{"adoption": {"forks": 673, "observed_at": "2026-09-03T02:15:09.831773+00:00", "stars": 1191}, "canonical_url": "https://ross.abutalabs.com/products/anserini", "card": {"archived": false, "artifact_type": "library", "description": "Anserini is a Lucene toolkit for reproducible information retrieval research", "domain": [], "enriched": true, "function": ["search-engine", "rag", "machine-learning", "sdk"], "health_score": 80, "homepage": "http://anserini.io/", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["castorini/anserini", "castorini/pyserini"], "name": "Anserini", "platform": ["python", "jvm", "cli", "cross-platform"], "pushed_at": "2026-09-02T19:39:53+00:00", "repo": "castorini/anserini", "stars": 1191, "tags": ["information-retrieval", "sparse-retrieval", "dense-retrieval", "bm25", "faiss", "lucene", "test-collections", "first-stage-retrieval", "mcp-server", "rest-api", "search", "natural-language-processing", "research"], "topics": ["information-retrieval", "lucene"], "urls": [{"kind": "homepage", "url": "http://anserini.io/"}], "use_cases": ["reproduce BM25 baseline runs on standard IR test collections", "run dense retrieval with prebuilt indexes for first-stage ranking", "build a multi-stage ranking pipeline with reproducible retrieval", "evaluate retrieval runs with trec_eval-style scripts", "search MS MARCO and other benchmark corpora", "expose retrieval via a REST API or MCP server"], "what_it_is": "Pyserini is a Python toolkit for reproducible information retrieval research supporting both sparse (via Anserini/Lucene) and dense (via Faiss) representations. It bundles queries, relevance judgments, prebuilt indexes, and evaluation scripts for standard IR test collections, with a REST API and MCP server.", "when_to_avoid": ["you need a production search engine with indexing, sharding, and serving out of the box", "you want a simple plug-and-play vector store without Java 21 dependencies", "your use case is general web search rather than benchmark-oriented retrieval"], "when_to_choose": ["you need reproducible, benchmarked sparse and dense retrieval in Python", "you want prebuilt indexes and judgments for common IR test collections", "you're doing academic IR research or building RAG first-stage retrieval"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/castorini/anserini", "repo": "castorini/anserini", "role": "main", "score": 77}, {"path": "/repos/castorini/pyserini", "repo": "castorini/pyserini", "role": "sdk", "score": 95}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-09-03T02:15:09.831773+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:50:38.835348+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "68152f0473006e1947cf0c1fd40bef419d6c7d20afa833366f20e34989b4f189", "fetched_at": "2026-09-03T02:15:09.831773+00:00", "kind": "readme", "missing": false, "url": "https://github.com/castorini/anserini"}, {"content_hash": "80b309a0162af99e679b66c7195e251bd76016af5bbc4f12b6208d46fa9fc953", "fetched_at": "2026-08-29T10:30:40.175800+00:00", "kind": "homepage", "missing": false, "url": "http://anserini.io/"}, {"content_hash": "a530273a5fe67fce7bb5bb647d9322e7019d68b4025811684ba3ca764255b38c", "fetched_at": "2026-08-29T10:30:40.178360+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pyserini/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 100, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3985, "days_push": 0, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 3, "stale_scrape": false}}