{"adoption": {"forks": 428, "observed_at": "2026-08-28T04:09:04.072525+00:00", "stars": 4974}, "canonical_url": "https://ross.abutalabs.com/products/text2vec", "card": {"archived": false, "artifact_type": "library", "description": "text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。", "domain": ["machine-learning"], "enriched": true, "function": ["nlp", "machine-learning", "search-engine"], "health_score": 63, "homepage": "https://pypi.org/project/text2vec/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["shibing624/text2vec"], "name": "shibing624/text2vec", "platform": ["python"], "pushed_at": "2026-02-14T14:59:10+00:00", "repo": "shibing624/text2vec", "stars": 4974, "tags": ["embeddings", "sentence-embeddings", "text-similarity", "word2vec", "sentence-bert", "cosent", "chinese-nlp", "semantic-search", "natural-language-processing", "search"], "topics": ["similarity", "nlp", "text-similarity", "text2vec", "word2vec", "embeddings", "sentence-embeddings"], "urls": [], "use_cases": ["compute semantic similarity between two sentences", "generate sentence embeddings for Chinese text", "build a semantic search or retrieval system", "encode documents into vectors for clustering", "train a custom text matching model with CoSENT", "find duplicate or paraphrase questions in a corpus"], "what_it_is": "A Python library that converts text (words, sentences, paragraphs) into vector embeddings, implementing Word2Vec, RankBM25, BERT, Sentence-BERT, and CoSENT models. It provides ready-to-use text representation and semantic similarity computation, with pretrained Chinese and multilingual models and a CLI for batch vectorization.", "when_to_avoid": ["you need production-scale vector database features like ANN indexing and filtering", "you only need English embeddings and prefer the broader sentence-transformers ecosystem", "you need the latest LLM-based embedding models rather than BERT-era encoders"], "when_to_choose": ["you need out-of-the-box sentence embeddings, especially for Chinese or multilingual text", "you want to compare multiple text similarity models (BM25, SBERT, CoSENT) in one library", "you need pretrained matching models with a simple Python API or CLI"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/text2vec", "repo": "shibing624/text2vec", "role": "main", "score": 53}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.072525+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:17:44.734253+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9cf8cc706fe5e6dba667674c69fe992d34b22f5f86d59ade6c2f8ecd7d794837", "fetched_at": "2026-08-28T04:09:04.072525+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/text2vec"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T08:58:56.833165+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/text2vec/"}, {"content_hash": "01fc72ad884892d0c364773350f3a2de175e3c0eb2b66581070d714a76926e2a", "fetched_at": "2026-08-29T08:58:56.842740+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/text2vec/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 67, "longevity": 100, "rhythm": 8}, "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": 2486, "days_push": 200, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 53, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}