piskvorky/gensim

Health v2 · maintenance only

Adoption not part of the score

16481 stars · 4409 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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.

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

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

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

Facets

library · maturity maintenance

nlp machine-learning search-engine data-science machine-learning data-science python windows cross-platform topic-modeling word2vec word-embeddings lda fasttext doc2vec document-similarity information-retrieval unsupervised-learning streaming-corpus natural-language-processing search linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="piskvorky/gensim")