{"adoption": {"forks": 4409, "observed_at": "2026-08-28T04:11:16.550842+00:00", "stars": 16481}, "canonical_url": "https://ross.abutalabs.com/products/gensim", "card": {"archived": false, "artifact_type": "library", "description": "Topic Modelling for Humans", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["nlp", "machine-learning", "search-engine", "data-science"], "health_score": 65, "homepage": "https://radimrehurek.com/gensim", "language": "Python", "license": "LGPL-2.1", "license_family": "copyleft", "maturity": "maintenance", "member_repos": ["piskvorky/gensim"], "name": "piskvorky/gensim", "platform": ["python", "windows", "cross-platform"], "pushed_at": "2025-11-01T12:01:39+00:00", "repo": "piskvorky/gensim", "stars": 16481, "tags": ["topic-modeling", "word2vec", "word-embeddings", "lda", "fasttext", "doc2vec", "document-similarity", "information-retrieval", "unsupervised-learning", "streaming-corpus", "natural-language-processing", "search", "linux", "macos"], "topics": ["gensim", "topic-modeling", "information-retrieval", "machine-learning", "natural-language-processing", "nlp", "data-science", "python", "data-mining", "word2vec", "word-embeddings", "neural-network", "document-similarity", "word-similarity", "fasttext"], "urls": [], "use_cases": ["train word2vec embeddings on a large text corpus", "discover topics in documents with LDA", "find semantically similar documents to a query", "compute document similarity with doc2vec", "stream a corpus larger than RAM for training", "compare word similarity with fasttext embeddings", "summarize and analyze unstructured text"], "what_it_is": "Gensim is a Python library for topic modelling, document indexing, and similarity retrieval over large text corpora. It provides memory-independent, parallelized implementations of algorithms like LDA, LSI, Word2Vec, Doc2Vec, and FastText for unsupervised semantic analysis of plain text.", "when_to_avoid": ["you need cutting-edge transformer-based models or GPU acceleration", "you expect new features - the project is in stable maintenance mode accepting only bug fixes", "you need deep learning pipelines beyond classic vector-space algorithms"], "when_to_choose": ["you need battle-tested, memory-efficient topic modelling or embedding training in Python", "your corpus is too large to fit in RAM and needs streaming or distributed training", "you want mature, well-documented NLP algorithms with optimized C backends"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/gensim", "repo": "piskvorky/gensim", "role": "main", "score": 50}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:16.550842+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:04:54.298317+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a620a76873ccddab1ecd73a1d49af91ee73204315d19c94dd4cb67b1b0606658", "fetched_at": "2026-08-28T04:11:16.550842+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim"}, {"content_hash": "039a7c40d5703e2fc0deee50ca406cb25a07a0a86fe9b3a2ee9faf0c9f906c55", "fetched_at": "2026-08-29T08:02:18.973219+00:00", "kind": "homepage", "missing": false, "url": "https://radimrehurek.com/gensim"}, {"content_hash": "67fdb6f0ffe5185fbcc753fa81e87b03e69ce2a054a7fb6abfb3f8dfef1d8f2a", "fetched_at": "2026-08-29T08:02:18.982364+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/auto_examples/index.html"}, {"content_hash": "c4119e5e08ee9f7101fa9a66fc38774074a52194c985f22944b49b3d8d142586", "fetched_at": "2026-08-29T08:02:18.984199+00:00", "kind": "site_page", "missing": false, "url": "https://radimrehurek.com/gensim/intro.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 50, "longevity": 100, "rhythm": 20}, "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": 5683, "days_push": 305, "days_rel": 321, "gap_med": null, "n_releases_24m": 1}, "score": 50, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}