{"adoption": {"forks": 109, "observed_at": "2026-08-28T04:04:33.486965+00:00", "stars": 1378}, "canonical_url": "https://ross.abutalabs.com/products/rank_bm25", "card": {"archived": false, "artifact_type": "library", "description": "A Collection of BM25 Algorithms in Python", "domain": [], "enriched": true, "function": ["search-engine", "nlp"], "health_score": 68, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["dorianbrown/rank_bm25"], "name": "dorianbrown/rank_bm25", "platform": ["python"], "pushed_at": "2026-05-02T22:17:06+00:00", "repo": "dorianbrown/rank_bm25", "stars": 1378, "tags": ["bm25", "document-ranking", "information-retrieval", "text-search", "search", "natural-language-processing"], "topics": ["bm25", "information-retrieval", "algorithm", "ranking"], "urls": [], "use_cases": ["rank documents by relevance to a query in python", "build a simple keyword search engine", "score a corpus with BM25", "implement lexical retrieval for RAG pipelines", "compare BM25 variants like BM25L and BM25+"], "what_it_is": "A Python library implementing several BM25 ranking algorithms (Okapi BM25, BM25L, BM25+) for scoring and ranking documents against a query. It is a lightweight, in-memory 'two line search engine' that requires users to handle their own tokenization and preprocessing.", "when_to_avoid": ["you need high-performance retrieval over large-scale production corpora", "you need built-in indexing, persistence, or text preprocessing", "you need semantic/vector search rather than lexical ranking"], "when_to_choose": ["you need a simple, dependency-light BM25 implementation for small to medium corpora", "you want to prototype lexical search or hybrid retrieval quickly", "you want control over your own tokenization and preprocessing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/rank_bm25", "repo": "dorianbrown/rank_bm25", "role": "main", "score": 59}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.486965+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:40:22.053086+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ee406166b498d213cfd5d02ddefa04293b40d2374c75eefaefaea5f759f0ef0", "fetched_at": "2026-08-28T04:04:33.486965+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dorianbrown/rank_bm25"}, {"content_hash": "aa1868880cbb0fd47c1399778e8f951e52a1a3296be09f225a209fd6b6993868", "fetched_at": "2026-08-29T11:56:24.319067+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rank_bm25/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 80, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2782, "days_push": 123, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 59, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}