{"adoption": {"forks": 101, "observed_at": "2026-08-28T04:05:34.236906+00:00", "stars": 1774}, "canonical_url": "https://ross.abutalabs.com/products/bm25s", "card": {"archived": false, "artifact_type": "library", "description": "Fast BM25 search in Python, powered by Numpy and Numba", "domain": ["machine-learning"], "enriched": true, "function": ["search-engine", "nlp", "rag"], "health_score": 100, "homepage": "https://bm25s.github.io", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["xhluca/bm25s"], "name": "xhluca/bm25s", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-25T03:14:31+00:00", "repo": "xhluca/bm25s", "stars": 1774, "tags": ["bm25", "lexical-search", "information-retrieval", "sparse-matrices", "numpy", "numba", "text-ranking", "search", "natural-language-processing", "retrieval-augmented-generation"], "topics": ["bm25", "bm25-l", "bm25-plus", "lexical-search", "retrieval", "robertson", "search", "okapi-bm25", "rag", "information-retrieval"], "urls": [], "use_cases": ["rank documents by relevance to a query in Python", "add fast lexical search to a RAG pipeline without Elasticsearch", "replace rank-bm25 with a much faster BM25 implementation", "build keyword retrieval over a corpus with minimal dependencies", "score and retrieve top-k documents for hybrid search", "share and load prebuilt BM25 indices via Hugging Face Hub"], "what_it_is": "BM25S is a pure Python library implementing BM25 lexical ranking using Numpy/Scipy sparse matrices with an optional Numba backend, achieving speeds comparable to or exceeding Elasticsearch without Java or servers. It supports BM25 variants (Okapi, BM25L, BM25+), tokenization, stemming, and Hugging Face Hub index sharing.", "when_to_avoid": ["you need a full search engine with distributed indexing, faceting, or analytics", "you require advanced analyzers or multilingual tokenization matching Elasticsearch quality", "your corpus is too large to fit in memory as sparse matrices"], "when_to_choose": ["you need fast BM25 scoring entirely in Python with no Java or web server", "you want a lightweight, low-memory lexical retriever for RAG or hybrid search", "you need BM25 variants like BM25L or BM25+ out of the box"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bm25s", "repo": "xhluca/bm25s", "role": "main", "score": 92}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.236906+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:25:24.488617+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0dd8ddb0f31f2595ac944261eecebd8aca64a99ea4e317f7c767de90de38095f", "fetched_at": "2026-08-28T04:05:34.236906+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xhluca/bm25s"}, {"content_hash": "89cee17e9cc95b30bfbbb8a9135bfc5cb4a9da62308922c95736c2de09e86607", "fetched_at": "2026-08-29T11:03:58.411028+00:00", "kind": "homepage", "missing": false, "url": "https://bm25s.github.io"}, {"content_hash": "c0f7bdada977bc79806d985d2945f0b628200240f55a1f9bc7c771f82f70b07f", "fetched_at": "2026-08-29T11:03:58.420009+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bm25s/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 62, "rhythm": 99}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 875, "days_push": 8, "days_rel": 8, "gap_med": 14.0, "n_releases_24m": 27}, "score": 92, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}