164, "noise_retention": 0.4752, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.498, "f_precision": 0.5956, "f_coverage": 0.5956, "f_balanced": 0.5669, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1358, "chars": 5435, "content_recall": 0.6164, "noise_retention": 0.4752, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.473, "f_precision": 0.5956, "f_coverage": 0.5956, "f_balanced": 0.5669, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 619, "chars": 2476, "content_recall": 0.6164, "noise_retention": 0.9257, "noise_keyword_total": 2, "noise_per_1k_tokens": 3.231, "f_precision": 0.2506, "f_coverage": 0.2506, "f_balanced": 0.1325, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1325, "chars": 5303, "content_recall": 0.6164, "noise_retention": 0.4752, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.509, "f_precision": 0.5956, "f_coverage": 0.5956, "f_balanced": 0.5669, "anchor_diag": { "content_chars": 549, "noise_chars": 1563, "content_ngrams": 73, "noise_ngrams": 202, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" } }, "scoreable": true }, "pip-docs": { "meta": { "id": "pip-docs", "url": "https://pip.pypa.io/en/stable/", "requested_url": "https://pip.pypa.io/en/stable/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 26484 } }, "anchors": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 222, "chars": 888, "content_recall": 0.8667, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8904, "f_coverage": 0.8904, "f_balanced": 0.9286, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 222, "chars": 888, "content_recall": 0.8667, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8904, "f_coverage": 0.8904, "f_balanced": 0.9286, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 176, "chars": 707, "content_recall": 0.5333, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5882, "f_coverage": 0.5882, "f_balanced": 0.6957, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 172, "chars": 689, "content_recall": 0.9556, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 5.814, "f_precision": 0.9641, "f_coverage": 0.9641, "f_balanced": 0.9773, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "readability": { "method": "readability", "tokens": 177, "chars": 711, "content_recall": 0.9556, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9641, "f_coverage": 0.9641, "f_balanced": 0.9773, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1455, "chars": 5823, "content_recall": 0.7778, "noise_retention": 0.2268, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7769, "f_coverage": 0.7769, "f_balanced": 0.7755, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1459, "chars": 5836, "content_recall": 0.7778, "noise_retention": 0.2268, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.685, "f_precision": 0.7769, "f_coverage": 0.7769, "f_balanced": 0.7755, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 635, "chars": 2541, "content_recall": 0.8667, "noise_retention": 0.9794, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0941, "f_coverage": 0.0941, "f_balanced": 0.0403, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1439, "chars": 5759, "content_recall": 0.7778, "noise_retention": 0.2268, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7769, "f_coverage": 0.7769, "f_balanced": 0.7755, "anchor_diag": { "content_chars": 662, "noise_chars": 1582, "content_ngrams": 90, "noise_ngrams": 194, "ambiguous_ngrams_removed": 0, "content_sentences": 7 }, "notes": "" } }, "scoreable": true }, "planetscale-docs": { "meta": { "id": "planetscale-docs", "url": "https://planetscale.com/docs", "requested_url": "https://planetscale.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 300793 } }, "anchors": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 237, "chars": 948, "content_recall": 0.625, "noise_retention": 0.0917, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6666, "f_coverage": 0.6666, "f_balanced": 0.7405, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 237, "chars": 948, "content_recall": 0.625, "noise_retention": 0.0917, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6666, "f_coverage": 0.6666, "f_balanced": 0.7405, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 237, "chars": 948, "content_recall": 0.625, "noise_retention": 0.0917, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6666, "f_coverage": 0.6666, "f_balanced": 0.7405, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 157, "chars": 629, "content_recall": 0.625, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6757, "f_coverage": 0.6757, "f_balanced": 0.7692, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" }, "readability": { "method": "readability", "tokens": 366, "chars": 1467, "content_recall": 0.625, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6757, "f_coverage": 0.6757, "f_balanced": 0.7692, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1211, "chars": 4844, "content_recall": 0.625, "noise_retention": 0.25, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6466, "f_coverage": 0.6466, "f_balanced": 0.6818, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1209, "chars": 4837, "content_recall": 0.625, "noise_retention": 0.25, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6466, "f_coverage": 0.6466, "f_balanced": 0.6818, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 680, "chars": 2723, "content_recall": 0.625, "noise_retention": 0.8667, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3597, "f_coverage": 0.3597, "f_balanced": 0.2198, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1204, "chars": 4818, "content_recall": 0.625, "noise_retention": 0.25, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6466, "f_coverage": 0.6466, "f_balanced": 0.6818, "anchor_diag": { "content_chars": 541, "noise_chars": 1060, "content_ngrams": 64, "noise_ngrams": 120, "ambiguous_ngrams_removed": 2, "content_sentences": 7 }, "notes": "" } }, "scoreable": true }, "plausible-docs": { "meta": { "id": "plausible-docs", "url": "https://plausible.io/docs", "requested_url": "https://plausible.io/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 32787 } }, "anchors": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1233, "chars": 4934, "content_recall": 0.8154, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.622, "f_precision": 0.8467, "f_coverage": 0.8467, "f_balanced": 0.8983, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1284, "chars": 5139, "content_recall": 0.8775, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.558, "f_precision": 0.8996, "f_coverage": 0.8996, "f_balanced": 0.9348, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 927, "chars": 3711, "content_recall": 0.5537, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.157, "f_precision": 0.608, "f_coverage": 0.608, "f_balanced": 0.7127, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1198, "chars": 4794, "content_recall": 0.9396, "noise_retention": 0.0142, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.835, "f_precision": 0.9485, "f_coverage": 0.9485, "f_balanced": 0.9622, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "readability": { "method": "readability", "tokens": 349, "chars": 1398, "content_recall": 0.1997, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.865, "f_precision": 0.2377, "f_coverage": 0.2377, "f_balanced": 0.3329, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2703, "chars": 10814, "content_recall": 0.6544, "noise_retention": 0.0496, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.85, "f_precision": 0.6978, "f_coverage": 0.6978, "f_balanced": 0.7751, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2753, "chars": 11013, "content_recall": 0.6544, "noise_retention": 0.0496, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.816, "f_precision": 0.6978, "f_coverage": 0.6978, "f_balanced": 0.7751, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1481, "chars": 5924, "content_recall": 0.9396, "noise_retention": 0.8652, "noise_keyword_total": 4, "noise_per_1k_tokens": 2.701, "f_precision": 0.4281, "f_coverage": 0.4281, "f_balanced": 0.2357, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2689, "chars": 10758, "content_recall": 0.6544, "noise_retention": 0.0496, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.859, "f_precision": 0.6978, "f_coverage": 0.6978, "f_balanced": 0.7751, "anchor_diag": { "content_chars": 4399, "noise_chars": 1393, "content_ngrams": 596, "noise_ngrams": 141, "ambiguous_ngrams_removed": 0, "content_sentences": 71 }, "notes": "" } }, "scoreable": true }, "playwright-docs": { "meta": { "id": "playwright-docs", "url": "https://playwright.dev/docs/intro", "requested_url": "https://playwright.dev/docs/intro", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 55934 } }, "anchors": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 959, "chars": 3839, "content_recall": 0.6216, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6725, "f_coverage": 0.6725, "f_balanced": 0.7667, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1014, "chars": 4056, "content_recall": 0.6732, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7203, "f_coverage": 0.7203, "f_balanced": 0.8047, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 675, "chars": 2701, "content_recall": 0.4742, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5299, "f_coverage": 0.5299, "f_balanced": 0.6433, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 978, "chars": 3912, "content_recall": 0.7322, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7736, "f_coverage": 0.7736, "f_balanced": 0.8454, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "readability": { "method": "readability", "tokens": 733, "chars": 2932, "content_recall": 0.6609, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.709, "f_coverage": 0.709, "f_balanced": 0.7959, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2476, "chars": 9905, "content_recall": 0.7027, "noise_retention": 0.0201, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7448, "f_coverage": 0.7448, "f_balanced": 0.8185, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2436, "chars": 9745, "content_recall": 0.7027, "noise_retention": 0.0201, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7448, "f_coverage": 0.7448, "f_balanced": 0.8185, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1325, "chars": 5301, "content_recall": 0.774, "noise_retention": 0.9463, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2101, "f_coverage": 0.2101, "f_balanced": 0.1004, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2464, "chars": 9856, "content_recall": 0.7027, "noise_retention": 0.0201, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7448, "f_coverage": 0.7448, "f_balanced": 0.8185, "anchor_diag": { "content_chars": 3602, "noise_chars": 2142, "content_ngrams": 407, "noise_ngrams": 149, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" } }, "scoreable": true }, "pnpm-docs": { "meta": { "id": "pnpm-docs", "url": "https://pnpm.io/", "requested_url": "https://pnpm.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 85950 } }, "anchors": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1461, "chars": 5847, "content_recall": 0.7112, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7548, "f_coverage": 0.7548, "f_balanced": 0.8313, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1494, "chars": 5979, "content_recall": 0.7653, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.803, "f_coverage": 0.803, "f_balanced": 0.867, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1069, "chars": 4276, "content_recall": 0.606, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6578, "f_coverage": 0.6578, "f_balanced": 0.7547, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1345, "chars": 5383, "content_recall": 0.7511, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7904, "f_coverage": 0.7904, "f_balanced": 0.8578, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1309, "chars": 5239, "content_recall": 0.7354, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7765, "f_coverage": 0.7765, "f_balanced": 0.8475, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3144, "chars": 12577, "content_recall": 0.7226, "noise_retention": 0.2031, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7363, "f_coverage": 0.7363, "f_balanced": 0.7579, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2937, "chars": 11751, "content_recall": 0.7183, "noise_retention": 0.2031, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7328, "f_coverage": 0.7328, "f_balanced": 0.7556, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1712, "chars": 6848, "content_recall": 0.7895, "noise_retention": 0.875, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3827, "f_coverage": 0.3827, "f_balanced": 0.2158, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3127, "chars": 12510, "content_recall": 0.7226, "noise_retention": 0.2031, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7363, "f_coverage": 0.7363, "f_balanced": 0.7579, "anchor_diag": { "content_chars": 6189, "noise_chars": 663, "content_ngrams": 703, "noise_ngrams": 64, "ambiguous_ngrams_removed": 0, "content_sentences": 60 }, "notes": "" } }, "scoreable": true }, "poetry-docs": { "meta": { "id": "poetry-docs", "url": "https://python-poetry.org/docs/", "requested_url": "https://python-poetry.org/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 83571 } }, "anchors": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2985, "chars": 11940, "content_recall": 0.7808, "noise_retention": 0.0118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.815, "f_coverage": 0.815, "f_balanced": 0.8723, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 3064, "chars": 12258, "content_recall": 0.8139, "noise_retention": 0.0118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8437, "f_coverage": 0.8437, "f_balanced": 0.8927, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2712, "chars": 10851, "content_recall": 0.707, "noise_retention": 0.0118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7497, "f_coverage": 0.7497, "f_balanced": 0.8243, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2355, "chars": 9422, "content_recall": 0.6773, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.724, "f_coverage": 0.724, "f_balanced": 0.8076, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2277, "chars": 9111, "content_recall": 0.6773, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.724, "f_coverage": 0.724, "f_balanced": 0.8076, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5420, "chars": 21683, "content_recall": 0.8275, "noise_retention": 0.2118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8193, "f_coverage": 0.8193, "f_balanced": 0.8074, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5399, "chars": 21596, "content_recall": 0.8281, "noise_retention": 0.2941, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8004, "f_coverage": 0.8004, "f_balanced": 0.7621, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4290, "chars": 17161, "content_recall": 0.839, "noise_retention": 0.8118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.496, "f_coverage": 0.496, "f_balanced": 0.3075, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5396, "chars": 21586, "content_recall": 0.8275, "noise_retention": 0.2118, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8193, "f_coverage": 0.8193, "f_balanced": 0.8074, "anchor_diag": { "content_chars": 18291, "noise_chars": 1118, "content_ngrams": 1478, "noise_ngrams": 85, "ambiguous_ngrams_removed": 8, "content_sentences": 159 }, "notes": "" } }, "scoreable": true }, "postgres-docs": { "meta": { "id": "postgres-docs", "url": "https://www.postgresql.org/docs/current/", "requested_url": "https://www.postgresql.org/docs/current/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 25445 } }, "anchors": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 947, "chars": 3790, "content_recall": 0.6857, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7317, "f_coverage": 0.7317, "f_balanced": 0.8136, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 947, "chars": 3790, "content_recall": 0.6857, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7317, "f_coverage": 0.7317, "f_balanced": 0.8136, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 879, "chars": 3517, "content_recall": 0.6857, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7317, "f_coverage": 0.7317, "f_balanced": 0.8136, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 72, "chars": 291, "content_recall": 0.6571, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7055, "f_coverage": 0.7055, "f_balanced": 0.7931, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" }, "readability": { "method": "readability", "tokens": 52, "chars": 209, "content_recall": 0.1143, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1389, "f_coverage": 0.1389, "f_balanced": 0.2051, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2229, "chars": 8917, "content_recall": 0.6857, "noise_retention": 0.0625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7246, "f_coverage": 0.7246, "f_balanced": 0.7921, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2127, "chars": 8509, "content_recall": 0.6857, "noise_retention": 0.0625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7246, "f_coverage": 0.7246, "f_balanced": 0.7921, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 954, "chars": 3817, "content_recall": 0.7714, "noise_retention": 0.75, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5444, "f_coverage": 0.5444, "f_balanced": 0.3776, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2212, "chars": 8850, "content_recall": 0.6857, "noise_retention": 0.0625, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7246, "f_coverage": 0.7246, "f_balanced": 0.7921, "anchor_diag": { "content_chars": 474, "noise_chars": 200, "content_ngrams": 35, "noise_ngrams": 16, "ambiguous_ngrams_removed": 4, "content_sentences": 3 }, "notes": "" } }, "scoreable": false }, "postgres-sql": { "meta": { "id": "postgres-sql", "url": "https://www.postgresql.org/docs/current/sql.html", "requested_url": "https://www.postgresql.org/docs/current/sql.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 31936 } }, "anchors": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1472, "chars": 5890, "content_recall": 0.8944, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9137, "f_coverage": 0.9137, "f_balanced": 0.9443, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1472, "chars": 5890, "content_recall": 0.8944, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9137, "f_coverage": 0.9137, "f_balanced": 0.9443, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1137, "chars": 4550, "content_recall": 0.3111, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3608, "f_coverage": 0.3608, "f_balanced": 0.4746, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 338, "chars": 1353, "content_recall": 0.9778, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9821, "f_coverage": 0.9821, "f_balanced": 0.9888, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "readability": { "method": "readability", "tokens": 21, "chars": 86, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3169, "chars": 12676, "content_recall": 0.8944, "noise_retention": 0.25, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8613, "f_coverage": 0.8613, "f_balanced": 0.8159, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3013, "chars": 12052, "content_recall": 0.8944, "noise_retention": 0.25, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8613, "f_coverage": 0.8613, "f_balanced": 0.8159, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1473, "chars": 5892, "content_recall": 0.9556, "noise_retention": 0.8, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5443, "f_coverage": 0.5443, "f_balanced": 0.3308, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3153, "chars": 12613, "content_recall": 0.8944, "noise_retention": 0.25, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8613, "f_coverage": 0.8613, "f_balanced": 0.8159, "anchor_diag": { "content_chars": 1515, "noise_chars": 200, "content_ngrams": 180, "noise_ngrams": 20, "ambiguous_ngrams_removed": 0, "content_sentences": 13 }, "notes": "" } }, "scoreable": true }, "posthog-docs": { "meta": { "id": "posthog-docs", "url": "https://posthog.com/docs", "requested_url": "https://posthog.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 1061802 } }, "anchors": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 201, "chars": 805, "content_recall": 0.7778, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.814, "f_coverage": 0.814, "f_balanced": 0.875, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 208, "chars": 834, "content_recall": 0.7778, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.814, "f_coverage": 0.814, "f_balanced": 0.875, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 103, "chars": 415, "content_recall": 0.1111, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1351, "f_coverage": 0.1351, "f_balanced": 0.2, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 159, "chars": 639, "content_recall": 0.1481, "noise_retention": 0.1667, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1773, "f_coverage": 0.1773, "f_balanced": 0.2516, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "readability": { "method": "readability", "tokens": 23, "chars": 95, "content_recall": 0.0, "noise_retention": 0.1833, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 707, "chars": 2829, "content_recall": 0.1481, "noise_retention": 0.3833, "noise_keyword_total": 4, "noise_per_1k_tokens": 5.658, "f_precision": 0.1747, "f_coverage": 0.1747, "f_balanced": 0.2389, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 712, "chars": 2849, "content_recall": 0.1481, "noise_retention": 0.3333, "noise_keyword_total": 4, "noise_per_1k_tokens": 5.618, "f_precision": 0.1754, "f_coverage": 0.1754, "f_balanced": 0.2424, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 304, "chars": 1218, "content_recall": 0.7778, "noise_retention": 0.9333, "noise_keyword_total": 2, "noise_per_1k_tokens": 6.579, "f_precision": 0.2482, "f_coverage": 0.2482, "f_balanced": 0.1228, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 839, "chars": 3357, "content_recall": 0.1481, "noise_retention": 0.3833, "noise_keyword_total": 4, "noise_per_1k_tokens": 4.768, "f_precision": 0.1747, "f_coverage": 0.1747, "f_balanced": 0.2389, "anchor_diag": { "content_chars": 440, "noise_chars": 570, "content_ngrams": 54, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 5 }, "notes": "" } }, "scoreable": true }, "prometheus-docs": { "meta": { "id": "prometheus-docs", "url": "https://prometheus.io/docs/introduction/overview/", "requested_url": "https://prometheus.io/docs/introduction/overview/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 176527 } }, "anchors": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1153, "chars": 4612, "content_recall": 0.8847, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9056, "f_coverage": 0.9056, "f_balanced": 0.9388, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1170, "chars": 4680, "content_recall": 0.9055, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9229, "f_coverage": 0.9229, "f_balanced": 0.9504, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1050, "chars": 4201, "content_recall": 0.7826, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8182, "f_coverage": 0.8182, "f_balanced": 0.878, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1086, "chars": 4347, "content_recall": 0.9471, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9572, "f_coverage": 0.9572, "f_balanced": 0.9728, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "readability": { "method": "readability", "tokens": 997, "chars": 3991, "content_recall": 0.8771, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8992, "f_coverage": 0.8992, "f_balanced": 0.9345, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3047, "chars": 12191, "content_recall": 0.8412, "noise_retention": 0.245, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8224, "f_coverage": 0.8224, "f_balanced": 0.7958, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2958, "chars": 11832, "content_recall": 0.8412, "noise_retention": 0.2785, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8142, "f_coverage": 0.8142, "f_balanced": 0.7768, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1702, "chars": 6810, "content_recall": 0.9471, "noise_retention": 0.9597, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1721, "f_coverage": 0.1721, "f_balanced": 0.0773, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3042, "chars": 12168, "content_recall": 0.8412, "noise_retention": 0.245, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8224, "f_coverage": 0.8224, "f_balanced": 0.7958, "anchor_diag": { "content_chars": 4131, "noise_chars": 2492, "content_ngrams": 529, "noise_ngrams": 298, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" } }, "scoreable": true }, "protobuf-docs": { "meta": { "id": "protobuf-docs", "url": "https://protobuf.dev/", "requested_url": "https://protobuf.dev/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 50855 } }, "anchors": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 457, "chars": 1830, "content_recall": 0.8107, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8426, "f_coverage": 0.8426, "f_balanced": 0.8954, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 466, "chars": 1865, "content_recall": 0.8107, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8426, "f_coverage": 0.8426, "f_balanced": 0.8954, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 289, "chars": 1159, "content_recall": 0.4911, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5468, "f_coverage": 0.5468, "f_balanced": 0.6587, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 385, "chars": 1542, "content_recall": 0.8107, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8426, "f_coverage": 0.8426, "f_balanced": 0.8954, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "readability": { "method": "readability", "tokens": 385, "chars": 1540, "content_recall": 0.8107, "noise_retention": 0.0039, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.842, "f_coverage": 0.842, "f_balanced": 0.8939, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2595, "chars": 10380, "content_recall": 0.7751, "noise_retention": 0.2664, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.385, "f_precision": 0.7665, "f_coverage": 0.7665, "f_balanced": 0.7538, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2696, "chars": 10786, "content_recall": 0.7751, "noise_retention": 0.2741, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.371, "f_precision": 0.7648, "f_coverage": 0.7648, "f_balanced": 0.7497, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 879, "chars": 3518, "content_recall": 0.8107, "noise_retention": 0.9537, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.138, "f_precision": 0.1886, "f_coverage": 0.1886, "f_balanced": 0.0877, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2587, "chars": 10348, "content_recall": 0.7751, "noise_retention": 0.2664, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.387, "f_precision": 0.7665, "f_coverage": 0.7665, "f_balanced": 0.7538, "anchor_diag": { "content_chars": 1832, "noise_chars": 3729, "content_ngrams": 169, "noise_ngrams": 259, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" } }, "scoreable": true }, "pulumi-docs": { "meta": { "id": "pulumi-docs", "url": "https://www.pulumi.com/docs/", "requested_url": "https://www.pulumi.com/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 415002 } }, "anchors": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 484, "chars": 1936, "content_recall": 0.4863, "noise_retention": 0.006, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5416, "f_coverage": 0.5416, "f_balanced": 0.6531, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 540, "chars": 2163, "content_recall": 0.4863, "noise_retention": 0.006, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5416, "f_coverage": 0.5416, "f_balanced": 0.6531, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 455, "chars": 1823, "content_recall": 0.4726, "noise_retention": 0.006, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.528, "f_coverage": 0.528, "f_balanced": 0.6406, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 61, "chars": 246, "content_recall": 0.1575, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1895, "f_coverage": 0.1895, "f_balanced": 0.2722, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" }, "readability": { "method": "readability", "tokens": 8, "chars": 32, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 16281, "chars": 65127, "content_recall": 0.5959, "noise_retention": 0.3776, "noise_keyword_total": 8, "noise_per_1k_tokens": 0.491, "f_precision": 0.601, "f_coverage": 0.601, "f_balanced": 0.6088, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 17084, "chars": 68338, "content_recall": 0.5205, "noise_retention": 0.3716, "noise_keyword_total": 8, "noise_per_1k_tokens": 0.468, "f_precision": 0.5391, "f_coverage": 0.5391, "f_balanced": 0.5694, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4442, "chars": 17769, "content_recall": 0.6438, "noise_retention": 0.9517, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.126, "f_precision": 0.1859, "f_coverage": 0.1859, "f_balanced": 0.0899, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 15581, "chars": 62327, "content_recall": 0.5959, "noise_retention": 0.3776, "noise_keyword_total": 8, "noise_per_1k_tokens": 0.513, "f_precision": 0.601, "f_coverage": 0.601, "f_balanced": 0.6088, "anchor_diag": { "content_chars": 1217, "noise_chars": 7383, "content_ngrams": 146, "noise_ngrams": 331, "ambiguous_ngrams_removed": 2, "content_sentences": 15 }, "notes": "" } }, "scoreable": true }, "puppet-docs": { "meta": { "id": "puppet-docs", "url": "https://help.puppet.com", "requested_url": "https://www.puppet.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 17423 } }, "anchors": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 191, "chars": 765, "content_recall": 0.9467, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9569, "f_coverage": 0.9569, "f_balanced": 0.9726, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 191, "chars": 765, "content_recall": 0.9467, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9569, "f_coverage": 0.9569, "f_balanced": 0.9726, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 114, "chars": 458, "content_recall": 0.48, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5357, "f_coverage": 0.5357, "f_balanced": 0.6486, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 208, "chars": 835, "content_recall": 0.76, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7983, "f_coverage": 0.7983, "f_balanced": 0.8636, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" }, "readability": { "method": "readability", "tokens": 41, "chars": 166, "content_recall": 0.12, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1456, "f_coverage": 0.1456, "f_balanced": 0.2143, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 777, "chars": 3110, "content_recall": 0.8, "noise_retention": 0.7564, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.287, "f_precision": 0.5491, "f_coverage": 0.5491, "f_balanced": 0.3735, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 799, "chars": 3199, "content_recall": 0.8, "noise_retention": 0.7308, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.252, "f_precision": 0.5738, "f_coverage": 0.5738, "f_balanced": 0.4029, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 482, "chars": 1931, "content_recall": 0.8, "noise_retention": 0.9615, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.075, "f_precision": 0.1613, "f_coverage": 0.1613, "f_balanced": 0.0734, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 761, "chars": 3044, "content_recall": 0.8, "noise_retention": 0.7564, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.314, "f_precision": 0.5491, "f_coverage": 0.5491, "f_balanced": 0.3735, "anchor_diag": { "content_chars": 649, "noise_chars": 669, "content_ngrams": 75, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 6 }, "notes": "" } }, "scoreable": true }, "puppeteer-docs": { "meta": { "id": "puppeteer-docs", "url": "https://pptr.dev/", "requested_url": "https://pptr.dev/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 36523 } }, "anchors": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 794, "chars": 3179, "content_recall": 0.7989, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8323, "f_coverage": 0.8323, "f_balanced": 0.8882, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 794, "chars": 3179, "content_recall": 0.7989, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8323, "f_coverage": 0.8323, "f_balanced": 0.8882, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 335, "chars": 1343, "content_recall": 0.2443, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2877, "f_coverage": 0.2877, "f_balanced": 0.3926, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 715, "chars": 2863, "content_recall": 0.8276, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8571, "f_coverage": 0.8571, "f_balanced": 0.9057, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "readability": { "method": "readability", "tokens": 137, "chars": 549, "content_recall": 0.1839, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2198, "f_coverage": 0.2198, "f_balanced": 0.3107, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1207, "chars": 4829, "content_recall": 0.7816, "noise_retention": 0.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 3.314, "f_precision": 0.8173, "f_coverage": 0.8173, "f_balanced": 0.8774, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1305, "chars": 5222, "content_recall": 0.7759, "noise_retention": 0.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 3.065, "f_precision": 0.8123, "f_coverage": 0.8123, "f_balanced": 0.8738, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 772, "chars": 3090, "content_recall": 0.8161, "noise_retention": 0.8095, "noise_keyword_total": 2, "noise_per_1k_tokens": 2.591, "f_precision": 0.4925, "f_coverage": 0.4925, "f_balanced": 0.3089, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1190, "chars": 4763, "content_recall": 0.7816, "noise_retention": 0.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 3.361, "f_precision": 0.8173, "f_coverage": 0.8173, "f_balanced": 0.8774, "anchor_diag": { "content_chars": 5897, "noise_chars": 204, "content_ngrams": 348, "noise_ngrams": 21, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" } }, "scoreable": true }, "pydantic-docs": { "meta": { "id": "pydantic-docs", "url": "https://pydantic.dev/docs/", "requested_url": "https://docs.pydantic.dev/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 51232 } }, "anchors": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 421, "chars": 1684, "content_recall": 0.6555, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.704, "f_coverage": 0.704, "f_balanced": 0.7919, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 421, "chars": 1684, "content_recall": 0.6555, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.704, "f_coverage": 0.704, "f_balanced": 0.7919, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 409, "chars": 1636, "content_recall": 0.6459, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6952, "f_coverage": 0.6952, "f_balanced": 0.7849, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 234, "chars": 937, "content_recall": 0.4163, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4713, "f_coverage": 0.4713, "f_balanced": 0.5878, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "readability": { "method": "readability", "tokens": 242, "chars": 969, "content_recall": 0.4593, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.515, "f_coverage": 0.515, "f_balanced": 0.6295, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 629, "chars": 2516, "content_recall": 0.7321, "noise_retention": 0.1935, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7458, "f_coverage": 0.7458, "f_balanced": 0.7675, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 678, "chars": 2713, "content_recall": 0.6699, "noise_retention": 0.1935, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6933, "f_coverage": 0.6933, "f_balanced": 0.7318, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 466, "chars": 1867, "content_recall": 0.8086, "noise_retention": 0.7097, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5959, "f_coverage": 0.5959, "f_balanced": 0.4272, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 610, "chars": 2440, "content_recall": 0.7321, "noise_retention": 0.1935, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7458, "f_coverage": 0.7458, "f_balanced": 0.7675, "anchor_diag": { "content_chars": 2280, "noise_chars": 474, "content_ngrams": 209, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" } }, "scoreable": true }, "pytest-docs": { "meta": { "id": "pytest-docs", "url": "https://docs.pytest.org/en/stable/", "requested_url": "https://docs.pytest.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 31975 } }, "anchors": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 835, "chars": 3340, "content_recall": 0.7616, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7998, "f_coverage": 0.7998, "f_balanced": 0.8647, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 851, "chars": 3406, "content_recall": 0.7616, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7998, "f_coverage": 0.7998, "f_balanced": 0.8647, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 638, "chars": 2552, "content_recall": 0.532, "noise_retention": 0.0102, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5862, "f_coverage": 0.5862, "f_balanced": 0.692, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 765, "chars": 3063, "content_recall": 0.7791, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8151, "f_coverage": 0.8151, "f_balanced": 0.8758, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" }, "readability": { "method": "readability", "tokens": 737, "chars": 2950, "content_recall": 0.7791, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8151, "f_coverage": 0.8151, "f_balanced": 0.8758, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2239, "chars": 8956, "content_recall": 0.657, "noise_retention": 0.3163, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6621, "f_coverage": 0.6621, "f_balanced": 0.6701, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2178, "chars": 8715, "content_recall": 0.6686, "noise_retention": 0.3469, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6654, "f_coverage": 0.6654, "f_balanced": 0.6607, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1325, "chars": 5300, "content_recall": 0.7791, "noise_retention": 0.9592, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1687, "f_coverage": 0.1687, "f_balanced": 0.0776, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2228, "chars": 8914, "content_recall": 0.657, "noise_retention": 0.3163, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6621, "f_coverage": 0.6621, "f_balanced": 0.6701, "anchor_diag": { "content_chars": 4195, "noise_chars": 2206, "content_ngrams": 344, "noise_ngrams": 294, "ambiguous_ngrams_removed": 2, "content_sentences": 35 }, "notes": "" } }, "scoreable": true }, "python-asyncio": { "meta": { "id": "python-asyncio", "url": "https://docs.python.org/3/library/asyncio.html", "requested_url": "https://docs.python.org/3/library/asyncio.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 25411 } }, "anchors": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 666, "chars": 2665, "content_recall": 0.7336, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7749, "f_coverage": 0.7749, "f_balanced": 0.8463, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 689, "chars": 2759, "content_recall": 0.719, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7618, "f_coverage": 0.7618, "f_balanced": 0.8365, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 629, "chars": 2519, "content_recall": 0.6642, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7121, "f_coverage": 0.7121, "f_balanced": 0.7982, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 560, "chars": 2242, "content_recall": 0.7956, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8295, "f_coverage": 0.8295, "f_balanced": 0.8862, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "readability": { "method": "readability", "tokens": 361, "chars": 1444, "content_recall": 0.5109, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5663, "f_coverage": 0.5663, "f_balanced": 0.6763, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1685, "chars": 6740, "content_recall": 0.6533, "noise_retention": 0.35, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6526, "f_coverage": 0.6526, "f_balanced": 0.6516, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1716, "chars": 6866, "content_recall": 0.6533, "noise_retention": 0.35, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6526, "f_coverage": 0.6526, "f_balanced": 0.6516, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 977, "chars": 3911, "content_recall": 0.7993, "noise_retention": 0.8667, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3999, "f_coverage": 0.3999, "f_balanced": 0.2285, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1666, "chars": 6666, "content_recall": 0.6533, "noise_retention": 0.35, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6526, "f_coverage": 0.6526, "f_balanced": 0.6516, "anchor_diag": { "content_chars": 2696, "noise_chars": 834, "content_ngrams": 274, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 32 }, "notes": "" } }, "scoreable": true }, "python-docs": { "meta": { "id": "python-docs", "url": "https://docs.python.org/3/", "requested_url": "https://docs.python.org/3/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 19641 } }, "anchors": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 268, "chars": 1073, "content_recall": 0.5882, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.641, "f_coverage": 0.641, "f_balanced": 0.7407, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 340, "chars": 1360, "content_recall": 0.8627, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8871, "f_coverage": 0.8871, "f_balanced": 0.9263, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 154, "chars": 618, "content_recall": 0.2484, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2923, "f_coverage": 0.2923, "f_balanced": 0.3979, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 355, "chars": 1422, "content_recall": 0.9216, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9363, "f_coverage": 0.9363, "f_balanced": 0.9592, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "readability": { "method": "readability", "tokens": 52, "chars": 208, "content_recall": 0.0196, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0244, "f_coverage": 0.0244, "f_balanced": 0.0385, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1618, "chars": 6475, "content_recall": 0.4183, "noise_retention": 0.1154, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4676, "f_coverage": 0.4676, "f_balanced": 0.568, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1657, "chars": 6630, "content_recall": 0.4183, "noise_retention": 0.1154, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4676, "f_coverage": 0.4676, "f_balanced": 0.568, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 808, "chars": 3233, "content_recall": 0.9216, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1596, "chars": 6385, "content_recall": 0.4183, "noise_retention": 0.1154, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4676, "f_coverage": 0.4676, "f_balanced": 0.568, "anchor_diag": { "content_chars": 1234, "noise_chars": 1289, "content_ngrams": 153, "noise_ngrams": 52, "ambiguous_ngrams_removed": 0, "content_sentences": 18 }, "notes": "" } }, "scoreable": true }, "python-library": { "meta": { "id": "python-library", "url": "https://docs.python.org/3/library/", "requested_url": "https://docs.python.org/3/library/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 73289 } }, "anchors": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 580, "chars": 2321, "content_recall": 0.1026, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.125, "f_coverage": 0.125, "f_balanced": 0.1861, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 654, "chars": 2619, "content_recall": 0.1026, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.125, "f_coverage": 0.125, "f_balanced": 0.1861, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 444, "chars": 1776, "content_recall": 0.0732, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0899, "f_coverage": 0.0899, "f_balanced": 0.1364, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 403, "chars": 1612, "content_recall": 0.1072, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1305, "f_coverage": 0.1305, "f_balanced": 0.1936, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" }, "readability": { "method": "readability", "tokens": 416, "chars": 1667, "content_recall": 0.1072, "noise_retention": 0.0588, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1303, "f_coverage": 0.1303, "f_balanced": 0.1925, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5383, "chars": 21533, "content_recall": 0.3245, "noise_retention": 0.3235, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.929, "f_precision": 0.3622, "f_coverage": 0.3622, "f_balanced": 0.4386, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5511, "chars": 22044, "content_recall": 0.3245, "noise_retention": 0.3235, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.907, "f_precision": 0.3622, "f_coverage": 0.3622, "f_balanced": 0.4386, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3387, "chars": 13550, "content_recall": 0.8824, "noise_retention": 1.0, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.886, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5365, "chars": 21460, "content_recall": 0.3245, "noise_retention": 0.3235, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.932, "f_precision": 0.3622, "f_coverage": 0.3622, "f_balanced": 0.4386, "anchor_diag": { "content_chars": 21517, "noise_chars": 565, "content_ngrams": 1735, "noise_ngrams": 34, "ambiguous_ngrams_removed": 0, "content_sentences": 163 }, "notes": "" } }, "scoreable": true }, "python-tutorial": { "meta": { "id": "python-tutorial", "url": "https://docs.python.org/3/tutorial/", "requested_url": "https://docs.python.org/3/tutorial/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 37133 } }, "anchors": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 753, "chars": 3013, "content_recall": 0.3359, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3873, "f_coverage": 0.3873, "f_balanced": 0.5028, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 797, "chars": 3188, "content_recall": 0.3384, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.39, "f_coverage": 0.39, "f_balanced": 0.5057, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 548, "chars": 2194, "content_recall": 0.2765, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3233, "f_coverage": 0.3233, "f_balanced": 0.4332, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 579, "chars": 2318, "content_recall": 0.3699, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4233, "f_coverage": 0.4233, "f_balanced": 0.5401, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "readability": { "method": "readability", "tokens": 589, "chars": 2357, "content_recall": 0.3699, "noise_retention": 0.0323, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4221, "f_coverage": 0.4221, "f_balanced": 0.5353, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3591, "chars": 14365, "content_recall": 0.5593, "noise_retention": 0.2258, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5922, "f_coverage": 0.5922, "f_balanced": 0.6495, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3658, "chars": 14633, "content_recall": 0.5593, "noise_retention": 0.2258, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5922, "f_coverage": 0.5922, "f_balanced": 0.6495, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1779, "chars": 7116, "content_recall": 0.8144, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3575, "chars": 14300, "content_recall": 0.5593, "noise_retention": 0.2258, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5922, "f_coverage": 0.5922, "f_balanced": 0.6495, "anchor_diag": { "content_chars": 9379, "noise_chars": 499, "content_ngrams": 792, "noise_ngrams": 31, "ambiguous_ngrams_removed": 0, "content_sentences": 36 }, "notes": "" } }, "scoreable": true }, "pytorch-docs": { "meta": { "id": "pytorch-docs", "url": "https://docs.pytorch.org/docs/stable/", "requested_url": "https://pytorch.org/docs/stable/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 1641 } }, "anchors": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 18, "chars": 73, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 18, "chars": 73, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 18, "chars": 73, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 7, "chars": 30, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 11, "chars": 47, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 17, "chars": 68, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 16, "chars": 66, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 10, "chars": 43, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 16, "chars": 66, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "qdrant-docs": { "meta": { "id": "qdrant-docs", "url": "https://qdrant.tech/documentation/", "requested_url": "https://qdrant.tech/documentation/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 59172 } }, "anchors": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 457, "chars": 1828, "content_recall": 0.7462, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7861, "f_coverage": 0.7861, "f_balanced": 0.8547, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 457, "chars": 1828, "content_recall": 0.7462, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7861, "f_coverage": 0.7861, "f_balanced": 0.8547, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 426, "chars": 1707, "content_recall": 0.6497, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6987, "f_coverage": 0.6987, "f_balanced": 0.7877, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 196, "chars": 786, "content_recall": 0.3655, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4186, "f_coverage": 0.4186, "f_balanced": 0.5353, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "readability": { "method": "readability", "tokens": 56, "chars": 227, "content_recall": 0.0812, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0995, "f_coverage": 0.0995, "f_balanced": 0.1502, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5179, "chars": 20717, "content_recall": 0.7005, "noise_retention": 0.1827, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.579, "f_precision": 0.7211, "f_coverage": 0.7211, "f_balanced": 0.7544, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5254, "chars": 21018, "content_recall": 0.6294, "noise_retention": 0.1827, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.571, "f_precision": 0.6598, "f_coverage": 0.6598, "f_balanced": 0.7112, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1359, "chars": 5436, "content_recall": 0.7817, "noise_retention": 0.8339, "noise_keyword_total": 3, "noise_per_1k_tokens": 2.208, "f_precision": 0.449, "f_coverage": 0.449, "f_balanced": 0.274, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5172, "chars": 20688, "content_recall": 0.7005, "noise_retention": 0.1827, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.58, "f_precision": 0.7211, "f_coverage": 0.7211, "f_balanced": 0.7544, "anchor_diag": { "content_chars": 1913, "noise_chars": 8572, "content_ngrams": 197, "noise_ngrams": 301, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" } }, "scoreable": true }, "rabbitmq-docs": { "meta": { "id": "rabbitmq-docs", "url": "https://www.rabbitmq.com/docs", "requested_url": "https://www.rabbitmq.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 22226 } }, "anchors": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 218, "chars": 874, "content_recall": 0.4214, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4765, "f_coverage": 0.4765, "f_balanced": 0.5929, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 227, "chars": 910, "content_recall": 0.4277, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.483, "f_coverage": 0.483, "f_balanced": 0.5991, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 126, "chars": 507, "content_recall": 0.1698, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2036, "f_coverage": 0.2036, "f_balanced": 0.2903, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 195, "chars": 780, "content_recall": 0.4465, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5021, "f_coverage": 0.5021, "f_balanced": 0.6174, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "readability": { "method": "readability", "tokens": 25, "chars": 102, "content_recall": 0.0252, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0312, "f_coverage": 0.0312, "f_balanced": 0.0491, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 938, "chars": 3754, "content_recall": 0.8616, "noise_retention": 0.2632, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.066, "f_precision": 0.8334, "f_coverage": 0.8334, "f_balanced": 0.7944, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 884, "chars": 3537, "content_recall": 0.8616, "noise_retention": 0.2632, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.131, "f_precision": 0.8334, "f_coverage": 0.8334, "f_balanced": 0.7944, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 561, "chars": 2244, "content_recall": 0.8868, "noise_retention": 0.8632, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.783, "f_precision": 0.4231, "f_coverage": 0.4231, "f_balanced": 0.2371, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 929, "chars": 3716, "content_recall": 0.8616, "noise_retention": 0.2632, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.076, "f_precision": 0.8334, "f_coverage": 0.8334, "f_balanced": 0.7944, "anchor_diag": { "content_chars": 1212, "noise_chars": 929, "content_ngrams": 159, "noise_ngrams": 95, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" } }, "scoreable": true }, "rails-guides": { "meta": { "id": "rails-guides", "url": "https://guides.rubyonrails.org/", "requested_url": "https://guides.rubyonrails.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 41451 } }, "anchors": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1955, "chars": 7822, "content_recall": 0.9709, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.512, "f_precision": 0.9766, "f_coverage": 0.9766, "f_balanced": 0.9852, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2148, "chars": 8592, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.466, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1755, "chars": 7022, "content_recall": 0.8516, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.57, "f_precision": 0.8776, "f_coverage": 0.8776, "f_balanced": 0.9198, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2845, "chars": 11383, "content_recall": 0.8124, "noise_retention": 0.0655, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.351, "f_precision": 0.8342, "f_coverage": 0.8342, "f_balanced": 0.8692, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2805, "chars": 11220, "content_recall": 0.8124, "noise_retention": 0.2579, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.357, "f_precision": 0.7973, "f_coverage": 0.7973, "f_balanced": 0.7757, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5430, "chars": 21721, "content_recall": 0.8064, "noise_retention": 0.8155, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.184, "f_precision": 0.4817, "f_coverage": 0.4817, "f_balanced": 0.3003, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5389, "chars": 21559, "content_recall": 0.8064, "noise_retention": 0.8155, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.186, "f_precision": 0.4817, "f_coverage": 0.4817, "f_balanced": 0.3003, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4001, "chars": 16007, "content_recall": 0.8124, "noise_retention": 0.9841, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.25, "f_precision": 0.0736, "f_coverage": 0.0736, "f_balanced": 0.0311, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5421, "chars": 21686, "content_recall": 0.8064, "noise_retention": 0.8155, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.184, "f_precision": 0.4817, "f_coverage": 0.4817, "f_balanced": 0.3003, "anchor_diag": { "content_chars": 7680, "noise_chars": 9331, "content_ngrams": 997, "noise_ngrams": 504, "ambiguous_ngrams_removed": 2, "content_sentences": 80 }, "notes": "" } }, "scoreable": true }, "react-docs": { "meta": { "id": "react-docs", "url": "https://react.dev/learn", "requested_url": "https://react.dev/learn", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 265160 } }, "anchors": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 3617, "chars": 14471, "content_recall": 0.7398, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7804, "f_coverage": 0.7804, "f_balanced": 0.8504, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 3723, "chars": 14895, "content_recall": 0.7704, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8075, "f_coverage": 0.8075, "f_balanced": 0.8703, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1918, "chars": 7674, "content_recall": 0.5143, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5696, "f_coverage": 0.5696, "f_balanced": 0.6792, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 3096, "chars": 12384, "content_recall": 0.8641, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8883, "f_coverage": 0.8883, "f_balanced": 0.9271, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" }, "readability": { "method": "readability", "tokens": 3047, "chars": 12188, "content_recall": 0.8825, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9037, "f_coverage": 0.9037, "f_balanced": 0.9376, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5866, "chars": 23465, "content_recall": 0.8322, "noise_retention": 0.6108, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6779, "f_coverage": 0.6779, "f_balanced": 0.5303, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6533, "chars": 26135, "content_recall": 0.8322, "noise_retention": 0.6847, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6267, "f_coverage": 0.6267, "f_balanced": 0.4573, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3575, "chars": 14301, "content_recall": 0.8716, "noise_retention": 0.9409, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2325, "f_coverage": 0.2325, "f_balanced": 0.1107, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5803, "chars": 23212, "content_recall": 0.8322, "noise_retention": 0.6108, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6779, "f_coverage": 0.6779, "f_balanced": 0.5303, "anchor_diag": { "content_chars": 17046, "noise_chars": 3148, "content_ngrams": 1472, "noise_ngrams": 203, "ambiguous_ngrams_removed": 40, "content_sentences": 150 }, "notes": "" } }, "scoreable": true }, "react-hooks": { "meta": { "id": "react-hooks", "url": "https://react.dev/reference/react/hooks", "requested_url": "https://react.dev/reference/react/hooks", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 173447 } }, "anchors": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1276, "chars": 5104, "content_recall": 0.8481, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.567, "f_precision": 0.8746, "f_coverage": 0.8746, "f_balanced": 0.9178, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1276, "chars": 5104, "content_recall": 0.8481, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.567, "f_precision": 0.8746, "f_coverage": 0.8746, "f_balanced": 0.9178, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 934, "chars": 3739, "content_recall": 0.6466, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.071, "f_precision": 0.6958, "f_coverage": 0.6958, "f_balanced": 0.7854, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1138, "chars": 4552, "content_recall": 0.9046, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.757, "f_precision": 0.9222, "f_coverage": 0.9222, "f_balanced": 0.9499, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1042, "chars": 4169, "content_recall": 0.8357, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.96, "f_precision": 0.8641, "f_coverage": 0.8641, "f_balanced": 0.9105, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4161, "chars": 16645, "content_recall": 0.7756, "noise_retention": 0.2047, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.481, "f_precision": 0.7795, "f_coverage": 0.7795, "f_balanced": 0.7854, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4366, "chars": 17464, "content_recall": 0.7756, "noise_retention": 0.2372, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.458, "f_precision": 0.773, "f_coverage": 0.773, "f_balanced": 0.7692, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1747, "chars": 6989, "content_recall": 0.9046, "noise_retention": 0.9163, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.145, "f_precision": 0.3055, "f_coverage": 0.3055, "f_balanced": 0.1533, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4141, "chars": 16567, "content_recall": 0.7756, "noise_retention": 0.2047, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.483, "f_precision": 0.7795, "f_coverage": 0.7795, "f_balanced": 0.7854, "anchor_diag": { "content_chars": 5235, "noise_chars": 4174, "content_ngrams": 566, "noise_ngrams": 215, "ambiguous_ngrams_removed": 40, "content_sentences": 61 }, "notes": "" } }, "scoreable": true }, "readthedocs": { "meta": { "id": "readthedocs", "url": "https://docs.readthedocs.com/platform/stable/", "requested_url": "https://docs.readthedocs.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 24329 } }, "anchors": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 705, "chars": 2823, "content_recall": 0.6704, "noise_retention": 0.004, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7173, "f_coverage": 0.7173, "f_balanced": 0.8014, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 787, "chars": 3151, "content_recall": 0.7877, "noise_retention": 0.004, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8221, "f_coverage": 0.8221, "f_balanced": 0.8797, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 531, "chars": 2125, "content_recall": 0.4749, "noise_retention": 0.0119, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5299, "f_coverage": 0.5299, "f_balanced": 0.6415, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 866, "chars": 3467, "content_recall": 0.6425, "noise_retention": 0.004, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6916, "f_coverage": 0.6916, "f_balanced": 0.7811, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" }, "readability": { "method": "readability", "tokens": 154, "chars": 616, "content_recall": 0.1508, "noise_retention": 0.004, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1817, "f_coverage": 0.1817, "f_balanced": 0.262, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2291, "chars": 9167, "content_recall": 0.6201, "noise_retention": 0.1067, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.436, "f_precision": 0.6605, "f_coverage": 0.6605, "f_balanced": 0.732, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2210, "chars": 8841, "content_recall": 0.6229, "noise_retention": 0.1067, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.452, "f_precision": 0.663, "f_coverage": 0.663, "f_balanced": 0.734, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1352, "chars": 5411, "content_recall": 0.6397, "noise_retention": 0.9368, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.74, "f_precision": 0.2266, "f_coverage": 0.2266, "f_balanced": 0.1151, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2270, "chars": 9081, "content_recall": 0.6201, "noise_retention": 0.1067, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.441, "f_precision": 0.6605, "f_coverage": 0.6605, "f_balanced": 0.732, "anchor_diag": { "content_chars": 2560, "noise_chars": 3809, "content_ngrams": 358, "noise_ngrams": 253, "ambiguous_ngrams_removed": 3, "content_sentences": 33 }, "notes": "" } }, "scoreable": true }, "redis-docs": { "meta": { "id": "redis-docs", "url": "https://redis.io/docs/latest/", "requested_url": "https://redis.io/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 119543 } }, "anchors": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 381, "chars": 1524, "content_recall": 0.2007, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2389, "f_coverage": 0.2389, "f_balanced": 0.3343, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 514, "chars": 2057, "content_recall": 0.4388, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4943, "f_coverage": 0.4943, "f_balanced": 0.6099, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 310, "chars": 1242, "content_recall": 0.102, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1244, "f_coverage": 0.1244, "f_balanced": 0.1852, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 447, "chars": 1790, "content_recall": 0.398, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4524, "f_coverage": 0.4524, "f_balanced": 0.5693, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2, "chars": 9, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1751, "chars": 7007, "content_recall": 0.415, "noise_retention": 0.25, "noise_keyword_total": 4, "noise_per_1k_tokens": 2.284, "f_precision": 0.4557, "f_coverage": 0.4557, "f_balanced": 0.5343, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1920, "chars": 7681, "content_recall": 0.415, "noise_retention": 0.25, "noise_keyword_total": 4, "noise_per_1k_tokens": 2.083, "f_precision": 0.4557, "f_coverage": 0.4557, "f_balanced": 0.5343, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 891, "chars": 3567, "content_recall": 0.619, "noise_retention": 0.8636, "noise_keyword_total": 3, "noise_per_1k_tokens": 3.367, "f_precision": 0.3625, "f_coverage": 0.3625, "f_balanced": 0.2235, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1746, "chars": 6986, "content_recall": 0.415, "noise_retention": 0.25, "noise_keyword_total": 4, "noise_per_1k_tokens": 2.291, "f_precision": 0.4557, "f_coverage": 0.4557, "f_balanced": 0.5343, "anchor_diag": { "content_chars": 2493, "noise_chars": 873, "content_ngrams": 294, "noise_ngrams": 88, "ambiguous_ngrams_removed": 11, "content_sentences": 16 }, "notes": "" } }, "scoreable": true }, "render-docs": { "meta": { "id": "render-docs", "url": "https://render.com/docs", "requested_url": "https://render.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 570337 } }, "anchors": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 292, "chars": 1168, "content_recall": 0.2226, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2636, "f_coverage": 0.2636, "f_balanced": 0.3641, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 301, "chars": 1207, "content_recall": 0.2516, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2959, "f_coverage": 0.2959, "f_balanced": 0.4021, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 245, "chars": 980, "content_recall": 0.1419, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1713, "f_coverage": 0.1713, "f_balanced": 0.2486, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 217, "chars": 870, "content_recall": 0.1, "noise_retention": 0.0298, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1219, "f_coverage": 0.1219, "f_balanced": 0.1813, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" }, "readability": { "method": "readability", "tokens": 55, "chars": 222, "content_recall": 0.0677, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0833, "f_coverage": 0.0833, "f_balanced": 0.1269, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3541, "chars": 14164, "content_recall": 0.2516, "noise_retention": 0.1577, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.565, "f_precision": 0.2927, "f_coverage": 0.2927, "f_balanced": 0.3875, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3823, "chars": 15294, "content_recall": 0.2516, "noise_retention": 0.1577, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.523, "f_precision": 0.2927, "f_coverage": 0.2927, "f_balanced": 0.3875, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1251, "chars": 5005, "content_recall": 0.7323, "noise_retention": 0.9405, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.799, "f_precision": 0.2246, "f_coverage": 0.2246, "f_balanced": 0.1101, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3533, "chars": 14133, "content_recall": 0.2516, "noise_retention": 0.1577, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.566, "f_precision": 0.2927, "f_coverage": 0.2927, "f_balanced": 0.3875, "anchor_diag": { "content_chars": 2718, "noise_chars": 5273, "content_ngrams": 310, "noise_ngrams": 336, "ambiguous_ngrams_removed": 5, "content_sentences": 37 }, "notes": "" } }, "scoreable": true }, "ruff-docs": { "meta": { "id": "ruff-docs", "url": "https://docs.astral.sh/ruff/", "requested_url": "https://docs.astral.sh/ruff/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 33612 } }, "anchors": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 786, "chars": 3147, "content_recall": 0.6893, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.735, "f_coverage": 0.735, "f_balanced": 0.8161, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 901, "chars": 3605, "content_recall": 0.7571, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7958, "f_coverage": 0.7958, "f_balanced": 0.8618, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 568, "chars": 2272, "content_recall": 0.5929, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6454, "f_coverage": 0.6454, "f_balanced": 0.7444, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 606, "chars": 2427, "content_recall": 0.9571, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9654, "f_coverage": 0.9654, "f_balanced": 0.9781, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" }, "readability": { "method": "readability", "tokens": 595, "chars": 2382, "content_recall": 0.9714, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.977, "f_coverage": 0.977, "f_balanced": 0.9855, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1564, "chars": 6258, "content_recall": 0.6571, "noise_retention": 0.0952, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6952, "f_coverage": 0.6952, "f_balanced": 0.7613, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1629, "chars": 6519, "content_recall": 0.6571, "noise_retention": 0.0952, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6952, "f_coverage": 0.6952, "f_balanced": 0.7613, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 719, "chars": 2876, "content_recall": 0.9429, "noise_retention": 0.2857, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8861, "f_coverage": 0.8861, "f_balanced": 0.8128, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1563, "chars": 6255, "content_recall": 0.6571, "noise_retention": 0.0952, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6952, "f_coverage": 0.6952, "f_balanced": 0.7613, "anchor_diag": { "content_chars": 2593, "noise_chars": 531, "content_ngrams": 280, "noise_ngrams": 21, "ambiguous_ngrams_removed": 37, "content_sentences": 27 }, "notes": "" } }, "scoreable": true }, "rust-book": { "meta": { "id": "rust-book", "url": "https://doc.rust-lang.org/book/", "requested_url": "https://doc.rust-lang.org/book/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 22496 } }, "anchors": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 276, "chars": 1105, "content_recall": 0.7845, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8198, "f_coverage": 0.8198, "f_balanced": 0.8792, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 310, "chars": 1243, "content_recall": 0.8621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8865, "f_coverage": 0.8865, "f_balanced": 0.9259, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 276, "chars": 1105, "content_recall": 0.7845, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8198, "f_coverage": 0.8198, "f_balanced": 0.8792, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 240, "chars": 963, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "readability": { "method": "readability", "tokens": 245, "chars": 980, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 368, "chars": 1472, "content_recall": 0.8621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8865, "f_coverage": 0.8865, "f_balanced": 0.9259, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 386, "chars": 1547, "content_recall": 0.8621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8865, "f_coverage": 0.8865, "f_balanced": 0.9259, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 304, "chars": 1216, "content_recall": 1.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 1.0, "f_coverage": 1.0, "f_balanced": 1.0, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 352, "chars": 1410, "content_recall": 0.8621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8865, "f_coverage": 0.8865, "f_balanced": 0.9259, "anchor_diag": { "content_chars": 914, "noise_chars": 0, "content_ngrams": 116, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 8 }, "notes": "" } }, "scoreable": true }, "rust-std": { "meta": { "id": "rust-std", "url": "https://doc.rust-lang.org/std/", "requested_url": "https://doc.rust-lang.org/std/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 56601 } }, "anchors": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2288, "chars": 9155, "content_recall": 0.8029, "noise_retention": 0.093, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8217, "f_coverage": 0.8217, "f_balanced": 0.8517, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2288, "chars": 9155, "content_recall": 0.8029, "noise_retention": 0.093, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8217, "f_coverage": 0.8217, "f_balanced": 0.8517, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1921, "chars": 7686, "content_recall": 0.6496, "noise_retention": 0.093, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6887, "f_coverage": 0.6887, "f_balanced": 0.757, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 5160, "chars": 20640, "content_recall": 0.9826, "noise_retention": 0.093, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9665, "f_coverage": 0.9665, "f_balanced": 0.9433, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" }, "readability": { "method": "readability", "tokens": 4891, "chars": 19567, "content_recall": 0.9826, "noise_retention": 0.093, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9665, "f_coverage": 0.9665, "f_balanced": 0.9433, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8850, "chars": 35400, "content_recall": 0.8121, "noise_retention": 0.6512, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6416, "f_coverage": 0.6416, "f_balanced": 0.488, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 8460, "chars": 33840, "content_recall": 0.8304, "noise_retention": 0.8837, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3727, "f_coverage": 0.3727, "f_balanced": 0.204, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 5039, "chars": 20156, "content_recall": 0.9847, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8843, "chars": 35375, "content_recall": 0.8121, "noise_retention": 0.6512, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6416, "f_coverage": 0.6416, "f_balanced": 0.488, "anchor_diag": { "content_chars": 7286, "noise_chars": 399, "content_ngrams": 979, "noise_ngrams": 43, "ambiguous_ngrams_removed": 2, "content_sentences": 65 }, "notes": "" } }, "scoreable": true }, "salesforce-product": { "meta": { "id": "salesforce-product", "url": "https://www.salesforce.com/products/?bc=OTH", "requested_url": "https://www.salesforce.com/products/", "category": "marketing", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 504023 } }, "anchors": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2688, "chars": 10755, "content_recall": 0.7915, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.826, "f_coverage": 0.826, "f_balanced": 0.8836, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2688, "chars": 10755, "content_recall": 0.7915, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.826, "f_coverage": 0.826, "f_balanced": 0.8836, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2647, "chars": 10591, "content_recall": 0.7811, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8169, "f_coverage": 0.8169, "f_balanced": 0.8771, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2873, "chars": 11493, "content_recall": 0.8221, "noise_retention": 0.814, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4883, "f_coverage": 0.4883, "f_balanced": 0.3034, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" }, "readability": { "method": "readability", "tokens": 72, "chars": 290, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 19169, "chars": 76679, "content_recall": 0.8909, "noise_retention": 0.0, "noise_keyword_total": 12, "noise_per_1k_tokens": 0.626, "f_precision": 0.9108, "f_coverage": 0.9108, "f_balanced": 0.9423, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 19291, "chars": 77166, "content_recall": 0.8909, "noise_retention": 0.0, "noise_keyword_total": 12, "noise_per_1k_tokens": 0.622, "f_precision": 0.9108, "f_coverage": 0.9108, "f_balanced": 0.9423, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3199, "chars": 12797, "content_recall": 0.9736, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9788, "f_coverage": 0.9788, "f_balanced": 0.9866, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 19070, "chars": 76281, "content_recall": 0.8909, "noise_retention": 0.0, "noise_keyword_total": 12, "noise_per_1k_tokens": 0.629, "f_precision": 0.9108, "f_coverage": 0.9108, "f_balanced": 0.9423, "anchor_diag": { "content_chars": 12788, "noise_chars": 1938, "content_ngrams": 1439, "noise_ngrams": 43, "ambiguous_ngrams_removed": 209, "content_sentences": 96 }, "notes": "" } }, "scoreable": true }, "salesforce-trailhead": { "meta": { "id": "salesforce-trailhead", "url": "https://trailhead.salesforce.com/", "requested_url": "https://trailhead.salesforce.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 239994 } }, "anchors": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 374, "chars": 1498, "content_recall": 0.5403, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.595, "f_coverage": 0.595, "f_balanced": 0.7015, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 374, "chars": 1498, "content_recall": 0.5403, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.595, "f_coverage": 0.595, "f_balanced": 0.7015, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 374, "chars": 1498, "content_recall": 0.5403, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.595, "f_coverage": 0.595, "f_balanced": 0.7015, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 529, "chars": 2119, "content_recall": 0.6967, "noise_retention": 0.1071, "noise_keyword_total": 2, "noise_per_1k_tokens": 3.781, "f_precision": 0.7287, "f_coverage": 0.7287, "f_balanced": 0.7827, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" }, "readability": { "method": "readability", "tokens": 356, "chars": 1426, "content_recall": 0.5877, "noise_retention": 0.0833, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6331, "f_coverage": 0.6331, "f_balanced": 0.7162, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2461, "chars": 9844, "content_recall": 0.6209, "noise_retention": 0.628, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.438, "f_precision": 0.5476, "f_coverage": 0.5476, "f_balanced": 0.4653, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2390, "chars": 9563, "content_recall": 0.6209, "noise_retention": 0.628, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.51, "f_precision": 0.5476, "f_coverage": 0.5476, "f_balanced": 0.4653, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1178, "chars": 4715, "content_recall": 0.8104, "noise_retention": 0.9524, "noise_keyword_total": 5, "noise_per_1k_tokens": 4.244, "f_precision": 0.1928, "f_coverage": 0.1928, "f_balanced": 0.09, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2450, "chars": 9801, "content_recall": 0.6209, "noise_retention": 0.628, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.449, "f_precision": 0.5476, "f_coverage": 0.5476, "f_balanced": 0.4653, "anchor_diag": { "content_chars": 3568, "noise_chars": 3224, "content_ngrams": 211, "noise_ngrams": 336, "ambiguous_ngrams_removed": 76, "content_sentences": 28 }, "notes": "" } }, "scoreable": true }, "scipy-docs": { "meta": { "id": "scipy-docs", "url": "https://docs.scipy.org/doc/scipy/", "requested_url": "https://docs.scipy.org/doc/scipy/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 22267 } }, "anchors": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 264, "chars": 1057, "content_recall": 0.8661, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.89, "f_coverage": 0.89, "f_balanced": 0.9283, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 275, "chars": 1102, "content_recall": 0.8976, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9164, "f_coverage": 0.9164, "f_balanced": 0.9461, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 242, "chars": 969, "content_recall": 0.8504, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8766, "f_coverage": 0.8766, "f_balanced": 0.9191, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 284, "chars": 1139, "content_recall": 0.874, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8966, "f_coverage": 0.8966, "f_balanced": 0.9328, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "readability": { "method": "readability", "tokens": 195, "chars": 782, "content_recall": 0.748, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7877, "f_coverage": 0.7877, "f_balanced": 0.8559, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 784, "chars": 3138, "content_recall": 0.8031, "noise_retention": 0.2045, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8016, "f_coverage": 0.8016, "f_balanced": 0.7993, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 789, "chars": 3157, "content_recall": 0.8031, "noise_retention": 0.2045, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8016, "f_coverage": 0.8016, "f_balanced": 0.7993, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 432, "chars": 1728, "content_recall": 0.8819, "noise_retention": 0.7273, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6096, "f_coverage": 0.6096, "f_balanced": 0.4166, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 770, "chars": 3080, "content_recall": 0.8031, "noise_retention": 0.2045, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8016, "f_coverage": 0.8016, "f_balanced": 0.7993, "anchor_diag": { "content_chars": 1008, "noise_chars": 459, "content_ngrams": 127, "noise_ngrams": 44, "ambiguous_ngrams_removed": 0, "content_sentences": 11 }, "notes": "" } }, "scoreable": true }, "scrapy-docs": { "meta": { "id": "scrapy-docs", "url": "https://docs.scrapy.org/en/latest/", "requested_url": "https://docs.scrapy.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 29730 } }, "anchors": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 931, "chars": 3724, "content_recall": 0.7722, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.809, "f_coverage": 0.809, "f_balanced": 0.8714, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1038, "chars": 4153, "content_recall": 0.8871, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.963, "f_precision": 0.9076, "f_coverage": 0.9076, "f_balanced": 0.9402, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 603, "chars": 2413, "content_recall": 0.4234, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4786, "f_coverage": 0.4786, "f_balanced": 0.5949, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1185, "chars": 4742, "content_recall": 0.5323, "noise_retention": 0.0993, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.688, "f_precision": 0.5797, "f_coverage": 0.5797, "f_balanced": 0.6691, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" }, "readability": { "method": "readability", "tokens": 15, "chars": 60, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2513, "chars": 10052, "content_recall": 0.4577, "noise_retention": 0.1656, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.99, "f_precision": 0.5031, "f_coverage": 0.5031, "f_balanced": 0.5911, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2472, "chars": 9891, "content_recall": 0.4577, "noise_retention": 0.1722, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.023, "f_precision": 0.5026, "f_coverage": 0.5026, "f_balanced": 0.5894, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1438, "chars": 5753, "content_recall": 0.5323, "noise_retention": 0.9338, "noise_keyword_total": 3, "noise_per_1k_tokens": 2.086, "f_precision": 0.2211, "f_coverage": 0.2211, "f_balanced": 0.1178, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2487, "chars": 9950, "content_recall": 0.4657, "noise_retention": 0.1656, "noise_keyword_total": 5, "noise_per_1k_tokens": 2.01, "f_precision": 0.5109, "f_coverage": 0.5109, "f_balanced": 0.5978, "anchor_diag": { "content_chars": 3833, "noise_chars": 2253, "content_ngrams": 496, "noise_ngrams": 151, "ambiguous_ngrams_removed": 1, "content_sentences": 60 }, "notes": "" } }, "scoreable": true }, "selenium-docs": { "meta": { "id": "selenium-docs", "url": "https://www.selenium.dev/documentation/", "requested_url": "https://www.selenium.dev/documentation/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 99102 } }, "anchors": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1395, "chars": 5580, "content_recall": 0.8818, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9032, "f_coverage": 0.9032, "f_balanced": 0.9372, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1395, "chars": 5580, "content_recall": 0.8818, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9032, "f_coverage": 0.9032, "f_balanced": 0.9372, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 901, "chars": 3605, "content_recall": 0.5386, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5934, "f_coverage": 0.5934, "f_balanced": 0.7001, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 962, "chars": 3851, "content_recall": 0.9614, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9689, "f_coverage": 0.9689, "f_balanced": 0.9803, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "readability": { "method": "readability", "tokens": 997, "chars": 3991, "content_recall": 0.9273, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.941, "f_coverage": 0.941, "f_balanced": 0.9623, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5301, "chars": 21207, "content_recall": 0.8205, "noise_retention": 0.1463, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.566, "f_precision": 0.8269, "f_coverage": 0.8269, "f_balanced": 0.8367, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5581, "chars": 22325, "content_recall": 0.8205, "noise_retention": 0.1463, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.538, "f_precision": 0.8269, "f_coverage": 0.8269, "f_balanced": 0.8367, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1632, "chars": 6531, "content_recall": 0.8545, "noise_retention": 0.9582, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.613, "f_precision": 0.1748, "f_coverage": 0.1748, "f_balanced": 0.0797, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5280, "chars": 21121, "content_recall": 0.8205, "noise_retention": 0.1463, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.568, "f_precision": 0.8269, "f_coverage": 0.8269, "f_balanced": 0.8367, "anchor_diag": { "content_chars": 4967, "noise_chars": 4210, "content_ngrams": 440, "noise_ngrams": 287, "ambiguous_ngrams_removed": 0, "content_sentences": 39 }, "notes": "" } }, "scoreable": true }, "sendgrid-docs": { "meta": { "id": "sendgrid-docs", "url": "https://www.twilio.com/docs/sendgrid", "requested_url": "https://docs.sendgrid.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 308763 } }, "anchors": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2189, "chars": 8756, "content_recall": 0.6692, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7166, "f_coverage": 0.7166, "f_balanced": 0.8018, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2189, "chars": 8756, "content_recall": 0.6692, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7166, "f_coverage": 0.7166, "f_balanced": 0.8018, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 743, "chars": 2975, "content_recall": 0.1678, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2013, "f_coverage": 0.2013, "f_balanced": 0.2873, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 599, "chars": 2399, "content_recall": 0.1964, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.669, "f_precision": 0.234, "f_coverage": 0.234, "f_balanced": 0.3283, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" }, "readability": { "method": "readability", "tokens": 81, "chars": 325, "content_recall": 0.0286, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0355, "f_coverage": 0.0355, "f_balanced": 0.0556, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3679, "chars": 14717, "content_recall": 0.7598, "noise_retention": 0.3966, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.815, "f_precision": 0.7223, "f_coverage": 0.7223, "f_balanced": 0.6726, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4439, "chars": 17757, "content_recall": 0.7598, "noise_retention": 0.3966, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.676, "f_precision": 0.7223, "f_coverage": 0.7223, "f_balanced": 0.6726, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2401, "chars": 9605, "content_recall": 0.7788, "noise_retention": 0.6552, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.249, "f_precision": 0.6222, "f_coverage": 0.6222, "f_balanced": 0.478, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3596, "chars": 14385, "content_recall": 0.7598, "noise_retention": 0.3966, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.834, "f_precision": 0.7223, "f_coverage": 0.7223, "f_balanced": 0.6726, "anchor_diag": { "content_chars": 18358, "noise_chars": 705, "content_ngrams": 1049, "noise_ngrams": 58, "ambiguous_ngrams_removed": 0, "content_sentences": 141 }, "notes": "" } }, "scoreable": true }, "sentry-docs": { "meta": { "id": "sentry-docs", "url": "https://docs.sentry.io/", "requested_url": "https://docs.sentry.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 224344 } }, "anchors": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 258, "chars": 1034, "content_recall": 0.31, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3597, "f_coverage": 0.3597, "f_balanced": 0.4733, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 258, "chars": 1034, "content_recall": 0.31, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3597, "f_coverage": 0.3597, "f_balanced": 0.4733, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 189, "chars": 757, "content_recall": 0.1485, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1789, "f_coverage": 0.1789, "f_balanced": 0.2586, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 193, "chars": 773, "content_recall": 0.3319, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3831, "f_coverage": 0.3831, "f_balanced": 0.4984, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "readability": { "method": "readability", "tokens": 45, "chars": 181, "content_recall": 0.0306, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0379, "f_coverage": 0.0379, "f_balanced": 0.0593, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1249, "chars": 4996, "content_recall": 0.4716, "noise_retention": 0.1034, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.521, "f_coverage": 0.521, "f_balanced": 0.6181, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1224, "chars": 4898, "content_recall": 0.3755, "noise_retention": 0.1034, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4249, "f_coverage": 0.4249, "f_balanced": 0.5294, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 525, "chars": 2103, "content_recall": 0.6856, "noise_retention": 0.7241, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5286, "f_coverage": 0.5286, "f_balanced": 0.3934, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1230, "chars": 4920, "content_recall": 0.4716, "noise_retention": 0.1034, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.521, "f_coverage": 0.521, "f_balanced": 0.6181, "anchor_diag": { "content_chars": 1741, "noise_chars": 297, "content_ngrams": 229, "noise_ngrams": 29, "ambiguous_ngrams_removed": 0, "content_sentences": 24 }, "notes": "" } }, "scoreable": true }, "shopify-admin-api": { "meta": { "id": "shopify-admin-api", "url": "https://shopify.dev/docs/api/admin-graphql/latest", "requested_url": "https://shopify.dev/docs/api/admin", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 471191 } }, "anchors": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 4407, "chars": 17628, "content_recall": 0.7717, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8086, "f_coverage": 0.8086, "f_balanced": 0.8711, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 4468, "chars": 17874, "content_recall": 0.7824, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.818, "f_coverage": 0.818, "f_balanced": 0.8779, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2729, "chars": 10918, "content_recall": 0.6053, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6571, "f_coverage": 0.6571, "f_balanced": 0.7541, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2828, "chars": 11312, "content_recall": 0.7432, "noise_retention": 0.012, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.782, "f_coverage": 0.782, "f_balanced": 0.8483, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2416, "chars": 9666, "content_recall": 0.6814, "noise_retention": 0.0542, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7217, "f_coverage": 0.7217, "f_balanced": 0.7921, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5991, "chars": 23964, "content_recall": 0.7681, "noise_retention": 0.3373, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.501, "f_precision": 0.7444, "f_coverage": 0.7444, "f_balanced": 0.7115, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6240, "chars": 24961, "content_recall": 0.776, "noise_retention": 0.3253, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.481, "f_precision": 0.7533, "f_coverage": 0.7533, "f_balanced": 0.7218, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4465, "chars": 17860, "content_recall": 0.8464, "noise_retention": 0.759, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.448, "f_precision": 0.5633, "f_coverage": 0.5633, "f_balanced": 0.3751, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5984, "chars": 23939, "content_recall": 0.7681, "noise_retention": 0.3373, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.501, "f_precision": 0.7444, "f_coverage": 0.7444, "f_balanced": 0.7115, "anchor_diag": { "content_chars": 17265, "noise_chars": 1976, "content_ngrams": 1406, "noise_ngrams": 166, "ambiguous_ngrams_removed": 7, "content_sentences": 172 }, "notes": "" } }, "scoreable": true }, "shopify-docs": { "meta": { "id": "shopify-docs", "url": "https://shopify.dev/docs", "requested_url": "https://shopify.dev/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 337384 } }, "anchors": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1026, "chars": 4105, "content_recall": 0.5847, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6377, "f_coverage": 0.6377, "f_balanced": 0.7379, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1103, "chars": 4414, "content_recall": 0.6752, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7221, "f_coverage": 0.7221, "f_balanced": 0.8061, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 539, "chars": 2159, "content_recall": 0.3387, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3904, "f_coverage": 0.3904, "f_balanced": 0.5061, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 565, "chars": 2260, "content_recall": 0.4756, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5314, "f_coverage": 0.5314, "f_balanced": 0.6447, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" }, "readability": { "method": "readability", "tokens": 71, "chars": 286, "content_recall": 0.0673, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0827, "f_coverage": 0.0827, "f_balanced": 0.1261, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2240, "chars": 8961, "content_recall": 0.6357, "noise_retention": 0.0833, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.339, "f_precision": 0.6772, "f_coverage": 0.6772, "f_balanced": 0.7508, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2247, "chars": 8989, "content_recall": 0.58, "noise_retention": 0.0833, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.335, "f_precision": 0.626, "f_coverage": 0.626, "f_balanced": 0.7105, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1097, "chars": 4389, "content_recall": 0.7216, "noise_retention": 0.6667, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.823, "f_precision": 0.5852, "f_coverage": 0.5852, "f_balanced": 0.456, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2227, "chars": 8910, "content_recall": 0.6357, "noise_retention": 0.0833, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.347, "f_precision": 0.6772, "f_coverage": 0.6772, "f_balanced": 0.7508, "anchor_diag": { "content_chars": 5733, "noise_chars": 531, "content_ngrams": 431, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 70 }, "notes": "" } }, "scoreable": true }, "sklearn-docs": { "meta": { "id": "sklearn-docs", "url": "https://scikit-learn.org/stable/", "requested_url": "https://scikit-learn.org/stable/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 35901 } }, "anchors": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 662, "chars": 2648, "content_recall": 0.5254, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5805, "f_coverage": 0.5805, "f_balanced": 0.6889, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 671, "chars": 2687, "content_recall": 0.5593, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6134, "f_coverage": 0.6134, "f_balanced": 0.7174, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 341, "chars": 1365, "content_recall": 0.2627, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3082, "f_coverage": 0.3082, "f_balanced": 0.4161, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 453, "chars": 1812, "content_recall": 0.8305, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8596, "f_coverage": 0.8596, "f_balanced": 0.9074, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "readability": { "method": "readability", "tokens": 44, "chars": 179, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2515, "chars": 10063, "content_recall": 0.5593, "noise_retention": 0.0303, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.398, "f_precision": 0.611, "f_coverage": 0.611, "f_balanced": 0.7094, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2525, "chars": 10102, "content_recall": 0.5593, "noise_retention": 0.0303, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.396, "f_precision": 0.611, "f_coverage": 0.611, "f_balanced": 0.7094, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1028, "chars": 4113, "content_recall": 0.8305, "noise_retention": 0.8788, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.973, "f_precision": 0.3827, "f_coverage": 0.3827, "f_balanced": 0.2115, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2494, "chars": 9979, "content_recall": 0.5593, "noise_retention": 0.0303, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.401, "f_precision": 0.611, "f_coverage": 0.611, "f_balanced": 0.7094, "anchor_diag": { "content_chars": 1145, "noise_chars": 580, "content_ngrams": 118, "noise_ngrams": 33, "ambiguous_ngrams_removed": 0, "content_sentences": 17 }, "notes": "" } }, "scoreable": true }, "slack-api": { "meta": { "id": "slack-api", "url": "https://docs.slack.dev/", "requested_url": "https://api.slack.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 43392 } }, "anchors": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 330, "chars": 1320, "content_recall": 0.4619, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5176, "f_coverage": 0.5176, "f_balanced": 0.6319, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 357, "chars": 1429, "content_recall": 0.5291, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5842, "f_coverage": 0.5842, "f_balanced": 0.6921, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 317, "chars": 1268, "content_recall": 0.4395, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4949, "f_coverage": 0.4949, "f_balanced": 0.6106, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 246, "chars": 984, "content_recall": 0.5336, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5885, "f_coverage": 0.5885, "f_balanced": 0.6959, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 247, "chars": 990, "content_recall": 0.574, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6275, "f_coverage": 0.6275, "f_balanced": 0.7293, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1376, "chars": 5506, "content_recall": 0.5336, "noise_retention": 0.1724, "noise_keyword_total": 3, "noise_per_1k_tokens": 2.18, "f_precision": 0.5744, "f_coverage": 0.5744, "f_balanced": 0.6489, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1254, "chars": 5016, "content_recall": 0.5426, "noise_retention": 0.1724, "noise_keyword_total": 3, "noise_per_1k_tokens": 2.392, "f_precision": 0.5827, "f_coverage": 0.5827, "f_balanced": 0.6555, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 533, "chars": 2134, "content_recall": 0.8027, "noise_retention": 0.9052, "noise_keyword_total": 2, "noise_per_1k_tokens": 3.752, "f_precision": 0.322, "f_coverage": 0.322, "f_balanced": 0.1696, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1362, "chars": 5448, "content_recall": 0.5336, "noise_retention": 0.1724, "noise_keyword_total": 3, "noise_per_1k_tokens": 2.203, "f_precision": 0.5744, "f_coverage": 0.5744, "f_balanced": 0.6489, "anchor_diag": { "content_chars": 2034, "noise_chars": 1176, "content_ngrams": 223, "noise_ngrams": 116, "ambiguous_ngrams_removed": 0, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "slack-home": { "meta": { "id": "slack-home", "url": "https://slack.com/", "requested_url": "https://slack.com/", "category": "marketing", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 244662 } }, "anchors": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1083, "chars": 4332, "content_recall": 0.4536, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5093, "f_coverage": 0.5093, "f_balanced": 0.6241, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1083, "chars": 4332, "content_recall": 0.4536, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5093, "f_coverage": 0.5093, "f_balanced": 0.6241, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 986, "chars": 3945, "content_recall": 0.4278, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4831, "f_coverage": 0.4831, "f_balanced": 0.5993, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1132, "chars": 4528, "content_recall": 0.4089, "noise_retention": 0.0081, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4634, "f_coverage": 0.4634, "f_balanced": 0.5791, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" }, "readability": { "method": "readability", "tokens": 292, "chars": 1169, "content_recall": 0.1632, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.196, "f_coverage": 0.196, "f_balanced": 0.2806, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 8331, "chars": 33327, "content_recall": 0.4966, "noise_retention": 0.1199, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.36, "f_precision": 0.544, "f_coverage": 0.544, "f_balanced": 0.6349, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6301, "chars": 25206, "content_recall": 0.445, "noise_retention": 0.1199, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.476, "f_precision": 0.4938, "f_coverage": 0.4938, "f_balanced": 0.5911, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3044, "chars": 12177, "content_recall": 0.6478, "noise_retention": 0.8679, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.657, "f_precision": 0.3638, "f_coverage": 0.3638, "f_balanced": 0.2195, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 9898, "chars": 39594, "content_recall": 0.4588, "noise_retention": 0.1199, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.303, "f_precision": 0.5073, "f_coverage": 0.5073, "f_balanced": 0.6031, "anchor_diag": { "content_chars": 7308, "noise_chars": 13189, "content_ngrams": 582, "noise_ngrams": 492, "ambiguous_ngrams_removed": 172, "content_sentences": 80 }, "notes": "" } }, "scoreable": true }, "snowflake-docs": { "meta": { "id": "snowflake-docs", "url": "https://docs.snowflake.com/en/", "requested_url": "https://docs.snowflake.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 135683 } }, "anchors": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 785, "chars": 3143, "content_recall": 0.5535, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6078, "f_coverage": 0.6078, "f_balanced": 0.7126, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 808, "chars": 3233, "content_recall": 0.5796, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6328, "f_coverage": 0.6328, "f_balanced": 0.7339, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 384, "chars": 1537, "content_recall": 0.1384, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1672, "f_coverage": 0.1672, "f_balanced": 0.2431, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 203, "chars": 812, "content_recall": 0.1828, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2185, "f_coverage": 0.2185, "f_balanced": 0.3091, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "readability": { "method": "readability", "tokens": 35, "chars": 143, "content_recall": 0.0313, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0389, "f_coverage": 0.0389, "f_balanced": 0.0608, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1558, "chars": 6235, "content_recall": 0.6475, "noise_retention": 0.4167, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.642, "f_precision": 0.6336, "f_coverage": 0.6336, "f_balanced": 0.6138, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1540, "chars": 6163, "content_recall": 0.4595, "noise_retention": 0.4167, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.649, "f_precision": 0.4799, "f_coverage": 0.4799, "f_balanced": 0.5141, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 987, "chars": 3951, "content_recall": 0.7337, "noise_retention": 0.8667, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.013, "f_precision": 0.386, "f_coverage": 0.386, "f_balanced": 0.2257, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1552, "chars": 6210, "content_recall": 0.6475, "noise_retention": 0.4167, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.644, "f_precision": 0.6336, "f_coverage": 0.6336, "f_balanced": 0.6138, "anchor_diag": { "content_chars": 4067, "noise_chars": 506, "content_ngrams": 383, "noise_ngrams": 60, "ambiguous_ngrams_removed": 0, "content_sentences": 41 }, "notes": "" } }, "scoreable": true }, "spacy-docs": { "meta": { "id": "spacy-docs", "url": "https://spacy.io/usage", "requested_url": "https://spacy.io/usage", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 117757 } }, "anchors": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 4184, "chars": 16738, "content_recall": 0.8542, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8799, "f_coverage": 0.8799, "f_balanced": 0.9214, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 4192, "chars": 16771, "content_recall": 0.8564, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8817, "f_coverage": 0.8817, "f_balanced": 0.9227, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 3838, "chars": 15353, "content_recall": 0.7666, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8042, "f_coverage": 0.8042, "f_balanced": 0.8679, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 3639, "chars": 14558, "content_recall": 0.8631, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8874, "f_coverage": 0.8874, "f_balanced": 0.9265, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2293, "chars": 9173, "content_recall": 0.5859, "noise_retention": 0.3378, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5997, "f_coverage": 0.5997, "f_balanced": 0.6217, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5562, "chars": 22251, "content_recall": 0.7943, "noise_retention": 0.6533, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.18, "f_precision": 0.6313, "f_coverage": 0.6313, "f_balanced": 0.4827, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5558, "chars": 22233, "content_recall": 0.7966, "noise_retention": 0.6533, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.18, "f_precision": 0.6324, "f_coverage": 0.6324, "f_balanced": 0.4831, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4456, "chars": 17824, "content_recall": 0.9379, "noise_retention": 0.8578, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.224, "f_precision": 0.4426, "f_coverage": 0.4426, "f_balanced": 0.247, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5579, "chars": 22316, "content_recall": 0.8071, "noise_retention": 0.6533, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.179, "f_precision": 0.6377, "f_coverage": 0.6377, "f_balanced": 0.485, "anchor_diag": { "content_chars": 15023, "noise_chars": 2757, "content_ngrams": 1804, "noise_ngrams": 225, "ambiguous_ngrams_removed": 0, "content_sentences": 120 }, "notes": "" } }, "scoreable": true }, "spark-docs": { "meta": { "id": "spark-docs", "url": "https://spark.apache.org/docs/latest/", "requested_url": "https://spark.apache.org/docs/latest/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 24442 } }, "anchors": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1603, "chars": 6413, "content_recall": 0.7783, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8144, "f_coverage": 0.8144, "f_balanced": 0.8753, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1619, "chars": 6478, "content_recall": 0.7831, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8186, "f_coverage": 0.8186, "f_balanced": 0.8783, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1262, "chars": 5050, "content_recall": 0.621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6719, "f_coverage": 0.6719, "f_balanced": 0.7662, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1574, "chars": 6299, "content_recall": 0.851, "noise_retention": 0.0161, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8746, "f_coverage": 0.8746, "f_balanced": 0.9126, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" }, "readability": { "method": "readability", "tokens": 883, "chars": 3532, "content_recall": 0.5089, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5644, "f_coverage": 0.5644, "f_balanced": 0.6746, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2784, "chars": 11139, "content_recall": 0.7199, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7626, "f_coverage": 0.7626, "f_balanced": 0.8371, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2802, "chars": 11209, "content_recall": 0.7199, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7626, "f_coverage": 0.7626, "f_balanced": 0.8371, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1875, "chars": 7503, "content_recall": 0.907, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2768, "chars": 11075, "content_recall": 0.7199, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7626, "f_coverage": 0.7626, "f_balanced": 0.8371, "anchor_diag": { "content_chars": 7016, "noise_chars": 570, "content_ngrams": 839, "noise_ngrams": 62, "ambiguous_ngrams_removed": 0, "content_sentences": 81 }, "notes": "" } }, "scoreable": true }, "sphinx-docs": { "meta": { "id": "sphinx-docs", "url": "https://www.sphinx-doc.org/en/master/", "requested_url": "https://www.sphinx-doc.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 29659 } }, "anchors": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 791, "chars": 3166, "content_recall": 0.2859, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3336, "f_coverage": 0.3336, "f_balanced": 0.4447, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 845, "chars": 3381, "content_recall": 0.3121, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3619, "f_coverage": 0.3619, "f_balanced": 0.4757, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 731, "chars": 2927, "content_recall": 0.2631, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3085, "f_coverage": 0.3085, "f_balanced": 0.4166, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 639, "chars": 2558, "content_recall": 0.3889, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.443, "f_coverage": 0.443, "f_balanced": 0.56, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "readability": { "method": "readability", "tokens": 219, "chars": 878, "content_recall": 0.1258, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1525, "f_coverage": 0.1525, "f_balanced": 0.2235, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3019, "chars": 12077, "content_recall": 0.4837, "noise_retention": 0.2063, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5246, "f_coverage": 0.5246, "f_balanced": 0.601, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2994, "chars": 11976, "content_recall": 0.4869, "noise_retention": 0.3016, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5183, "f_coverage": 0.5183, "f_balanced": 0.5738, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1403, "chars": 5613, "content_recall": 0.7974, "noise_retention": 0.9365, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2408, "f_coverage": 0.2408, "f_balanced": 0.1176, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3005, "chars": 12023, "content_recall": 0.4837, "noise_retention": 0.2063, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5246, "f_coverage": 0.5246, "f_balanced": 0.601, "anchor_diag": { "content_chars": 5765, "noise_chars": 528, "content_ngrams": 612, "noise_ngrams": 63, "ambiguous_ngrams_removed": 0, "content_sentences": 49 }, "notes": "" } }, "scoreable": true }, "splunk-docs": { "meta": { "id": "splunk-docs", "url": "https://docs.splunk.com/Documentation", "requested_url": "https://docs.splunk.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 109697 } }, "anchors": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 199, "chars": 798, "content_recall": 0.1497, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1804, "f_coverage": 0.1804, "f_balanced": 0.2604, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 199, "chars": 798, "content_recall": 0.1497, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1804, "f_coverage": 0.1804, "f_balanced": 0.2604, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 152, "chars": 611, "content_recall": 0.0719, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0882, "f_coverage": 0.0882, "f_balanced": 0.1341, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 97, "chars": 388, "content_recall": 0.1916, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 10.309, "f_precision": 0.2286, "f_coverage": 0.2286, "f_balanced": 0.3216, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" }, "readability": { "method": "readability", "tokens": 53, "chars": 214, "content_recall": 0.0958, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.117, "f_coverage": 0.117, "f_balanced": 0.1749, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4650, "chars": 18601, "content_recall": 0.3114, "noise_retention": 0.4898, "noise_keyword_total": 9, "noise_per_1k_tokens": 1.935, "f_precision": 0.3377, "f_coverage": 0.3377, "f_balanced": 0.3867, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4922, "chars": 19689, "content_recall": 0.3114, "noise_retention": 0.4898, "noise_keyword_total": 9, "noise_per_1k_tokens": 1.829, "f_precision": 0.3377, "f_coverage": 0.3377, "f_balanced": 0.3867, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1645, "chars": 6581, "content_recall": 0.6108, "noise_retention": 0.9593, "noise_keyword_total": 7, "noise_per_1k_tokens": 4.255, "f_precision": 0.1605, "f_coverage": 0.1605, "f_balanced": 0.0762, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4799, "chars": 19197, "content_recall": 0.3114, "noise_retention": 0.4898, "noise_keyword_total": 9, "noise_per_1k_tokens": 1.875, "f_precision": 0.3377, "f_coverage": 0.3377, "f_balanced": 0.3867, "anchor_diag": { "content_chars": 1380, "noise_chars": 8330, "content_ngrams": 167, "noise_ngrams": 492, "ambiguous_ngrams_removed": 11, "content_sentences": 15 }, "notes": "" } }, "scoreable": true }, "spring-docs": { "meta": { "id": "spring-docs", "url": "https://docs.spring.io/spring-boot/", "requested_url": "https://docs.spring.io/spring-boot/docs/current/reference/html/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 83978 } }, "anchors": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 261, "chars": 1046, "content_recall": 0.7771, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8133, "f_coverage": 0.8133, "f_balanced": 0.8746, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 261, "chars": 1046, "content_recall": 0.7771, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8133, "f_coverage": 0.8133, "f_balanced": 0.8746, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 261, "chars": 1046, "content_recall": 0.7771, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8133, "f_coverage": 0.8133, "f_balanced": 0.8746, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 246, "chars": 987, "content_recall": 0.8025, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8355, "f_coverage": 0.8355, "f_balanced": 0.8905, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" }, "readability": { "method": "readability", "tokens": 82, "chars": 330, "content_recall": 0.2611, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3064, "f_coverage": 0.3064, "f_balanced": 0.4141, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 7987, "chars": 31949, "content_recall": 0.8089, "noise_retention": 0.5289, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.125, "f_precision": 0.7075, "f_coverage": 0.7075, "f_balanced": 0.5954, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 8237, "chars": 32948, "content_recall": 0.8089, "noise_retention": 0.5289, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.121, "f_precision": 0.7075, "f_coverage": 0.7075, "f_balanced": 0.5954, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2626, "chars": 10505, "content_recall": 0.8535, "noise_retention": 0.9422, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.381, "f_precision": 0.2273, "f_coverage": 0.2273, "f_balanced": 0.1082, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 7966, "chars": 31865, "content_recall": 0.8089, "noise_retention": 0.5289, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.126, "f_precision": 0.7075, "f_coverage": 0.7075, "f_balanced": 0.5954, "anchor_diag": { "content_chars": 2485, "noise_chars": 2617, "content_ngrams": 157, "noise_ngrams": 225, "ambiguous_ngrams_removed": 3, "content_sentences": 20 }, "notes": "" } }, "scoreable": true }, "sqlalchemy-docs": { "meta": { "id": "sqlalchemy-docs", "url": "https://docs.sqlalchemy.org/en/20/", "requested_url": "https://docs.sqlalchemy.org/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 25751 } }, "anchors": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 454, "chars": 1816, "content_recall": 0.407, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4617, "f_coverage": 0.4617, "f_balanced": 0.5785, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 502, "chars": 2008, "content_recall": 0.4512, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5068, "f_coverage": 0.5068, "f_balanced": 0.6218, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 436, "chars": 1745, "content_recall": 0.3814, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4352, "f_coverage": 0.4352, "f_balanced": 0.5522, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 734, "chars": 2936, "content_recall": 0.6907, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7362, "f_coverage": 0.7362, "f_balanced": 0.8171, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "readability": { "method": "readability", "tokens": 156, "chars": 627, "content_recall": 0.1186, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.144, "f_coverage": 0.144, "f_balanced": 0.2121, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1862, "chars": 7451, "content_recall": 0.3558, "noise_retention": 0.0426, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.407, "f_coverage": 0.407, "f_balanced": 0.5188, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1852, "chars": 7408, "content_recall": 0.3558, "noise_retention": 0.0426, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.407, "f_coverage": 0.407, "f_balanced": 0.5188, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1039, "chars": 4157, "content_recall": 0.7186, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1840, "chars": 7361, "content_recall": 0.3558, "noise_retention": 0.0426, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.407, "f_coverage": 0.407, "f_balanced": 0.5188, "anchor_diag": { "content_chars": 4772, "noise_chars": 457, "content_ngrams": 430, "noise_ngrams": 47, "ambiguous_ngrams_removed": 0, "content_sentences": 52 }, "notes": "" } }, "scoreable": true }, "stripe-billing": { "meta": { "id": "stripe-billing", "url": "https://docs.stripe.com/billing", "requested_url": "https://docs.stripe.com/billing", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 370923 } }, "anchors": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 794, "chars": 3176, "content_recall": 0.6498, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6987, "f_coverage": 0.6987, "f_balanced": 0.7877, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 822, "chars": 3290, "content_recall": 0.715, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7582, "f_coverage": 0.7582, "f_balanced": 0.8338, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 189, "chars": 758, "content_recall": 0.0628, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0773, "f_coverage": 0.0773, "f_balanced": 0.1182, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 342, "chars": 1371, "content_recall": 0.2657, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3114, "f_coverage": 0.3114, "f_balanced": 0.4198, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "readability": { "method": "readability", "tokens": 69, "chars": 277, "content_recall": 0.0024, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.003, "f_coverage": 0.003, "f_balanced": 0.0048, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1598, "chars": 6393, "content_recall": 0.5749, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6167, "f_coverage": 0.6167, "f_balanced": 0.6922, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1582, "chars": 6329, "content_recall": 0.4106, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4591, "f_coverage": 0.4591, "f_balanced": 0.5578, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1014, "chars": 4057, "content_recall": 0.7343, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1589, "chars": 6359, "content_recall": 0.5749, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6167, "f_coverage": 0.6167, "f_balanced": 0.6922, "anchor_diag": { "content_chars": 3896, "noise_chars": 192, "content_ngrams": 414, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" } }, "scoreable": true }, "stripe-checkout": { "meta": { "id": "stripe-checkout", "url": "https://docs.stripe.com/payments/checkout", "requested_url": "https://docs.stripe.com/payments/checkout", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 489984 } }, "anchors": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1016, "chars": 4065, "content_recall": 0.7083, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7522, "f_coverage": 0.7522, "f_balanced": 0.8293, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1016, "chars": 4065, "content_recall": 0.7083, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7522, "f_coverage": 0.7522, "f_balanced": 0.8293, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 571, "chars": 2287, "content_recall": 0.2034, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.242, "f_coverage": 0.242, "f_balanced": 0.3381, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 487, "chars": 1950, "content_recall": 0.3676, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4209, "f_coverage": 0.4209, "f_balanced": 0.5376, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "readability": { "method": "readability", "tokens": 99, "chars": 397, "content_recall": 0.0196, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0244, "f_coverage": 0.0244, "f_balanced": 0.0385, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2196, "chars": 8786, "content_recall": 0.6569, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6907, "f_coverage": 0.6907, "f_balanced": 0.7484, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2171, "chars": 8684, "content_recall": 0.5, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5464, "f_coverage": 0.5464, "f_balanced": 0.6349, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1271, "chars": 5087, "content_recall": 0.7917, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2184, "chars": 8738, "content_recall": 0.6569, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6907, "f_coverage": 0.6907, "f_balanced": 0.7484, "anchor_diag": { "content_chars": 3781, "noise_chars": 192, "content_ngrams": 408, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 46 }, "notes": "" } }, "scoreable": true }, "stripe-docs-home": { "meta": { "id": "stripe-docs-home", "url": "https://docs.stripe.com/", "requested_url": "https://docs.stripe.com/", "category": "api_docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 1301324 } }, "anchors": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 675, "chars": 2700, "content_recall": 0.7849, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8202, "f_coverage": 0.8202, "f_balanced": 0.8795, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 675, "chars": 2700, "content_recall": 0.7849, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8202, "f_coverage": 0.8202, "f_balanced": 0.8795, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 370, "chars": 1481, "content_recall": 0.3656, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4187, "f_coverage": 0.4187, "f_balanced": 0.5354, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 349, "chars": 1399, "content_recall": 0.3835, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4374, "f_coverage": 0.4374, "f_balanced": 0.5544, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "readability": { "method": "readability", "tokens": 131, "chars": 527, "content_recall": 0.0717, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.088, "f_coverage": 0.088, "f_balanced": 0.1338, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1758, "chars": 7032, "content_recall": 0.509, "noise_retention": 0.1667, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5519, "f_coverage": 0.5519, "f_balanced": 0.632, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1882, "chars": 7531, "content_recall": 0.3907, "noise_retention": 0.1667, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4371, "f_coverage": 0.4371, "f_balanced": 0.532, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 845, "chars": 3383, "content_recall": 0.8315, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1669, "chars": 6678, "content_recall": 0.509, "noise_retention": 0.1667, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5519, "f_coverage": 0.5519, "f_balanced": 0.632, "anchor_diag": { "content_chars": 3675, "noise_chars": 162, "content_ngrams": 279, "noise_ngrams": 18, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" } }, "scoreable": true }, "stripe-docs-payments": { "meta": { "id": "stripe-docs-payments", "url": "https://docs.stripe.com/payments", "requested_url": "https://docs.stripe.com/payments", "category": "api_docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 463160 } }, "anchors": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 381, "chars": 1527, "content_recall": 0.6518, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7006, "f_coverage": 0.7006, "f_balanced": 0.7892, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 411, "chars": 1646, "content_recall": 0.7321, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7736, "f_coverage": 0.7736, "f_balanced": 0.8454, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 75, "chars": 301, "content_recall": 0.0045, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0056, "f_coverage": 0.0056, "f_balanced": 0.0089, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 110, "chars": 441, "content_recall": 0.1027, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1251, "f_coverage": 0.1251, "f_balanced": 0.1862, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "readability": { "method": "readability", "tokens": 56, "chars": 227, "content_recall": 0.0982, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1198, "f_coverage": 0.1198, "f_balanced": 0.1789, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1345, "chars": 5381, "content_recall": 0.5848, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6258, "f_coverage": 0.6258, "f_balanced": 0.6993, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1345, "chars": 5381, "content_recall": 0.3839, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4322, "f_coverage": 0.4322, "f_balanced": 0.5327, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 816, "chars": 3265, "content_recall": 0.6964, "noise_retention": 1.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1336, "chars": 5346, "content_recall": 0.5848, "noise_retention": 0.1304, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6258, "f_coverage": 0.6258, "f_balanced": 0.6993, "anchor_diag": { "content_chars": 2424, "noise_chars": 192, "content_ngrams": 224, "noise_ngrams": 23, "ambiguous_ngrams_removed": 0, "content_sentences": 25 }, "notes": "" } }, "scoreable": true }, "stripe-home": { "meta": { "id": "stripe-home", "url": "https://stripe.com/", "requested_url": "https://stripe.com/", "category": "marketing", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 666191 } }, "anchors": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1960, "chars": 7843, "content_recall": 0.6097, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 1.02, "f_precision": 0.6613, "f_coverage": 0.6613, "f_balanced": 0.7575, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2190, "chars": 8761, "content_recall": 0.659, "noise_retention": 0.0, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.913, "f_precision": 0.7072, "f_coverage": 0.7072, "f_balanced": 0.7944, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1509, "chars": 6036, "content_recall": 0.531, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.663, "f_precision": 0.5859, "f_coverage": 0.5859, "f_balanced": 0.6936, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1602, "chars": 6409, "content_recall": 0.5079, "noise_retention": 0.2061, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.624, "f_precision": 0.5473, "f_coverage": 0.5473, "f_balanced": 0.6195, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1718, "chars": 6875, "content_recall": 0.5645, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6184, "f_coverage": 0.6184, "f_balanced": 0.7217, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5941, "chars": 23766, "content_recall": 0.6579, "noise_retention": 0.2872, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.01, "f_precision": 0.6682, "f_coverage": 0.6682, "f_balanced": 0.6843, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 6171, "chars": 24684, "content_recall": 0.6579, "noise_retention": 0.2872, "noise_keyword_total": 6, "noise_per_1k_tokens": 0.972, "f_precision": 0.6682, "f_coverage": 0.6682, "f_balanced": 0.6843, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 3329, "chars": 13318, "content_recall": 0.7482, "noise_retention": 0.9122, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.202, "f_precision": 0.2988, "f_coverage": 0.2988, "f_balanced": 0.1572, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5928, "chars": 23714, "content_recall": 0.6579, "noise_retention": 0.2872, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.012, "f_precision": 0.6682, "f_coverage": 0.6682, "f_balanced": 0.6843, "anchor_diag": { "content_chars": 11457, "noise_chars": 2585, "content_ngrams": 953, "noise_ngrams": 296, "ambiguous_ngrams_removed": 0, "content_sentences": 119 }, "notes": "" } }, "scoreable": true }, "supabase-docs": { "meta": { "id": "supabase-docs", "url": "https://supabase.com/docs", "requested_url": "https://supabase.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 273100 } }, "anchors": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 364, "chars": 1457, "content_recall": 0.3302, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3813, "f_coverage": 0.3813, "f_balanced": 0.4965, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 384, "chars": 1538, "content_recall": 0.3551, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4077, "f_coverage": 0.4077, "f_balanced": 0.5241, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 238, "chars": 954, "content_recall": 0.1713, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2054, "f_coverage": 0.2054, "f_balanced": 0.2926, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 411, "chars": 1646, "content_recall": 0.3832, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.433, "f_precision": 0.4371, "f_coverage": 0.4371, "f_balanced": 0.5541, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" }, "readability": { "method": "readability", "tokens": 272, "chars": 1089, "content_recall": 0.2897, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 3.676, "f_precision": 0.3377, "f_coverage": 0.3377, "f_balanced": 0.4493, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2267, "chars": 9071, "content_recall": 0.704, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.441, "f_precision": 0.7483, "f_coverage": 0.7483, "f_balanced": 0.8263, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2258, "chars": 9033, "content_recall": 0.5919, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.443, "f_precision": 0.6445, "f_coverage": 0.6445, "f_balanced": 0.7436, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 878, "chars": 3513, "content_recall": 0.8505, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.139, "f_precision": 0.8767, "f_coverage": 0.8767, "f_balanced": 0.9192, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2264, "chars": 9056, "content_recall": 0.704, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.442, "f_precision": 0.7483, "f_coverage": 0.7483, "f_balanced": 0.8263, "anchor_diag": { "content_chars": 2820, "noise_chars": 486, "content_ngrams": 321, "noise_ngrams": 11, "ambiguous_ngrams_removed": 33, "content_sentences": 28 }, "notes": "" } }, "scoreable": true }, "superset-docs": { "meta": { "id": "superset-docs", "url": "https://superset.apache.org/docs/intro/", "requested_url": "https://superset.apache.org/docs/intro", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 313 } }, "anchors": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 13, "chars": 55, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 13, "chars": 55, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 13, "chars": 55, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 3, "chars": 15, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1, "chars": 1, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1, "chars": 0, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "svelte-docs": { "meta": { "id": "svelte-docs", "url": "https://svelte.dev/docs/svelte/overview", "requested_url": "https://svelte.dev/docs/svelte/overview", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 84639 } }, "anchors": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 360, "chars": 1443, "content_recall": 0.7778, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.814, "f_coverage": 0.814, "f_balanced": 0.875, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 360, "chars": 1443, "content_recall": 0.7778, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.814, "f_coverage": 0.814, "f_balanced": 0.875, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 232, "chars": 930, "content_recall": 0.5648, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6187, "f_coverage": 0.6187, "f_balanced": 0.7219, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 272, "chars": 1090, "content_recall": 0.8981, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9168, "f_coverage": 0.9168, "f_balanced": 0.9463, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "readability": { "method": "readability", "tokens": 174, "chars": 696, "content_recall": 0.6944, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7396, "f_coverage": 0.7396, "f_balanced": 0.8197, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1481, "chars": 5926, "content_recall": 0.75, "noise_retention": 0.1314, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7711, "f_coverage": 0.7711, "f_balanced": 0.8049, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1568, "chars": 6275, "content_recall": 0.75, "noise_retention": 0.1314, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7711, "f_coverage": 0.7711, "f_balanced": 0.8049, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 648, "chars": 2592, "content_recall": 0.963, "noise_retention": 0.96, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1715, "f_coverage": 0.1715, "f_balanced": 0.0768, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1481, "chars": 5924, "content_recall": 0.75, "noise_retention": 0.1257, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7719, "f_coverage": 0.7719, "f_balanced": 0.8074, "anchor_diag": { "content_chars": 1065, "noise_chars": 1472, "content_ngrams": 108, "noise_ngrams": 175, "ambiguous_ngrams_removed": 0, "content_sentences": 9 }, "notes": "" } }, "scoreable": true }, "tailwind-docs": { "meta": { "id": "tailwind-docs", "url": "https://tailwindcss.com/docs/installation/using-vite", "requested_url": "https://tailwindcss.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 329738 } }, "anchors": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 746, "chars": 2986, "content_recall": 0.7137, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7571, "f_coverage": 0.7571, "f_balanced": 0.833, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 746, "chars": 2986, "content_recall": 0.7137, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7571, "f_coverage": 0.7571, "f_balanced": 0.833, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 552, "chars": 2211, "content_recall": 0.5344, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5892, "f_coverage": 0.5892, "f_balanced": 0.6965, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 388, "chars": 1552, "content_recall": 0.6832, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7294, "f_coverage": 0.7294, "f_balanced": 0.8118, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" }, "readability": { "method": "readability", "tokens": 62, "chars": 249, "content_recall": 0.0763, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0936, "f_coverage": 0.0936, "f_balanced": 0.1418, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2914, "chars": 11659, "content_recall": 0.7061, "noise_retention": 0.1906, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7246, "f_coverage": 0.7246, "f_balanced": 0.7542, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3050, "chars": 12200, "content_recall": 0.7061, "noise_retention": 0.1906, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7246, "f_coverage": 0.7246, "f_balanced": 0.7542, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1356, "chars": 5425, "content_recall": 0.7443, "noise_retention": 0.9901, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.047, "f_coverage": 0.047, "f_balanced": 0.0195, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2902, "chars": 11609, "content_recall": 0.7061, "noise_retention": 0.1906, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7246, "f_coverage": 0.7246, "f_balanced": 0.7542, "anchor_diag": { "content_chars": 2684, "noise_chars": 3093, "content_ngrams": 262, "noise_ngrams": 404, "ambiguous_ngrams_removed": 14, "content_sentences": 23 }, "notes": "" } }, "scoreable": true }, "tekton-docs": { "meta": { "id": "tekton-docs", "url": "https://tekton.dev/docs/", "requested_url": "https://tekton.dev/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 100452 } }, "anchors": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 336, "chars": 1346, "content_recall": 0.5565, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6107, "f_coverage": 0.6107, "f_balanced": 0.7151, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 386, "chars": 1544, "content_recall": 0.5913, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6439, "f_coverage": 0.6439, "f_balanced": 0.7432, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 247, "chars": 990, "content_recall": 0.4435, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.499, "f_coverage": 0.499, "f_balanced": 0.6145, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 265, "chars": 1060, "content_recall": 0.8522, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8781, "f_coverage": 0.8781, "f_balanced": 0.9202, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" }, "readability": { "method": "readability", "tokens": 279, "chars": 1118, "content_recall": 0.887, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9075, "f_coverage": 0.9075, "f_balanced": 0.9401, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2608, "chars": 10435, "content_recall": 0.5565, "noise_retention": 0.2561, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.383, "f_precision": 0.586, "f_coverage": 0.586, "f_balanced": 0.6367, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2996, "chars": 11984, "content_recall": 0.5565, "noise_retention": 0.2561, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.334, "f_precision": 0.586, "f_coverage": 0.586, "f_balanced": 0.6367, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1159, "chars": 4636, "content_recall": 0.6174, "noise_retention": 0.9677, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.863, "f_precision": 0.1337, "f_coverage": 0.1337, "f_balanced": 0.0615, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2855, "chars": 11422, "content_recall": 0.5565, "noise_retention": 0.2561, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.35, "f_precision": 0.586, "f_coverage": 0.586, "f_balanced": 0.6367, "anchor_diag": { "content_chars": 971, "noise_chars": 6013, "content_ngrams": 115, "noise_ngrams": 371, "ambiguous_ngrams_removed": 0, "content_sentences": 14 }, "notes": "" } }, "scoreable": true }, "telegram-api": { "meta": { "id": "telegram-api", "url": "https://core.telegram.org/bots/api", "requested_url": "https://core.telegram.org/bots/api", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 860075 } }, "anchors": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 153485, "chars": 613941, "content_recall": 0.7008, "noise_retention": 0.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.026, "f_precision": 0.7454, "f_coverage": 0.7454, "f_balanced": 0.8241, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 154987, "chars": 619948, "content_recall": 0.7107, "noise_retention": 0.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.026, "f_precision": 0.7544, "f_coverage": 0.7544, "f_balanced": 0.8309, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 147075, "chars": 588302, "content_recall": 0.6367, "noise_retention": 0.0, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.027, "f_precision": 0.6866, "f_coverage": 0.6866, "f_balanced": 0.778, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 123187, "chars": 492750, "content_recall": 0.7031, "noise_retention": 0.0, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.041, "f_precision": 0.7475, "f_coverage": 0.7475, "f_balanced": 0.8257, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" }, "readability": { "method": "readability", "tokens": 120860, "chars": 483440, "content_recall": 0.7158, "noise_retention": 0.0, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.041, "f_precision": 0.7589, "f_coverage": 0.7589, "f_balanced": 0.8343, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 147927, "chars": 591709, "content_recall": 0.6872, "noise_retention": 0.0, "noise_keyword_total": 26, "noise_per_1k_tokens": 0.176, "f_precision": 0.7331, "f_coverage": 0.7331, "f_balanced": 0.8146, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 138847, "chars": 555389, "content_recall": 0.7172, "noise_retention": 0.0, "noise_keyword_total": 26, "noise_per_1k_tokens": 0.187, "f_precision": 0.7602, "f_coverage": 0.7602, "f_balanced": 0.8353, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 123034, "chars": 492139, "content_recall": 0.7277, "noise_retention": 0.0, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.041, "f_precision": 0.7696, "f_coverage": 0.7696, "f_balanced": 0.8424, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 148963, "chars": 595853, "content_recall": 0.6865, "noise_retention": 0.0, "noise_keyword_total": 26, "noise_per_1k_tokens": 0.175, "f_precision": 0.7324, "f_coverage": 0.7324, "f_balanced": 0.8141, "anchor_diag": { "content_chars": 384807, "noise_chars": 0, "content_ngrams": 30499, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 3831 }, "notes": "" } }, "scoreable": true }, "tensorflow-docs": { "meta": { "id": "tensorflow-docs", "url": "https://www.tensorflow.org/guide", "requested_url": "https://www.tensorflow.org/guide", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 145093 } }, "anchors": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 900, "chars": 3603, "content_recall": 0.7434, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7836, "f_coverage": 0.7836, "f_balanced": 0.8528, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 908, "chars": 3633, "content_recall": 0.741, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7815, "f_coverage": 0.7815, "f_balanced": 0.8512, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 900, "chars": 3603, "content_recall": 0.7434, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7836, "f_coverage": 0.7836, "f_balanced": 0.8528, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 771, "chars": 3086, "content_recall": 0.4916, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5473, "f_coverage": 0.5473, "f_balanced": 0.6592, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "readability": { "method": "readability", "tokens": 249, "chars": 999, "content_recall": 0.1799, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2151, "f_coverage": 0.2151, "f_balanced": 0.3049, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3643, "chars": 14572, "content_recall": 0.6067, "noise_retention": 0.2577, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.372, "f_precision": 0.6297, "f_coverage": 0.6297, "f_balanced": 0.6677, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3808, "chars": 15233, "content_recall": 0.6067, "noise_retention": 0.2577, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.313, "f_precision": 0.6297, "f_coverage": 0.6297, "f_balanced": 0.6677, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1804, "chars": 7219, "content_recall": 0.7722, "noise_retention": 0.9097, "noise_keyword_total": 4, "noise_per_1k_tokens": 2.217, "f_precision": 0.3076, "f_coverage": 0.3076, "f_balanced": 0.1617, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3629, "chars": 14516, "content_recall": 0.6067, "noise_retention": 0.2577, "noise_keyword_total": 5, "noise_per_1k_tokens": 1.378, "f_precision": 0.6297, "f_coverage": 0.6297, "f_balanced": 0.6677, "anchor_diag": { "content_chars": 4269, "noise_chars": 6049, "content_ngrams": 417, "noise_ngrams": 454, "ambiguous_ngrams_removed": 0, "content_sentences": 42 }, "notes": "" } }, "scoreable": true }, "terraform-aws": { "meta": { "id": "terraform-aws", "url": "https://registry.terraform.io/providers/hashicorp/aws/latest/docs", "requested_url": "https://registry.terraform.io/providers/hashicorp/aws/latest/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 8523 } }, "anchors": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 26, "chars": 107, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 26, "chars": 107, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 26, "chars": 107, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 14, "chars": 57, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "readability": { "method": "readability", "tokens": 5, "chars": 23, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 21, "chars": 87, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 16, "chars": 67, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 4, "chars": 18, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 15, "chars": 63, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 0, "noise_chars": 0, "content_ngrams": 0, "noise_ngrams": 0, "ambiguous_ngrams_removed": 0, "content_sentences": 0 }, "notes": "" } }, "scoreable": false }, "thrift-docs": { "meta": { "id": "thrift-docs", "url": "https://thrift.apache.org/docs/", "requested_url": "https://thrift.apache.org/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 5671 } }, "anchors": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 222, "chars": 889, "content_recall": 0.7071, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7511, "f_coverage": 0.7511, "f_balanced": 0.8284, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 222, "chars": 889, "content_recall": 0.7071, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7511, "f_coverage": 0.7511, "f_balanced": 0.8284, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 222, "chars": 889, "content_recall": 0.7071, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7511, "f_coverage": 0.7511, "f_balanced": 0.8284, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 151, "chars": 606, "content_recall": 0.7374, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7783, "f_coverage": 0.7783, "f_balanced": 0.8488, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" }, "readability": { "method": "readability", "tokens": 176, "chars": 704, "content_recall": 0.7374, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7783, "f_coverage": 0.7783, "f_balanced": 0.8488, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 611, "chars": 2444, "content_recall": 0.7374, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7783, "f_coverage": 0.7783, "f_balanced": 0.8488, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 621, "chars": 2486, "content_recall": 0.7374, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7783, "f_coverage": 0.7783, "f_balanced": 0.8488, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 337, "chars": 1350, "content_recall": 0.8384, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8664, "f_coverage": 0.8664, "f_balanced": 0.9121, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 601, "chars": 2404, "content_recall": 0.7374, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7783, "f_coverage": 0.7783, "f_balanced": 0.8488, "anchor_diag": { "content_chars": 1032, "noise_chars": 291, "content_ngrams": 99, "noise_ngrams": 0, "ambiguous_ngrams_removed": 33, "content_sentences": 9 }, "notes": "" } }, "scoreable": true }, "trafilatura-docs": { "meta": { "id": "trafilatura-docs", "url": "https://trafilatura.readthedocs.io/en/latest/", "requested_url": "https://trafilatura.readthedocs.io/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 46279 } }, "anchors": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1598, "chars": 6394, "content_recall": 0.548, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6025, "f_coverage": 0.6025, "f_balanced": 0.708, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1704, "chars": 6818, "content_recall": 0.5841, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6371, "f_coverage": 0.6371, "f_balanced": 0.7374, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1482, "chars": 5930, "content_recall": 0.5197, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5749, "f_coverage": 0.5749, "f_balanced": 0.6839, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1243, "chars": 4972, "content_recall": 0.5655, "noise_retention": 0.0135, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6183, "f_coverage": 0.6183, "f_balanced": 0.7189, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1074, "chars": 4296, "content_recall": 0.5197, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5749, "f_coverage": 0.5749, "f_balanced": 0.6839, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3899, "chars": 15598, "content_recall": 0.6572, "noise_retention": 0.1351, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6904, "f_coverage": 0.6904, "f_balanced": 0.7469, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3824, "chars": 15296, "content_recall": 0.6561, "noise_retention": 0.3243, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6599, "f_coverage": 0.6599, "f_balanced": 0.6658, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2110, "chars": 8442, "content_recall": 0.8614, "noise_retention": 0.7838, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5394, "f_coverage": 0.5394, "f_balanced": 0.3457, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3870, "chars": 15483, "content_recall": 0.6572, "noise_retention": 0.1351, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6904, "f_coverage": 0.6904, "f_balanced": 0.7469, "anchor_diag": { "content_chars": 10331, "noise_chars": 1031, "content_ngrams": 916, "noise_ngrams": 74, "ambiguous_ngrams_removed": 4, "content_sentences": 73 }, "notes": "" } }, "scoreable": true }, "twilio-docs-sms": { "meta": { "id": "twilio-docs-sms", "url": "https://www.twilio.com/docs/messaging", "requested_url": "https://www.twilio.com/docs/sms", "category": "api_docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 280032 } }, "anchors": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 817, "chars": 3270, "content_recall": 0.5558, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.61, "f_coverage": 0.61, "f_balanced": 0.7145, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 828, "chars": 3315, "content_recall": 0.5702, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6239, "f_coverage": 0.6239, "f_balanced": 0.7263, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 397, "chars": 1590, "content_recall": 0.2273, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2688, "f_coverage": 0.2688, "f_balanced": 0.3704, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 590, "chars": 2362, "content_recall": 0.4814, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.695, "f_precision": 0.5371, "f_coverage": 0.5371, "f_balanced": 0.6499, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" }, "readability": { "method": "readability", "tokens": 103, "chars": 413, "content_recall": 0.0826, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1012, "f_coverage": 0.1012, "f_balanced": 0.1527, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4992, "chars": 19971, "content_recall": 0.655, "noise_retention": 0.3956, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.601, "f_precision": 0.6442, "f_coverage": 0.6442, "f_balanced": 0.6287, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5025, "chars": 20101, "content_recall": 0.655, "noise_retention": 0.3956, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.597, "f_precision": 0.6442, "f_coverage": 0.6442, "f_balanced": 0.6287, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2232, "chars": 8930, "content_recall": 0.7066, "noise_retention": 0.8787, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.344, "f_precision": 0.3595, "f_coverage": 0.3595, "f_balanced": 0.207, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4981, "chars": 19926, "content_recall": 0.655, "noise_retention": 0.3956, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.602, "f_precision": 0.6442, "f_coverage": 0.6442, "f_balanced": 0.6287, "anchor_diag": { "content_chars": 5441, "noise_chars": 7763, "content_ngrams": 484, "noise_ngrams": 503, "ambiguous_ngrams_removed": 1, "content_sentences": 59 }, "notes": "" } }, "scoreable": true }, "twilio-docs": { "meta": { "id": "twilio-docs", "url": "https://www.twilio.com/docs", "requested_url": "https://www.twilio.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 230471 } }, "anchors": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1954, "chars": 7819, "content_recall": 0.9137, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9297, "f_coverage": 0.9297, "f_balanced": 0.9549, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1954, "chars": 7819, "content_recall": 0.9137, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9297, "f_coverage": 0.9297, "f_balanced": 0.9549, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 653, "chars": 2615, "content_recall": 0.2566, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3014, "f_coverage": 0.3014, "f_balanced": 0.4084, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1065, "chars": 4263, "content_recall": 0.5755, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6289, "f_coverage": 0.6289, "f_balanced": 0.7306, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1063, "chars": 4255, "content_recall": 0.5324, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5873, "f_coverage": 0.5873, "f_balanced": 0.6948, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3470, "chars": 13882, "content_recall": 0.6787, "noise_retention": 0.1643, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.576, "f_precision": 0.7052, "f_coverage": 0.7052, "f_balanced": 0.749, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3412, "chars": 13649, "content_recall": 0.6691, "noise_retention": 0.1643, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.586, "f_precision": 0.6969, "f_coverage": 0.6969, "f_balanced": 0.7432, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2508, "chars": 10034, "content_recall": 0.6942, "noise_retention": 0.7571, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.797, "f_precision": 0.5061, "f_coverage": 0.5061, "f_balanced": 0.3598, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3456, "chars": 13824, "content_recall": 0.6787, "noise_retention": 0.1643, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.579, "f_precision": 0.7052, "f_coverage": 0.7052, "f_balanced": 0.749, "anchor_diag": { "content_chars": 6832, "noise_chars": 1879, "content_ngrams": 834, "noise_ngrams": 140, "ambiguous_ngrams_removed": 0, "content_sentences": 69 }, "notes": "" } }, "scoreable": true }, "twilio-segment": { "meta": { "id": "twilio-segment", "url": "https://www.twilio.com/docs/segment", "requested_url": "https://segment.com/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 228478 } }, "anchors": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 502, "chars": 2008, "content_recall": 0.5691, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6228, "f_coverage": 0.6228, "f_balanced": 0.7254, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 522, "chars": 2090, "content_recall": 0.5813, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6344, "f_coverage": 0.6344, "f_balanced": 0.7352, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 246, "chars": 984, "content_recall": 0.2561, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3009, "f_coverage": 0.3009, "f_balanced": 0.4078, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 343, "chars": 1375, "content_recall": 0.5244, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.915, "f_precision": 0.5795, "f_coverage": 0.5795, "f_balanced": 0.688, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" }, "readability": { "method": "readability", "tokens": 62, "chars": 248, "content_recall": 0.0691, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0849, "f_coverage": 0.0849, "f_balanced": 0.1293, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3263, "chars": 13054, "content_recall": 0.5447, "noise_retention": 0.3016, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.919, "f_precision": 0.5698, "f_coverage": 0.5698, "f_balanced": 0.612, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3276, "chars": 13107, "content_recall": 0.5447, "noise_retention": 0.3016, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.916, "f_precision": 0.5698, "f_coverage": 0.5698, "f_balanced": 0.612, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1413, "chars": 5655, "content_recall": 0.6504, "noise_retention": 0.9536, "noise_keyword_total": 3, "noise_per_1k_tokens": 2.123, "f_precision": 0.1805, "f_coverage": 0.1805, "f_balanced": 0.0866, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3253, "chars": 13015, "content_recall": 0.5447, "noise_retention": 0.3016, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.922, "f_precision": 0.5698, "f_coverage": 0.5698, "f_balanced": 0.612, "anchor_diag": { "content_chars": 2521, "noise_chars": 6504, "content_ngrams": 246, "noise_ngrams": 431, "ambiguous_ngrams_removed": 0, "content_sentences": 26 }, "notes": "" } }, "scoreable": true }, "twilio-verify": { "meta": { "id": "twilio-verify", "url": "https://www.twilio.com/docs/verify", "requested_url": "https://www.twilio.com/docs/verify", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 331912 } }, "anchors": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 821, "chars": 3286, "content_recall": 0.5491, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6035, "f_coverage": 0.6035, "f_balanced": 0.7089, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 838, "chars": 3352, "content_recall": 0.5531, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6074, "f_coverage": 0.6074, "f_balanced": 0.7123, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 425, "chars": 1701, "content_recall": 0.2465, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2902, "f_coverage": 0.2902, "f_balanced": 0.3955, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 595, "chars": 2382, "content_recall": 0.4309, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.681, "f_precision": 0.4862, "f_coverage": 0.4862, "f_balanced": 0.6022, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" }, "readability": { "method": "readability", "tokens": 156, "chars": 625, "content_recall": 0.1383, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1671, "f_coverage": 0.1671, "f_balanced": 0.243, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3304, "chars": 13217, "content_recall": 0.7114, "noise_retention": 0.2978, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.211, "f_precision": 0.7096, "f_coverage": 0.7096, "f_balanced": 0.7068, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3422, "chars": 13688, "content_recall": 0.7114, "noise_retention": 0.2978, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.169, "f_precision": 0.7096, "f_coverage": 0.7096, "f_balanced": 0.7068, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1722, "chars": 6890, "content_recall": 0.6693, "noise_retention": 0.9118, "noise_keyword_total": 4, "noise_per_1k_tokens": 2.323, "f_precision": 0.2889, "f_coverage": 0.2889, "f_balanced": 0.1559, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3288, "chars": 13154, "content_recall": 0.7114, "noise_retention": 0.2978, "noise_keyword_total": 4, "noise_per_1k_tokens": 1.217, "f_precision": 0.7096, "f_coverage": 0.7096, "f_balanced": 0.7068, "anchor_diag": { "content_chars": 6041, "noise_chars": 3897, "content_ngrams": 499, "noise_ngrams": 272, "ambiguous_ngrams_removed": 3, "content_sentences": 53 }, "notes": "" } }, "scoreable": true }, "twilio-voice": { "meta": { "id": "twilio-voice", "url": "https://www.twilio.com/docs/voice", "requested_url": "https://www.twilio.com/docs/voice", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 256122 } }, "anchors": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 835, "chars": 3342, "content_recall": 0.6712, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7184, "f_coverage": 0.7184, "f_balanced": 0.8033, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 835, "chars": 3342, "content_recall": 0.6712, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7184, "f_coverage": 0.7184, "f_balanced": 0.8033, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 348, "chars": 1394, "content_recall": 0.2268, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2682, "f_coverage": 0.2682, "f_balanced": 0.3697, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 428, "chars": 1714, "content_recall": 0.4286, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.336, "f_precision": 0.4839, "f_coverage": 0.4839, "f_balanced": 0.6, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" }, "readability": { "method": "readability", "tokens": 84, "chars": 338, "content_recall": 0.0816, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1, "f_coverage": 0.1, "f_balanced": 0.1509, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3984, "chars": 15936, "content_recall": 0.7007, "noise_retention": 0.3226, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.753, "f_precision": 0.6959, "f_coverage": 0.6959, "f_balanced": 0.6889, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4006, "chars": 16026, "content_recall": 0.6463, "noise_retention": 0.3226, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.749, "f_precision": 0.6523, "f_coverage": 0.6523, "f_balanced": 0.6615, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1769, "chars": 7078, "content_recall": 0.78, "noise_retention": 0.9447, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.696, "f_precision": 0.2154, "f_coverage": 0.2154, "f_balanced": 0.1033, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3972, "chars": 15889, "content_recall": 0.7007, "noise_retention": 0.3226, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.755, "f_precision": 0.6959, "f_coverage": 0.6959, "f_balanced": 0.6889, "anchor_diag": { "content_chars": 4370, "noise_chars": 7057, "content_ngrams": 441, "noise_ngrams": 434, "ambiguous_ngrams_removed": 4, "content_sentences": 37 }, "notes": "" } }, "scoreable": true }, "typescript-docs": { "meta": { "id": "typescript-docs", "url": "https://www.typescriptlang.org/docs/", "requested_url": "https://www.typescriptlang.org/docs/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 170589 } }, "anchors": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 240, "chars": 961, "content_recall": 0.2222, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2632, "f_coverage": 0.2632, "f_balanced": 0.3636, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 257, "chars": 1028, "content_recall": 0.2222, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2632, "f_coverage": 0.2632, "f_balanced": 0.3636, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 166, "chars": 664, "content_recall": 0.0808, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.099, "f_coverage": 0.099, "f_balanced": 0.1495, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 171, "chars": 686, "content_recall": 0.2222, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2632, "f_coverage": 0.2632, "f_balanced": 0.3636, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "readability": { "method": "readability", "tokens": 14, "chars": 59, "content_recall": 0.0, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0, "f_coverage": 0.0, "f_balanced": 0.0, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3229, "chars": 12919, "content_recall": 0.2525, "noise_retention": 0.2671, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.31, "f_precision": 0.2906, "f_coverage": 0.2906, "f_balanced": 0.3756, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3288, "chars": 13154, "content_recall": 0.2525, "noise_retention": 0.274, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.304, "f_precision": 0.2904, "f_coverage": 0.2904, "f_balanced": 0.3747, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 900, "chars": 3603, "content_recall": 0.5354, "noise_retention": 0.9452, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1944, "f_coverage": 0.1944, "f_balanced": 0.0994, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2300, "chars": 9203, "content_recall": 0.2525, "noise_retention": 0.2671, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.435, "f_precision": 0.2906, "f_coverage": 0.2906, "f_balanced": 0.3756, "anchor_diag": { "content_chars": 882, "noise_chars": 1200, "content_ngrams": 99, "noise_ngrams": 146, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" } }, "scoreable": true }, "typescript-handbook": { "meta": { "id": "typescript-handbook", "url": "https://www.typescriptlang.org/docs/handbook/intro.html", "requested_url": "https://www.typescriptlang.org/docs/handbook/intro.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 196232 } }, "anchors": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1286, "chars": 5146, "content_recall": 0.89, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.91, "f_coverage": 0.91, "f_balanced": 0.9418, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1310, "chars": 5243, "content_recall": 0.89, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.91, "f_coverage": 0.91, "f_balanced": 0.9418, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1023, "chars": 4093, "content_recall": 0.7011, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7457, "f_coverage": 0.7457, "f_balanced": 0.8243, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1198, "chars": 4792, "content_recall": 0.9409, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9521, "f_coverage": 0.9521, "f_balanced": 0.9695, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1159, "chars": 4639, "content_recall": 0.9097, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9264, "f_coverage": 0.9264, "f_balanced": 0.9527, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5225, "chars": 20902, "content_recall": 0.9228, "noise_retention": 0.1483, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.191, "f_precision": 0.9077, "f_coverage": 0.9077, "f_balanced": 0.8859, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5278, "chars": 21112, "content_recall": 0.9179, "noise_retention": 0.1657, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.189, "f_precision": 0.8999, "f_coverage": 0.8999, "f_balanced": 0.8741, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2127, "chars": 8510, "content_recall": 0.9721, "noise_retention": 0.9419, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2346, "f_coverage": 0.2346, "f_balanced": 0.1097, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4295, "chars": 17180, "content_recall": 0.9228, "noise_retention": 0.1483, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.233, "f_precision": 0.9077, "f_coverage": 0.9077, "f_balanced": 0.8859, "anchor_diag": { "content_chars": 6059, "noise_chars": 3604, "content_ngrams": 609, "noise_ngrams": 344, "ambiguous_ngrams_removed": 3, "content_sentences": 45 }, "notes": "" } }, "scoreable": true }, "ubuntu-server": { "meta": { "id": "ubuntu-server", "url": "https://ubuntu.com/server/docs/", "requested_url": "https://ubuntu.com/server/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 90559 } }, "anchors": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 876, "chars": 3507, "content_recall": 0.3634, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4164, "f_coverage": 0.4164, "f_balanced": 0.5331, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1111, "chars": 4447, "content_recall": 0.4841, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5398, "f_coverage": 0.5398, "f_balanced": 0.6524, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 737, "chars": 2948, "content_recall": 0.3236, "noise_retention": 0.0128, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3739, "f_coverage": 0.3739, "f_balanced": 0.4874, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1371, "chars": 5487, "content_recall": 0.7268, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7688, "f_coverage": 0.7688, "f_balanced": 0.8418, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" }, "readability": { "method": "readability", "tokens": 683, "chars": 2733, "content_recall": 0.3475, "noise_retention": 0.0256, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3988, "f_coverage": 0.3988, "f_balanced": 0.5123, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 7990, "chars": 31962, "content_recall": 0.4536, "noise_retention": 0.3462, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4832, "f_coverage": 0.4832, "f_balanced": 0.5356, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 7948, "chars": 31793, "content_recall": 0.4642, "noise_retention": 0.5, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4709, "f_coverage": 0.4709, "f_balanced": 0.4814, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2896, "chars": 11584, "content_recall": 0.7308, "noise_retention": 0.859, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3979, "f_coverage": 0.3979, "f_balanced": 0.2364, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 8006, "chars": 32027, "content_recall": 0.4536, "noise_retention": 0.3462, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4832, "f_coverage": 0.4832, "f_balanced": 0.5356, "anchor_diag": { "content_chars": 7678, "noise_chars": 624, "content_ngrams": 754, "noise_ngrams": 78, "ambiguous_ngrams_removed": 0, "content_sentences": 93 }, "notes": "" } }, "scoreable": true }, "umami-docs": { "meta": { "id": "umami-docs", "url": "https://docs.umami.is/docs", "requested_url": "https://umami.is/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 70677 } }, "anchors": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 655, "chars": 2620, "content_recall": 0.8343, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.527, "f_precision": 0.8629, "f_coverage": 0.8629, "f_balanced": 0.9097, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 664, "chars": 2659, "content_recall": 0.8434, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.506, "f_precision": 0.8706, "f_coverage": 0.8706, "f_balanced": 0.915, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 449, "chars": 1797, "content_recall": 0.506, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.227, "f_precision": 0.5615, "f_coverage": 0.5615, "f_balanced": 0.672, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 489, "chars": 1959, "content_recall": 0.6837, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.045, "f_precision": 0.7299, "f_coverage": 0.7299, "f_balanced": 0.8122, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" }, "readability": { "method": "readability", "tokens": 485, "chars": 1941, "content_recall": 0.6837, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 2.062, "f_precision": 0.7299, "f_coverage": 0.7299, "f_balanced": 0.8122, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1360, "chars": 5442, "content_recall": 0.6596, "noise_retention": 0.2692, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.735, "f_precision": 0.6727, "f_coverage": 0.6727, "f_balanced": 0.6934, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1333, "chars": 5333, "content_recall": 0.6054, "noise_retention": 0.0385, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.75, "f_precision": 0.6539, "f_coverage": 0.6539, "f_balanced": 0.743, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 847, "chars": 3389, "content_recall": 0.8584, "noise_retention": 0.5385, "noise_keyword_total": 1, "noise_per_1k_tokens": 1.181, "f_precision": 0.7325, "f_coverage": 0.7325, "f_balanced": 0.6003, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1354, "chars": 5418, "content_recall": 0.6596, "noise_retention": 0.2692, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.739, "f_precision": 0.6727, "f_coverage": 0.6727, "f_balanced": 0.6934, "anchor_diag": { "content_chars": 3370, "noise_chars": 921, "content_ngrams": 332, "noise_ngrams": 26, "ambiguous_ngrams_removed": 85, "content_sentences": 28 }, "notes": "" } }, "scoreable": true }, "uv-docs": { "meta": { "id": "uv-docs", "url": "https://docs.astral.sh/uv/", "requested_url": "https://docs.astral.sh/uv/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 83236 } }, "anchors": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1404, "chars": 5619, "content_recall": 0.6644, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7122, "f_coverage": 0.7122, "f_balanced": 0.7984, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1534, "chars": 6136, "content_recall": 0.7095, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7533, "f_coverage": 0.7533, "f_balanced": 0.8301, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 827, "chars": 3309, "content_recall": 0.3823, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4362, "f_coverage": 0.4362, "f_balanced": 0.5531, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1311, "chars": 5245, "content_recall": 0.8013, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8345, "f_coverage": 0.8345, "f_balanced": 0.8897, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1241, "chars": 4965, "content_recall": 0.8698, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.893, "f_coverage": 0.893, "f_balanced": 0.9304, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2895, "chars": 11580, "content_recall": 0.7479, "noise_retention": 0.0724, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7781, "f_coverage": 0.7781, "f_balanced": 0.8281, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3058, "chars": 12234, "content_recall": 0.7629, "noise_retention": 0.0814, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7897, "f_coverage": 0.7897, "f_balanced": 0.8335, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1739, "chars": 6958, "content_recall": 0.8397, "noise_retention": 0.7647, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5547, "f_coverage": 0.5547, "f_balanced": 0.3676, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2918, "chars": 11675, "content_recall": 0.7479, "noise_retention": 0.0724, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7781, "f_coverage": 0.7781, "f_balanced": 0.8281, "anchor_diag": { "content_chars": 7503, "noise_chars": 4022, "content_ngrams": 599, "noise_ngrams": 221, "ambiguous_ngrams_removed": 10, "content_sentences": 62 }, "notes": "" } }, "scoreable": true }, "vercel-docs": { "meta": { "id": "vercel-docs", "url": "https://vercel.com/docs", "requested_url": "https://vercel.com/docs", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 844649 } }, "anchors": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1628, "chars": 6515, "content_recall": 0.7258, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7679, "f_coverage": 0.7679, "f_balanced": 0.8411, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1700, "chars": 6802, "content_recall": 0.7587, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7972, "f_coverage": 0.7972, "f_balanced": 0.8628, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1261, "chars": 5046, "content_recall": 0.5671, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6209, "f_coverage": 0.6209, "f_balanced": 0.7238, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1620, "chars": 6481, "content_recall": 0.7211, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7637, "f_coverage": 0.7637, "f_balanced": 0.838, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" }, "readability": { "method": "readability", "tokens": 983, "chars": 3932, "content_recall": 0.4854, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5411, "f_coverage": 0.5411, "f_balanced": 0.6536, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4301, "chars": 17206, "content_recall": 0.6554, "noise_retention": 0.0233, "noise_keyword_total": 8, "noise_per_1k_tokens": 1.86, "f_precision": 0.7016, "f_coverage": 0.7016, "f_balanced": 0.7844, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4376, "chars": 17506, "content_recall": 0.5756, "noise_retention": 0.0233, "noise_keyword_total": 8, "noise_per_1k_tokens": 1.828, "f_precision": 0.6271, "f_coverage": 0.6271, "f_balanced": 0.7243, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2563, "chars": 10254, "content_recall": 0.8254, "noise_retention": 0.9256, "noise_keyword_total": 6, "noise_per_1k_tokens": 2.341, "f_precision": 0.2735, "f_coverage": 0.2735, "f_balanced": 0.1365, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4296, "chars": 17184, "content_recall": 0.6554, "noise_retention": 0.0233, "noise_keyword_total": 8, "noise_per_1k_tokens": 1.862, "f_precision": 0.7016, "f_coverage": 0.7016, "f_balanced": 0.7844, "anchor_diag": { "content_chars": 12199, "noise_chars": 5287, "content_ngrams": 1065, "noise_ngrams": 215, "ambiguous_ngrams_removed": 118, "content_sentences": 96 }, "notes": "" } }, "scoreable": true }, "vite-docs": { "meta": { "id": "vite-docs", "url": "https://vite.dev/guide/", "requested_url": "https://vitejs.dev/guide/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 89758 } }, "anchors": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2538, "chars": 10152, "content_recall": 0.7905, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8251, "f_coverage": 0.8251, "f_balanced": 0.883, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2547, "chars": 10189, "content_recall": 0.7951, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.829, "f_coverage": 0.829, "f_balanced": 0.8858, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2174, "chars": 8696, "content_recall": 0.6468, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.696, "f_coverage": 0.696, "f_balanced": 0.7856, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2110, "chars": 8441, "content_recall": 0.8801, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9018, "f_coverage": 0.9018, "f_balanced": 0.9363, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1739, "chars": 6956, "content_recall": 0.785, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8203, "f_coverage": 0.8203, "f_balanced": 0.8795, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3883, "chars": 15532, "content_recall": 0.7887, "noise_retention": 0.064, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8143, "f_coverage": 0.8143, "f_balanced": 0.856, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3923, "chars": 15695, "content_recall": 0.7887, "noise_retention": 0.064, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8143, "f_coverage": 0.8143, "f_balanced": 0.856, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2414, "chars": 9658, "content_recall": 0.8719, "noise_retention": 0.84, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4614, "f_coverage": 0.4614, "f_balanced": 0.2704, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3587, "chars": 14350, "content_recall": 0.7887, "noise_retention": 0.064, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8143, "f_coverage": 0.8143, "f_balanced": 0.856, "anchor_diag": { "content_chars": 8617, "noise_chars": 1810, "content_ngrams": 1093, "noise_ngrams": 125, "ambiguous_ngrams_removed": 0, "content_sentences": 94 }, "notes": "" } }, "scoreable": true }, "vitest-docs": { "meta": { "id": "vitest-docs", "url": "https://vitest.dev/guide/", "requested_url": "https://vitest.dev/guide/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": true, "bytes": 75244 } }, "anchors": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1208, "chars": 4834, "content_recall": 0.7696, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8068, "f_coverage": 0.8068, "f_balanced": 0.8698, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1220, "chars": 4883, "content_recall": 0.772, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8089, "f_coverage": 0.8089, "f_balanced": 0.8713, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1050, "chars": 4200, "content_recall": 0.6793, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7259, "f_coverage": 0.7259, "f_balanced": 0.8091, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 987, "chars": 3949, "content_recall": 0.8575, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8826, "f_coverage": 0.8826, "f_balanced": 0.9233, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" }, "readability": { "method": "readability", "tokens": 798, "chars": 3195, "content_recall": 0.8171, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8481, "f_coverage": 0.8481, "f_balanced": 0.8993, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2943, "chars": 11774, "content_recall": 0.8052, "noise_retention": 0.1081, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8212, "f_coverage": 0.8212, "f_balanced": 0.8463, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2975, "chars": 11903, "content_recall": 0.8052, "noise_retention": 0.1081, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8212, "f_coverage": 0.8212, "f_balanced": 0.8463, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1410, "chars": 5643, "content_recall": 0.8432, "noise_retention": 0.9099, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3156, "f_coverage": 0.3156, "f_balanced": 0.1628, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2934, "chars": 11737, "content_recall": 0.8052, "noise_retention": 0.1081, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8212, "f_coverage": 0.8212, "f_balanced": 0.8463, "anchor_diag": { "content_chars": 3420, "noise_chars": 3303, "content_ngrams": 421, "noise_ngrams": 222, "ambiguous_ngrams_removed": 0, "content_sentences": 33 }, "notes": "" } }, "scoreable": true }, "vue-docs": { "meta": { "id": "vue-docs", "url": "https://vuejs.org/guide/introduction.html", "requested_url": "https://vuejs.org/guide/introduction.html", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 114346 } }, "anchors": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 2389, "chars": 9557, "content_recall": 0.8434, "noise_retention": 0.013, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8687, "f_coverage": 0.8687, "f_balanced": 0.9096, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 2435, "chars": 9743, "content_recall": 0.8562, "noise_retention": 0.013, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8795, "f_coverage": 0.8795, "f_balanced": 0.9169, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1927, "chars": 7711, "content_recall": 0.7166, "noise_retention": 0.013, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7581, "f_coverage": 0.7581, "f_balanced": 0.8303, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 2113, "chars": 8453, "content_recall": 0.834, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8627, "f_coverage": 0.8627, "f_balanced": 0.9095, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" }, "readability": { "method": "readability", "tokens": 2053, "chars": 8212, "content_recall": 0.7949, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8289, "f_coverage": 0.8289, "f_balanced": 0.8857, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 4258, "chars": 17032, "content_recall": 0.8715, "noise_retention": 0.1342, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.705, "f_precision": 0.8703, "f_coverage": 0.8703, "f_balanced": 0.8686, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 4527, "chars": 18110, "content_recall": 0.8604, "noise_retention": 0.1645, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.663, "f_precision": 0.8553, "f_coverage": 0.8553, "f_balanced": 0.8478, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2770, "chars": 11081, "content_recall": 0.8953, "noise_retention": 0.9307, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.722, "f_precision": 0.2645, "f_coverage": 0.2645, "f_balanced": 0.1286, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 4250, "chars": 17003, "content_recall": 0.8715, "noise_retention": 0.1342, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.706, "f_precision": 0.8703, "f_coverage": 0.8703, "f_balanced": 0.8686, "anchor_diag": { "content_chars": 11660, "noise_chars": 3529, "content_ngrams": 1175, "noise_ngrams": 231, "ambiguous_ngrams_removed": 1, "content_sentences": 104 }, "notes": "" } }, "scoreable": true }, "vultr-docs": { "meta": { "id": "vultr-docs", "url": "https://docs.vultr.com/", "requested_url": "https://docs.vultr.com/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 214359 } }, "anchors": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 941, "chars": 3764, "content_recall": 0.7587, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7972, "f_coverage": 0.7972, "f_balanced": 0.8628, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 941, "chars": 3764, "content_recall": 0.7587, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7972, "f_coverage": 0.7972, "f_balanced": 0.8628, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 941, "chars": 3764, "content_recall": 0.7587, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7972, "f_coverage": 0.7972, "f_balanced": 0.8628, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 123, "chars": 495, "content_recall": 0.083, "noise_retention": 0.0897, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.1015, "f_coverage": 0.1015, "f_balanced": 0.1521, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "readability": { "method": "readability", "tokens": 397, "chars": 1591, "content_recall": 0.332, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3832, "f_coverage": 0.3832, "f_balanced": 0.4986, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3328, "chars": 13314, "content_recall": 0.7085, "noise_retention": 0.2115, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.803, "f_precision": 0.7232, "f_coverage": 0.7232, "f_balanced": 0.7463, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3469, "chars": 13877, "content_recall": 0.5792, "noise_retention": 0.2115, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.73, "f_precision": 0.6116, "f_coverage": 0.6116, "f_balanced": 0.6678, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1302, "chars": 5208, "content_recall": 0.8456, "noise_retention": 0.8974, "noise_keyword_total": 4, "noise_per_1k_tokens": 3.072, "f_precision": 0.3453, "f_coverage": 0.3453, "f_balanced": 0.1829, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 3314, "chars": 13258, "content_recall": 0.7085, "noise_retention": 0.2115, "noise_keyword_total": 6, "noise_per_1k_tokens": 1.811, "f_precision": 0.7232, "f_coverage": 0.7232, "f_balanced": 0.7463, "anchor_diag": { "content_chars": 7109, "noise_chars": 1322, "content_ngrams": 518, "noise_ngrams": 156, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" } }, "scoreable": true }, "weaviate-docs": { "meta": { "id": "weaviate-docs", "url": "https://docs.weaviate.io/weaviate", "requested_url": "https://weaviate.io/developers/weaviate", "category": "docs", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": false, "bytes": 39316 } }, "anchors": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1056, "chars": 4224, "content_recall": 0.6904, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.736, "f_coverage": 0.736, "f_balanced": 0.8169, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1142, "chars": 4570, "content_recall": 0.752, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7913, "f_coverage": 0.7913, "f_balanced": 0.8585, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 753, "chars": 3013, "content_recall": 0.4538, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5095, "f_coverage": 0.5095, "f_balanced": 0.6243, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 958, "chars": 3833, "content_recall": 0.6775, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7242, "f_coverage": 0.7242, "f_balanced": 0.8077, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" }, "readability": { "method": "readability", "tokens": 89, "chars": 356, "content_recall": 0.0616, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.0758, "f_coverage": 0.0758, "f_balanced": 0.116, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 2167, "chars": 8671, "content_recall": 0.6921, "noise_retention": 0.0984, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7258, "f_coverage": 0.7258, "f_balanced": 0.7831, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 2089, "chars": 8358, "content_recall": 0.6921, "noise_retention": 0.0984, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7258, "f_coverage": 0.7258, "f_balanced": 0.7831, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 1447, "chars": 5791, "content_recall": 0.8152, "noise_retention": 0.6721, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6284, "f_coverage": 0.6284, "f_balanced": 0.4677, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 2128, "chars": 8512, "content_recall": 0.6921, "noise_retention": 0.0984, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7258, "f_coverage": 0.7258, "f_balanced": 0.7831, "anchor_diag": { "content_chars": 6338, "noise_chars": 778, "content_ngrams": 617, "noise_ngrams": 61, "ambiguous_ngrams_removed": 0, "content_sentences": 55 }, "notes": "" } }, "scoreable": true }, "webpack-docs": { "meta": { "id": "webpack-docs", "url": "https://webpack.js.org/concepts/", "requested_url": "https://webpack.js.org/concepts/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 117720 } }, "anchors": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 1594, "chars": 6378, "content_recall": 0.8003, "noise_retention": 0.0016, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8334, "f_coverage": 0.8334, "f_balanced": 0.8884, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 1594, "chars": 6378, "content_recall": 0.8003, "noise_retention": 0.0016, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8334, "f_coverage": 0.8334, "f_balanced": 0.8884, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 1078, "chars": 4315, "content_recall": 0.5374, "noise_retention": 0.0016, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.592, "f_coverage": 0.592, "f_balanced": 0.6987, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 1426, "chars": 5706, "content_recall": 0.9037, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9215, "f_coverage": 0.9215, "f_balanced": 0.9494, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "readability": { "method": "readability", "tokens": 1704, "chars": 6816, "content_recall": 0.875, "noise_retention": 0.2676, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8422, "f_coverage": 0.8422, "f_balanced": 0.7974, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 5279, "chars": 21118, "content_recall": 0.806, "noise_retention": 0.6135, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.758, "f_precision": 0.6623, "f_coverage": 0.6623, "f_balanced": 0.5225, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 5296, "chars": 21186, "content_recall": 0.806, "noise_retention": 0.6197, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.755, "f_precision": 0.6586, "f_coverage": 0.6586, "f_balanced": 0.5168, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 2695, "chars": 10782, "content_recall": 0.8721, "noise_retention": 0.9374, "noise_keyword_total": 3, "noise_per_1k_tokens": 1.113, "f_precision": 0.2432, "f_coverage": 0.2432, "f_balanced": 0.1168, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 5271, "chars": 21086, "content_recall": 0.806, "noise_retention": 0.6135, "noise_keyword_total": 4, "noise_per_1k_tokens": 0.759, "f_precision": 0.6623, "f_coverage": 0.6623, "f_balanced": 0.5225, "anchor_diag": { "content_chars": 6299, "noise_chars": 5075, "content_ngrams": 696, "noise_ngrams": 639, "ambiguous_ngrams_removed": 0, "content_sentences": 53 }, "notes": "" } }, "scoreable": true }, "wikipedia-html": { "meta": { "id": "wikipedia-html", "url": "https://en.wikipedia.org/wiki/HTML", "requested_url": "https://en.wikipedia.org/wiki/HTML", "category": "article", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": true, "bytes": 798214 } }, "anchors": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 17533, "chars": 70135, "content_recall": 0.822, "noise_retention": 0.0162, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.114, "f_precision": 0.8499, "f_coverage": 0.8499, "f_balanced": 0.8956, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 18209, "chars": 72836, "content_recall": 0.8631, "noise_retention": 0.0162, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.11, "f_precision": 0.8848, "f_coverage": 0.8848, "f_balanced": 0.9195, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 14558, "chars": 58235, "content_recall": 0.6749, "noise_retention": 0.0168, "noise_keyword_total": 2, "noise_per_1k_tokens": 0.137, "f_precision": 0.7201, "f_coverage": 0.7201, "f_balanced": 0.8004, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 16858, "chars": 67433, "content_recall": 0.8823, "noise_retention": 0.0019, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.059, "f_precision": 0.9032, "f_coverage": 0.9032, "f_balanced": 0.9366, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" }, "readability": { "method": "readability", "tokens": 11321, "chars": 45286, "content_recall": 0.6395, "noise_retention": 0.0, "noise_keyword_total": 1, "noise_per_1k_tokens": 0.088, "f_precision": 0.6892, "f_coverage": 0.6892, "f_balanced": 0.7801, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 57234, "chars": 228938, "content_recall": 0.7421, "noise_retention": 0.0973, "noise_keyword_total": 13, "noise_per_1k_tokens": 0.227, "f_precision": 0.7695, "f_coverage": 0.7695, "f_balanced": 0.8146, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 57192, "chars": 228768, "content_recall": 0.8048, "noise_retention": 0.1291, "noise_keyword_total": 13, "noise_per_1k_tokens": 0.227, "f_precision": 0.8172, "f_coverage": 0.8172, "f_balanced": 0.8365, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 20584, "chars": 82336, "content_recall": 0.9632, "noise_retention": 0.9775, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.243, "f_precision": 0.1027, "f_coverage": 0.1027, "f_balanced": 0.0439, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 57925, "chars": 231702, "content_recall": 0.7421, "noise_retention": 0.0973, "noise_keyword_total": 13, "noise_per_1k_tokens": 0.224, "f_precision": 0.7695, "f_coverage": 0.7695, "f_balanced": 0.8146, "anchor_diag": { "content_chars": 67094, "noise_chars": 12658, "content_ngrams": 7263, "noise_ngrams": 1603, "ambiguous_ngrams_removed": 52, "content_sentences": 574 }, "notes": "" } }, "scoreable": true }, "wikipedia-nlp": { "meta": { "id": "wikipedia-nlp", "url": "https://en.wikipedia.org/wiki/Natural_language_processing", "requested_url": "https://en.wikipedia.org/wiki/Natural_language_processing", "category": "article", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": true, "bytes": 463983 } }, "anchors": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 8248, "chars": 32993, "content_recall": 0.8215, "noise_retention": 0.0212, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8488, "f_coverage": 0.8488, "f_balanced": 0.8933, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 8781, "chars": 35125, "content_recall": 0.8855, "noise_retention": 0.0212, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9027, "f_coverage": 0.9027, "f_balanced": 0.9298, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 6619, "chars": 26479, "content_recall": 0.681, "noise_retention": 0.0212, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7251, "f_coverage": 0.7251, "f_balanced": 0.8032, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 11562, "chars": 46249, "content_recall": 0.8751, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8976, "f_coverage": 0.8976, "f_balanced": 0.9334, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" }, "readability": { "method": "readability", "tokens": 10721, "chars": 42886, "content_recall": 0.883, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9041, "f_coverage": 0.9041, "f_balanced": 0.9378, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 35052, "chars": 140211, "content_recall": 0.667, "noise_retention": 0.2861, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.143, "f_precision": 0.6759, "f_coverage": 0.6759, "f_balanced": 0.6897, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 34650, "chars": 138602, "content_recall": 0.7419, "noise_retention": 0.3126, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.144, "f_precision": 0.7303, "f_coverage": 0.7303, "f_balanced": 0.7136, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 13923, "chars": 55693, "content_recall": 0.9637, "noise_retention": 0.947, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.215, "f_precision": 0.2171, "f_coverage": 0.2171, "f_balanced": 0.1004, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 35483, "chars": 141933, "content_recall": 0.6668, "noise_retention": 0.2861, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.141, "f_precision": 0.6757, "f_coverage": 0.6757, "f_balanced": 0.6895, "anchor_diag": { "content_chars": 32174, "noise_chars": 7535, "content_ngrams": 3580, "noise_ngrams": 755, "ambiguous_ngrams_removed": 59, "content_sentences": 234 }, "notes": "" } }, "scoreable": true }, "wikipedia-rag": { "meta": { "id": "wikipedia-rag", "url": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation", "requested_url": "https://en.wikipedia.org/wiki/Retrieval-augmented_generation", "category": "article", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": true, "bytes": 251453 } }, "anchors": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 4929, "chars": 19718, "content_recall": 0.8445, "noise_retention": 0.0138, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8695, "f_coverage": 0.8695, "f_balanced": 0.9098, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 5026, "chars": 20107, "content_recall": 0.872, "noise_retention": 0.0138, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8927, "f_coverage": 0.8927, "f_balanced": 0.9256, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 4088, "chars": 16353, "content_recall": 0.6792, "noise_retention": 0.0138, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7243, "f_coverage": 0.7243, "f_balanced": 0.8044, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 4019, "chars": 16077, "content_recall": 0.8644, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8885, "f_coverage": 0.8885, "f_balanced": 0.9272, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" }, "readability": { "method": "readability", "tokens": 4023, "chars": 16093, "content_recall": 0.947, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9571, "f_coverage": 0.9571, "f_balanced": 0.9728, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 20134, "chars": 80539, "content_recall": 0.7721, "noise_retention": 0.1839, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.248, "f_precision": 0.7805, "f_coverage": 0.7805, "f_balanced": 0.7935, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 20128, "chars": 80513, "content_recall": 0.8434, "noise_retention": 0.2368, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.248, "f_precision": 0.8261, "f_coverage": 0.8261, "f_balanced": 0.8013, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 6189, "chars": 24756, "content_recall": 0.9648, "noise_retention": 0.9356, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.485, "f_precision": 0.254, "f_coverage": 0.254, "f_balanced": 0.1207, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 20414, "chars": 81658, "content_recall": 0.7751, "noise_retention": 0.1839, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.245, "f_precision": 0.783, "f_coverage": 0.783, "f_balanced": 0.7951, "anchor_diag": { "content_chars": 16371, "noise_chars": 4178, "content_ngrams": 1961, "noise_ngrams": 435, "ambiguous_ngrams_removed": 43, "content_sentences": 126 }, "notes": "" } }, "scoreable": true }, "wikipedia-vector": { "meta": { "id": "wikipedia-vector", "url": "https://en.wikipedia.org/wiki/Vector_database", "requested_url": "https://en.wikipedia.org/wiki/Vector_database", "category": "article", "status_code": 200, "signals": { "has_json_ld": true, "has_microdata": false, "has_table": true, "bytes": 323506 } }, "anchors": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 3436, "chars": 13745, "content_recall": 0.5095, "noise_retention": 0.0043, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.5646, "f_coverage": 0.5646, "f_balanced": 0.6741, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 4401, "chars": 17606, "content_recall": 0.7812, "noise_retention": 0.0043, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8163, "f_coverage": 0.8163, "f_balanced": 0.8755, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 2481, "chars": 9927, "content_recall": 0.3367, "noise_retention": 0.0043, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3881, "f_coverage": 0.3881, "f_balanced": 0.5032, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 3492, "chars": 13971, "content_recall": 0.878, "noise_retention": 0.0065, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8989, "f_coverage": 0.8989, "f_balanced": 0.9322, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" }, "readability": { "method": "readability", "tokens": 3203, "chars": 12812, "content_recall": 0.872, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8949, "f_coverage": 0.8949, "f_balanced": 0.9316, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 15046, "chars": 60187, "content_recall": 0.5515, "noise_retention": 0.2386, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.332, "f_precision": 0.5837, "f_coverage": 0.5837, "f_balanced": 0.6397, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 14466, "chars": 57867, "content_recall": 0.7263, "noise_retention": 0.2646, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.346, "f_precision": 0.7281, "f_coverage": 0.7281, "f_balanced": 0.7308, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 5036, "chars": 20144, "content_recall": 0.9377, "noise_retention": 0.9393, "noise_keyword_total": 3, "noise_per_1k_tokens": 0.596, "f_precision": 0.2412, "f_coverage": 0.2412, "f_balanced": 0.1141, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 15114, "chars": 60456, "content_recall": 0.5508, "noise_retention": 0.2386, "noise_keyword_total": 5, "noise_per_1k_tokens": 0.331, "f_precision": 0.5831, "f_coverage": 0.5831, "f_balanced": 0.6392, "anchor_diag": { "content_chars": 14344, "noise_chars": 4413, "content_ngrams": 1476, "noise_ngrams": 461, "ambiguous_ngrams_removed": 41, "content_sentences": 110 }, "notes": "" } }, "scoreable": true }, "yarn-docs": { "meta": { "id": "yarn-docs", "url": "https://yarnpkg.com/getting-started", "requested_url": "https://yarnpkg.com/getting-started", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": true, "has_table": false, "bytes": 27357 } }, "anchors": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 278, "chars": 1114, "content_recall": 0.8615, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8861, "f_coverage": 0.8861, "f_balanced": 0.9256, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 278, "chars": 1114, "content_recall": 0.8615, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8861, "f_coverage": 0.8861, "f_balanced": 0.9256, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 278, "chars": 1114, "content_recall": 0.8615, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8861, "f_coverage": 0.8861, "f_balanced": 0.9256, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 243, "chars": 975, "content_recall": 0.8615, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8861, "f_coverage": 0.8861, "f_balanced": 0.9256, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "readability": { "method": "readability", "tokens": 56, "chars": 226, "content_recall": 0.1769, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.2118, "f_coverage": 0.2118, "f_balanced": 0.3007, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 3822, "chars": 15291, "content_recall": 0.9231, "noise_retention": 0.1429, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9091, "f_coverage": 0.9091, "f_balanced": 0.8889, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 3819, "chars": 15276, "content_recall": 0.9231, "noise_retention": 0.1429, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9091, "f_coverage": 0.9091, "f_balanced": 0.8889, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 364, "chars": 1456, "content_recall": 0.9385, "noise_retention": 0.8367, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.4814, "f_coverage": 0.4814, "f_balanced": 0.2781, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 573, "chars": 2295, "content_recall": 0.9231, "noise_retention": 0.1429, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.9091, "f_coverage": 0.9091, "f_balanced": 0.8889, "anchor_diag": { "content_chars": 1996, "noise_chars": 581, "content_ngrams": 130, "noise_ngrams": 49, "ambiguous_ngrams_removed": 0, "content_sentences": 10 }, "notes": "" } }, "scoreable": true }, "zendesk-api": { "meta": { "id": "zendesk-api", "url": "https://developer.zendesk.com/api-reference/", "requested_url": "https://developer.zendesk.com/api-reference/", "category": "docs", "status_code": 200, "signals": { "has_json_ld": false, "has_microdata": false, "has_table": false, "bytes": 87046 } }, "anchors": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "methods": { "chromerag": { "method": "chromerag", "tokens": 566, "chars": 2265, "content_recall": 0.7621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8002, "f_coverage": 0.8002, "f_balanced": 0.865, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "chromerag_coverage": { "method": "chromerag_coverage", "tokens": 566, "chars": 2265, "content_recall": 0.7621, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.8002, "f_coverage": 0.8002, "f_balanced": 0.865, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "chromerag_precision": { "method": "chromerag_precision", "tokens": 501, "chars": 2006, "content_recall": 0.6784, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.725, "f_coverage": 0.725, "f_balanced": 0.8084, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "trafilatura": { "method": "trafilatura", "tokens": 500, "chars": 2000, "content_recall": 0.674, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.721, "f_coverage": 0.721, "f_balanced": 0.8053, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "readability": { "method": "readability", "tokens": 317, "chars": 1269, "content_recall": 0.5639, "noise_retention": 0.0, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.6178, "f_coverage": 0.6178, "f_balanced": 0.7211, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "markdownify": { "method": "markdownify", "tokens": 1722, "chars": 6890, "content_recall": 0.7533, "noise_retention": 0.2133, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7597, "f_coverage": 0.7597, "f_balanced": 0.7696, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "html2text": { "method": "html2text", "tokens": 1735, "chars": 6941, "content_recall": 0.7533, "noise_retention": 0.2133, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7597, "f_coverage": 0.7597, "f_balanced": 0.7696, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "beautifulsoup_text": { "method": "beautifulsoup_text", "tokens": 826, "chars": 3306, "content_recall": 0.7533, "noise_retention": 0.8933, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.3405, "f_coverage": 0.3405, "f_balanced": 0.1869, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" }, "markitdown": { "method": "markitdown", "tokens": 1711, "chars": 6845, "content_recall": 0.7533, "noise_retention": 0.2133, "noise_keyword_total": 0, "noise_per_1k_tokens": 0.0, "f_precision": 0.7597, "f_coverage": 0.7597, "f_balanced": 0.7696, "anchor_diag": { "content_chars": 1706, "noise_chars": 921, "content_ngrams": 227, "noise_ngrams": 75, "ambiguous_ngrams_removed": 0, "content_sentences": 21 }, "notes": "" } }, "scoreable": true } }, "summary": { "chromerag": { "pages_scored": 242, "avg_content_recall": 0.6647, "avg_noise_retention": 0.0065, "avg_f_balanced": 0.771, "avg_f_precision": 0.7019, "avg_f_coverage": 0.7019, "avg_tokens": 3382.6694, "avg_noise_per_1k_tokens": 0.0687 }, "chromerag_coverage": { "pages_scored": 242, "avg_content_recall": 0.6877, "avg_noise_retention": 0.0071, "avg_f_balanced": 0.7882, "avg_f_precision": 0.7231, "avg_f_coverage": 0.7231, "avg_tokens": 3456.7934, "avg_noise_per_1k_tokens": 0.0728 }, "chromerag_precision": { "pages_scored": 242, "avg_content_recall": 0.5251, "avg_noise_retention": 0.0066, "avg_f_balanced": 0.6524, "avg_f_precision": 0.5679, "avg_f_coverage": 0.5679, "avg_tokens": 2928.4091, "avg_noise_per_1k_tokens": 0.0585 }, "trafilatura": { "pages_scored": 242, "avg_content_recall": 0.6398, "avg_noise_retention": 0.0122, "avg_f_balanced": 0.7392, "avg_f_precision": 0.6732, "avg_f_coverage": 0.6732, "avg_tokens": 2485.5537, "avg_noise_per_1k_tokens": 0.214 }, "readability": { "pages_scored": 242, "avg_content_recall": 0.4491, "avg_noise_retention": 0.0129, "avg_f_balanced": 0.5307, "avg_f_precision": 0.475, "avg_f_coverage": 0.475, "avg_tokens": 2064.1446, "avg_noise_per_1k_tokens": 0.0827 }, "markdownify": { "pages_scored": 242, "avg_content_recall": 0.6909, "avg_noise_retention": 0.2509, "avg_f_balanced": 0.6951, "avg_f_precision": 0.6861, "avg_f_coverage": 0.6861, "avg_tokens": 8832.686, "avg_noise_per_1k_tokens": 0.565 }, "html2text": { "pages_scored": 242, "avg_content_recall": 0.676, "avg_noise_retention": 0.2673, "avg_f_balanced": 0.6718, "avg_f_precision": 0.6632, "avg_f_coverage": 0.6632, "avg_tokens": 8715.2231, "avg_noise_per_1k_tokens": 0.5571 }, "beautifulsoup_text": { "pages_scored": 242, "avg_content_recall": 0.8145, "avg_noise_retention": 0.824, "avg_f_balanced": 0.243, "avg_f_precision": 0.3658, "avg_f_coverage": 0.3658, "avg_tokens": 4472.1446, "avg_noise_per_1k_tokens": 0.9225 }, "markitdown": { "pages_scored": 242, "avg_content_recall": 0.6908, "avg_noise_retention": 0.2498, "avg_f_balanced": 0.6955, "avg_f_precision": 0.6862, "avg_f_coverage": 0.6862, "avg_tokens": 8872.7273, "avg_noise_per_1k_tokens": 0.5595 } }, "n_pages": 268, "n_scoreable": 242, "scoreable_rule": "input DOM content_ngrams >= 50", "summary_all_fetched": { "chromerag": { "pages_scored": 268, "avg_content_recall": 0.6331, "avg_noise_retention": 0.0069, "avg_f_balanced": 0.7314, "avg_tokens": 3071.2873 }, "chromerag_coverage": { "pages_scored": 268, "avg_content_recall": 0.6538, "avg_noise_retention": 0.0074, "avg_f_balanced": 0.747, "avg_tokens": 3138.2201 }, "chromerag_precision": { "pages_scored": 268, "avg_content_recall": 0.5011, "avg_noise_retention": 0.007, "avg_f_balanced": 0.6185, "avg_tokens": 2658.9254 }, "trafilatura": { "pages_scored": 268, "avg_content_recall": 0.6067, "avg_noise_retention": 0.0242, "avg_f_balanced": 0.6956, "avg_tokens": 2275.9888 }, "readability": { "pages_scored": 268, "avg_content_recall": 0.4196, "avg_noise_retention": 0.0168, "avg_f_balanced": 0.4953, "avg_tokens": 1869.8769 }, "markdownify": { "pages_scored": 268, "avg_content_recall": 0.6577, "avg_noise_retention": 0.2412, "avg_f_balanced": 0.6608, "avg_tokens": 8368.3582 }, "html2text": { "pages_scored": 268, "avg_content_recall": 0.644, "avg_noise_retention": 0.2561, "avg_f_balanced": 0.6395, "avg_tokens": 8264.0373 }, "beautifulsoup_text": { "pages_scored": 268, "avg_content_recall": 0.7727, "avg_noise_retention": 0.7935, "avg_f_balanced": 0.2332, "avg_tokens": 4135.9664 }, "markitdown": { "pages_scored": 268, "avg_content_recall": 0.6576, "avg_noise_retention": 0.2402, "avg_f_balanced": 0.6612, "avg_tokens": 8409.847 } }, "paired_bootstrap": [ { "a": "chromerag_coverage", "b": "trafilatura", "metric": "f_balanced", "n": 242, "mean_diff": 0.049, "ci_low": 0.0214, "ci_high": 0.0787 }, { "a": "chromerag_coverage", "b": "trafilatura", "metric": "content_recall", "n": 242, "mean_diff": 0.0479, "ci_low": 0.0212, "ci_high": 0.0755 }, { "a": "chromerag_coverage", "b": "trafilatura", "metric": "noise_retention", "n": 242, "mean_diff": -0.0051, "ci_low": -0.0144, "ci_high": 0.0029 }, { "a": "chromerag", "b": "trafilatura", "metric": "f_balanced", "n": 242, "mean_diff": 0.0318, "ci_low": 0.0045, "ci_high": 0.0607 }, { "a": "chromerag", "b": "trafilatura", "metric": "content_recall", "n": 242, "mean_diff": 0.0249, "ci_low": -0.0046, "ci_high": 0.0544 }, { "a": "chromerag", "b": "trafilatura", "metric": "noise_retention", "n": 242, "mean_diff": -0.0057, "ci_low": -0.0153, "ci_high": 0.0027 }, { "a": "chromerag_coverage", "b": "markitdown", "metric": "f_balanced", "n": 242, "mean_diff": 0.0927, "ci_low": 0.0687, "ci_high": 0.117 }, { "a": "chromerag_coverage", "b": "markitdown", "metric": "content_recall", "n": 242, "mean_diff": -0.0031, "ci_low": -0.0249, "ci_high": 0.0169 }, { "a": "chromerag_coverage", "b": "markitdown", "metric": "noise_retention", "n": 242, "mean_diff": -0.2427, "ci_low": -0.2661, "ci_high": -0.2203 } ], "by_category": { "api_docs": { "chromerag": { "pages": 4, "avg_content_recall": 0.6677, "avg_noise_retention": 0.0, "avg_f_balanced": 0.7979, "avg_tokens": 899.0 }, "chromerag_coverage": { "pages": 4, "avg_content_recall": 0.7096, "avg_noise_retention": 0.0, "avg_f_balanced": 0.8273, "avg_tokens": 946.5 }, "trafilatura": { "pages": 4, "avg_content_recall": 0.4475, "avg_noise_retention": 0.0, "avg_f_balanced": 0.5733, "avg_tokens": 613.25 }, "markitdown": { "pages": 4, "avg_content_recall": 0.6222, "avg_noise_retention": 0.1821, "avg_f_balanced": 0.6994, "avg_tokens": 4440.25 } }, "article": { "chromerag": { "pages": 8, "avg_content_recall": 0.7427, "avg_noise_retention": 0.0205, "avg_f_balanced": 0.8371, "avg_tokens": 7508.75 }, "chromerag_coverage": { "pages": 8, "avg_content_recall": 0.7932, "avg_noise_retention": 0.0205, "avg_f_balanced": 0.8718, "avg_tokens": 7793.625 }, "trafilatura": { "pages": 8, "avg_content_recall": 0.7175, "avg_noise_retention": 0.0027, "avg_f_balanced": 0.8118, "avg_tokens": 7310.125 }, "markitdown": { "pages": 8, "avg_content_recall": 0.7077, "avg_noise_retention": 0.2752, "avg_f_balanced": 0.7049, "avg_tokens": 21492.875 } }, "cloud": { "chromerag": { "pages": 7, "avg_content_recall": 0.6827, "avg_noise_retention": 0.0, "avg_f_balanced": 0.7998, "avg_tokens": 1154.8571 }, "chromerag_coverage": { "pages": 7, "avg_content_recall": 0.6868, "avg_noise_retention": 0.0, "avg_f_balanced": 0.8028, "avg_tokens": 1160.2857 }, "trafilatura": { "pages": 7, "avg_content_recall": 0.5837, "avg_noise_retention": 0.0, "avg_f_balanced": 0.7017, "avg_tokens": 994.0 }, "markitdown": { "pages": 7, "avg_content_recall": 0.8106, "avg_noise_retention": 0.2734, "avg_f_balanced": 0.7657, "avg_tokens": 5437.5714 } }, "docs": { "chromerag": { "pages": 208, "avg_content_recall": 0.659, "avg_noise_retention": 0.0068, "avg_f_balanced": 0.7642, "avg_tokens": 3360.9952 }, "chromerag_coverage": { "pages": 208, "avg_content_recall": 0.682, "avg_noise_retention": 0.0075, "avg_f_balanced": 0.7817, "avg_tokens": 3430.1779 }, "trafilatura": { "pages": 208, "avg_content_recall": 0.6446, "avg_noise_retention": 0.0091, "avg_f_balanced": 0.745, "avg_tokens": 2361.0913 }, "markitdown": { "pages": 208, "avg_content_recall": 0.685, "avg_noise_retention": 0.252, "avg_f_balanced": 0.6907, "avg_tokens": 8366.6923 } }, "hub": { "chromerag": { "pages": 2, "avg_content_recall": 0.6705, "avg_noise_retention": 0.0, "avg_f_balanced": 0.7944, "avg_tokens": 5924.0 }, "chromerag_coverage": { "pages": 2, "avg_content_recall": 0.6904, "avg_noise_retention": 0.0, "avg_f_balanced": 0.8061, "avg_tokens": 6127.0 }, "trafilatura": { "pages": 2, "avg_content_recall": 0.433, "avg_noise_retention": 0.0, "avg_f_balanced": 0.5187, "avg_tokens": 5308.5 }, "markitdown": { "pages": 2, "avg_content_recall": 0.5508, "avg_noise_retention": 0.0576, "avg_f_balanced": 0.6934, "avg_tokens": 11820.5 } }, "marketing": { "chromerag": { "pages": 8, "avg_content_recall": 0.6855, "avg_noise_retention": 0.0, "avg_f_balanced": 0.8071, "avg_tokens": 1845.875 }, "chromerag_coverage": { "pages": 8, "avg_content_recall": 0.6979, "avg_noise_retention": 0.0, "avg_f_balanced": 0.8163, "avg_tokens": 1892.125 }, "trafilatura": { "pages": 8, "avg_content_recall": 0.5884, "avg_noise_retention": 0.1285, "avg_f_balanced": 0.644, "avg_tokens": 1456.75 }, "markitdown": { "pages": 8, "avg_content_recall": 0.7239, "avg_noise_retention": 0.3056, "avg_f_balanced": 0.672, "avg_tokens": 8619.25 } }, "pricing": { "chromerag": { "pages": 5, "avg_content_recall": 0.7126, "avg_noise_retention": 0.0, "avg_f_balanced": 0.8157, "avg_tokens": 4230.8 }, "chromerag_coverage": { "pages": 5, "avg_content_recall": 0.7192, "avg_noise_retention": 0.0, "avg_f_balanced": 0.821, "avg_tokens": 4283.8 }, "trafilatura": { "pages": 5, "avg_content_recall": 0.7093, "avg_noise_retention": 0.0, "avg_f_balanced": 0.8051, "avg_tokens": 4046.8 }, "markitdown": { "pages": 5, "avg_content_recall": 0.797, "avg_noise_retention": 0.1262, "avg_f_balanced": 0.8169, "avg_tokens": 17313.2 } } }, "corpus_urls_listed": 367, "corpus_url_count": 367, "n_fetched": 268, "n_thin": 26 }