{"adoption": {"forks": 257, "observed_at": "2026-08-28T04:03:58.164750+00:00", "stars": 1201}, "canonical_url": "https://ross.abutalabs.com/products/sent2vec", "card": {"archived": false, "artifact_type": "library", "description": "General purpose unsupervised sentence representations ", "domain": ["machine-learning"], "enriched": true, "function": ["machine-learning", "nlp"], "health_score": 20, "homepage": null, "language": "C++", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["epfml/sent2vec"], "name": "epfml/sent2vec", "platform": ["python", "cpp", "cross-platform"], "pushed_at": "2022-08-03T18:18:45+00:00", "repo": "epfml/sent2vec", "stars": 1201, "tags": ["sentence-embeddings", "word-embeddings", "unsupervised-learning", "fasttext", "cython", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["generate sentence embeddings for text classification", "get numerical features for short texts and sentences", "train an unsupervised sentence embedding model", "find nearest neighbour sentences and word analogies", "extract word embeddings from pre-trained models", "embed sentences in python while keeping the model in memory"], "what_it_is": "Sent2vec is a C++ library with a Cython/Python interface that trains unsupervised distributed representations of sentences and short texts, built on Facebook's FastText. It includes pre-trained models for generating sentence and word embeddings usable as features in downstream machine learning tasks.", "when_to_avoid": ["you need state-of-the-art contextual embeddings from transformer models", "you need cross-lingual sentence embeddings (use Bi-sent2vec instead)", "you need an actively developed project with recent updates"], "when_to_choose": ["you need fast, lightweight unsupervised sentence embeddings without a GPU", "you want to train custom embeddings on your own corpus", "you need embeddings as input features for classical ML models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/sent2vec", "repo": "epfml/sent2vec", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.164750+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:20:40.853433+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0b600416d0326427eebfd6f95b2824ea359511f2737934b1a300e18c9a451786", "fetched_at": "2026-08-28T04:03:58.164750+00:00", "kind": "readme", "missing": false, "url": "https://github.com/epfml/sent2vec"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3458, "days_push": 1491, "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}}