{"adoption": {"forks": 142, "observed_at": "2026-08-28T04:03:24.982786+00:00", "stars": 1058}, "canonical_url": "https://ross.abutalabs.com/products/gensim-data", "card": {"archived": false, "artifact_type": "dataset", "description": "Data repository for pretrained NLP models and NLP corpora.", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["machine-learning", "nlp", "data-science"], "health_score": 20, "homepage": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/", "language": "Python", "license": "LGPL-2.1", "license_family": "copyleft", "maturity": "maintenance", "member_repos": ["piskvorky/gensim-data"], "name": "piskvorky/gensim-data", "platform": ["python", "cross-platform"], "pushed_at": "2018-03-16T13:55:53+00:00", "repo": "piskvorky/gensim-data", "stars": 1058, "tags": ["word2vec", "glove", "lda", "lsi", "corpora", "pretrained-models", "gensim", "text-data", "natural-language-processing"], "topics": ["dataset", "gensim", "word2vec-model", "corpora", "pretrained-models", "lsi-model", "glove-model", "lda-model"], "urls": [], "use_cases": ["download pretrained word embeddings like glove-twitter-25", "load a text corpus to train a word2vec model", "get a stable copy of English Wikipedia text data", "find similar words using pretrained vectors", "download NLP datasets with a consistent Python API", "access text8 corpus for training embeddings"], "what_it_is": "A data repository hosting pretrained NLP models (Word2Vec, GloVe, LDA, LSI) and text corpora as immutable GitHub release attachments, accessed via Gensim's download API. It provides long-term storage and a standardized loading interface for unstructured text datasets.", "when_to_avoid": ["you need image, audio, or non-text datasets", "you need transformer-based models like BERT or GPT", "you want actively updated datasets with new releases"], "when_to_choose": ["you need pretrained word vectors or text corpora with a reliable, long-term download source", "you already use Gensim and want one-line dataset loading", "you want immutable, versioned NLP datasets with usage examples"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/gensim-data", "repo": "piskvorky/gensim-data", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.982786+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:57:51.837600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1596af49b4664281ef834680462dc7379b84e81b412bd55e84b27543d814c3cb", "fetched_at": "2026-08-28T04:03:24.982786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/gensim-data"}, {"content_hash": "b26697774bab38b7acb69ed2ca5450619795156eb8f9a5e46d6c92aea00715de", "fetched_at": "2026-08-29T13:00:12.753872+00:00", "kind": "homepage", "missing": false, "url": "https://rare-technologies.com/new-api-for-pretrained-nlp-models-and-datasets-in-gensim/"}, {"content_hash": "f33c361f4d4fa5d4ca495c5e8bcd7d73b00d916d02bfa9001a68c1d642745230", "fetched_at": "2026-08-29T13:00:12.762137+00:00", "kind": "site_page", "missing": false, "url": "https://documentation.pii-tools.com/"}, {"content_hash": "9bbbbc8842bd93033118e9a79bf4eb2b173e69c534c3798d683c2d06ca5523cf", "fetched_at": "2026-08-29T13:00:12.756799+00:00", "kind": "site_page", "missing": false, "url": "https://pii-tools.com/pricing"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "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": 3246, "days_push": 3092, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}