# shibing624/text2vec

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。

Repository: https://github.com/shibing624/text2vec
Canonical: https://ross.abutalabs.com/products/text2vec
Homepage: https://pypi.org/project/text2vec/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: similarity, nlp, text-similarity, text2vec, word2vec, embeddings, sentence-embeddings
Last push: 2026-02-14T14:59:10+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 67, release rhythm 8, longevity 100
- inputs: {"age_days": 2486, "days_push": 200, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4974, forks 428 (observed 2026-08-28T04:09:04.072525+00:00)

## 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.

## 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

## 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

## 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

## Facets
- artifact type: library
- maturity: active
- function: nlp, machine-learning, search-engine
- domain: machine-learning
- platform: python
- tags: embeddings, sentence-embeddings, text-similarity, word2vec, sentence-bert, cosent, chinese-nlp, semantic-search, natural-language-processing, search

## Member repositories
- shibing624/text2vec (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:04.072525+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:17:44.734253+00:00, confidence not recorded.
  - readme: https://github.com/shibing624/text2vec (fetched 2026-08-28T04:09:04.072525+00:00, sha 9cf8cc706fe5)
  - homepage: https://pypi.org/project/text2vec/ (fetched 2026-08-29T08:58:56.833165+00:00, sha 4b4e8fead74a)
  - registry_pypi: https://pypi.org/pypi/text2vec/json (fetched 2026-08-29T08:58:56.842740+00:00, sha 01fc72ad8848)
- Data as of 2026-08-30T08:39:29.467469+00:00.