kitio.aiAdded Nov 5, 2026
Gensim
FreeFree Python library for topic modelling and text embeddings
What is Gensim?
Gensim is an open-source Python library for training semantic NLP models such as word2vec, LSI and LDA on large text collections. Data scientists use it to turn documents into vectors and find related texts, even when the corpus does not fit in memory.
Corpora can be streamed from disk or cloud storage like S3, so training scales to very large datasets. The library includes similarity indexes for querying documents, a downloader for pretrained models and datasets, and implementations of doc2vec and fastText.
Gensim is free under an open-source license, with documentation, an API reference and a support page on the project site. The project is funded by donations and maintained by Radim Řehůřek and contributors on GitHub.
Features
- Topic modelling (LDA, LSI)
- Word2vec and doc2vec
- Document similarity search
- Streaming large corpora
- Pretrained model downloader
Tags
Releases
+ Submit new release- Listed
Gensim was added to the directory.
Organization
Radim Řehůřek
🇨🇿 Czechia
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Free
- Paid options from
- 100% free
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top Gensim alternatives
View allModels & APIs
Open-source Python library for production natural language processing
Models & APIs
Open-source Python library of NLP models for QA, NER and classification
Models & APIs
Python and AI development platform with vetted packages and models
If you liked Gensim
Self-supervised method for embedding joint neural and behavior data
FreeData & analytics1 viewsMade in SwitzerlandOpen-source deep learning library that runs on JAX, PyTorch and TF
FreeModels & APIs4 views4 clicks to the websiteMade in United StatesOpen-source Python framework for ML and AI workflows
FreeModels & APIs38 views29 clicks to the website- LLMNew
Command-line tool and Python library for working with any LLM
FreeModels & APIsMade in United States Open-source Python library for building web demos of ML models
FreeModels & APIs1 viewsMade in United States
Pros and cons
Pros
- Handles corpora larger than memory
- Mature and well documented
- Free and open source
Cons
- Focused on classic NLP, not LLMs
- Python only
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is Gensim?
Gensim is an open-source Python library for training semantic NLP models such as word2vec, LSI and LDA on large text collections. Data scientists use it to turn documents into vectors and find related texts, even when the corpus does not fit in memory.
Can Gensim train word2vec models?
Yes. Gensim includes word2vec, doc2vec and fastText implementations and can train them on your own text.
Does Gensim work with large datasets?
Yes. It streams documents instead of loading them all into memory, and can read corpora from sources such as S3.
How much does Gensim cost?
Gensim is 100% free.
Is there a free version of Gensim?
Yes. Gensim is completely free to use.
What are the main features of Gensim?
Topic modelling (LDA, LSI), Word2vec and doc2vec, Document similarity search, Streaming large corpora, Pretrained model downloader.
Who makes Gensim?
Gensim is made by Radim Řehůřek.
What are the best alternatives to Gensim?
Popular alternatives include spaCy, DeepPavlov, TextBlob.