gensim

Python framework for fast Vector Space Modelling

These details have not been verified by PyPI

Project links

Project description

Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora. Target audience is the natural language processing (NLP) and information retrieval (IR) community.

Features

All algorithms are memory-independent w.r.t. the corpus size (can process input larger than RAM, streamed, out-of-core)
Intuitive interfaces
- easy to plug in your own input corpus/datastream (simple streaming API)
- easy to extend with other Vector Space algorithms (simple transformation API)
Efficient multicore implementations of popular algorithms, such as online Latent Semantic Analysis (LSA/LSI/SVD), Latent Dirichlet Allocation (LDA), Random Projections (RP), Hierarchical Dirichlet Process (HDP) or word2vec deep learning.
Distributed computing: can run Latent Semantic Analysis and Latent Dirichlet Allocation on a cluster of computers.
Extensive documentation and Jupyter Notebook tutorials.

If this feature list left you scratching your head, you can first read more about the Vector Space Model and unsupervised document analysis on Wikipedia.

Installation

This software depends on NumPy and Scipy, two Python packages for scientific computing. You must have them installed prior to installing gensim.

It is also recommended you install a fast BLAS library before installing NumPy. This is optional, but using an optimized BLAS such as MKL, ATLAS or OpenBLAS is known to improve performance by as much as an order of magnitude. On OSX, NumPy picks up its vecLib BLAS automatically, so you don’t need to do anything special.

Install the latest version of gensim:

pip install --upgrade gensim

Or, if you have instead downloaded and unzipped the source tar.gz package:

python setup.py install

For alternative modes of installation, see the documentation.

Gensim is being continuously tested under all supported Python versions. Support for Python 2.7 was dropped in gensim 4.0.0 – install gensim 3.8.3 if you must use Python 2.7.

How come gensim is so fast and memory efficient? Isn’t it pure Python, and isn’t Python slow and greedy?

Many scientific algorithms can be expressed in terms of large matrix operations (see the BLAS note above). Gensim taps into these low-level BLAS libraries, by means of its dependency on NumPy. So while gensim-the-top-level-code is pure Python, it actually executes highly optimized Fortran/C under the hood, including multithreading (if your BLAS is so configured).

Memory-wise, gensim makes heavy use of Python’s built-in generators and iterators for streamed data processing. Memory efficiency was one of gensim’s design goals, and is a central feature of gensim, rather than something bolted on as an afterthought.

Documentation

Citing gensim

When citing gensim in academic papers and theses, please use this BibTeX entry:

@inproceedings{rehurek_lrec,
      title = {{Software Framework for Topic Modelling with Large Corpora}},
      author = {Radim {\v R}eh{\r u}{\v r}ek and Petr Sojka},
      booktitle = {{Proceedings of the LREC 2010 Workshop on New
           Challenges for NLP Frameworks}},
      pages = {45--50},
      year = 2010,
      month = May,
      day = 22,
      publisher = {ELRA},
      address = {Valletta, Malta},
      language={English}
}

Project details

These details have not been verified by PyPI

Project links

Release history Release notifications | RSS feed

This version

4.4.0

Oct 18, 2025

4.3.3

Jul 19, 2024

4.3.2

Aug 24, 2023

4.3.1

Mar 10, 2023

4.3.0

Dec 21, 2022

4.2.0

May 1, 2022

4.1.2

Sep 17, 2021

4.1.1

Sep 14, 2021

4.1.0

Aug 29, 2021

4.0.1

Apr 1, 2021

4.0.0

Mar 25, 2021

3.8.3

May 4, 2020

3.8.2

Apr 12, 2020

3.8.1

Sep 26, 2019

3.8.0

Jul 9, 2019

3.7.3

May 8, 2019

3.7.2

Apr 10, 2019

3.7.1

Jan 31, 2019

3.7.0

Jan 18, 2019

3.6.0

Sep 20, 2018

3.5.0

Jul 6, 2018

3.4.0

Mar 1, 2018

3.3.0

Feb 2, 2018

3.2.0

Dec 9, 2017

3.1.0

Nov 6, 2017

3.0.0

Sep 27, 2017

2.3.0

Jul 25, 2017

2.2.0

Jun 21, 2017

2.1.0

May 12, 2017

2.0.0

Apr 10, 2017

1.0.1

Mar 3, 2017

1.0.0

Feb 25, 2017

0.13.4

Dec 25, 2016

0.13.3

Oct 21, 2016

0.13.2

Aug 26, 2016

0.13.1

Jun 24, 2016

0.13.0

Jun 22, 2016

0.12.4

Jan 31, 2016

0.12.3

Nov 6, 2015

0.12.2

Sep 19, 2015

0.12.1

Jul 20, 2015

0.12.0

Jul 6, 2015

0.11.1

Apr 11, 2015

0.10.3

Nov 19, 2014

0.10.2

Sep 18, 2014

0.10.1

Jul 22, 2014

0.10.0

Jun 4, 2014

0.9.1

Apr 12, 2014

0.9.0

Mar 15, 2014

0.8.9

Dec 26, 2013

0.8.8

Nov 3, 2013

0.8.7

Sep 18, 2013

0.8.6

Sep 15, 2012

0.8.5

Jul 22, 2012

0.8.4

Mar 9, 2012

0.8.3

Dec 2, 2011

0.8.2

Oct 30, 2011

0.8.1

Oct 10, 2011

0.8.0

Jun 28, 2011

0.7.8

Mar 26, 2011

0.7.7

Feb 13, 2011

0.7.6

Jan 10, 2011

0.7.5

Nov 3, 2010

0.7.4

Sep 13, 2010

0.7.3

Sep 7, 2010

0.7.2

Sep 1, 2010

0.7.1

Aug 28, 2010

0.7.0

Aug 28, 2010

0.6.0

Jun 19, 2010

0.5.0

Apr 28, 2010

0.4.7

Apr 27, 2010

0.4.6

Apr 17, 2010

0.4.5

Apr 5, 2010

0.4.4

Mar 30, 2010

0.4.3

Mar 29, 2010

0.4.2

Mar 28, 2010

0.4.1

Mar 19, 2010

0.4

Mar 19, 2010

0.3.0

Mar 18, 2010

0.2

Mar 18, 2010

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gensim-4.4.0.tar.gz (23.3 MB view details)

Uploaded Oct 18, 2025 Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

gensim-4.4.0-cp313-cp313-win_amd64.whl (24.4 MB view details)

Uploaded Oct 18, 2025 CPython 3.13Windows x86-64

gensim-4.4.0-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (27.8 MB view details)

Uploaded Oct 18, 2025 CPython 3.13manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

gensim-4.4.0-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (27.7 MB view details)

Uploaded Oct 18, 2025 CPython 3.13manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

gensim-4.4.0-cp313-cp313-macosx_11_0_arm64.whl (24.4 MB view details)

Uploaded Oct 18, 2025 CPython 3.13macOS 11.0+ ARM64

gensim-4.4.0-cp313-cp313-macosx_10_13_x86_64.whl (24.5 MB view details)

Uploaded Oct 18, 2025 CPython 3.13macOS 10.13+ x86-64

gensim-4.4.0-cp312-cp312-win_amd64.whl (24.4 MB view details)

Uploaded Oct 18, 2025 CPython 3.12Windows x86-64

gensim-4.4.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (27.9 MB view details)

Uploaded Oct 18, 2025 CPython 3.12manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

gensim-4.4.0-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (27.8 MB view details)

Uploaded Oct 18, 2025 CPython 3.12manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

gensim-4.4.0-cp312-cp312-macosx_11_0_arm64.whl (24.5 MB view details)

Uploaded Oct 18, 2025 CPython 3.12macOS 11.0+ ARM64

gensim-4.4.0-cp312-cp312-macosx_10_13_x86_64.whl (24.5 MB view details)

Uploaded Oct 18, 2025 CPython 3.12macOS 10.13+ x86-64

gensim-4.4.0-cp311-cp311-win_amd64.whl (24.4 MB view details)

Uploaded Oct 18, 2025 CPython 3.11Windows x86-64

gensim-4.4.0-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (27.8 MB view details)

Uploaded Oct 18, 2025 CPython 3.11manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

gensim-4.4.0-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (27.8 MB view details)

Uploaded Oct 18, 2025 CPython 3.11manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

gensim-4.4.0-cp311-cp311-macosx_11_0_arm64.whl (24.5 MB view details)

Uploaded Oct 18, 2025 CPython 3.11macOS 11.0+ ARM64

gensim-4.4.0-cp311-cp311-macosx_10_9_x86_64.whl (24.5 MB view details)

Uploaded Oct 18, 2025 CPython 3.11macOS 10.9+ x86-64

gensim-4.4.0-cp310-cp310-win_amd64.whl (24.4 MB view details)

Uploaded Oct 18, 2025 CPython 3.10Windows x86-64

gensim-4.4.0-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (27.6 MB view details)

Uploaded Oct 18, 2025 CPython 3.10manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

gensim-4.4.0-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (27.6 MB view details)

Uploaded Oct 18, 2025 CPython 3.10manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

gensim-4.4.0-cp310-cp310-macosx_11_0_arm64.whl (24.4 MB view details)

Uploaded Oct 18, 2025 CPython 3.10macOS 11.0+ ARM64

gensim-4.4.0-cp310-cp310-macosx_10_9_x86_64.whl (24.5 MB view details)

Uploaded Oct 18, 2025 CPython 3.10macOS 10.9+ x86-64

gensim-4.4.0-cp39-cp39-win_amd64.whl (24.4 MB view details)

Uploaded Oct 18, 2025 CPython 3.9Windows x86-64

gensim-4.4.0-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (27.6 MB view details)

Uploaded Oct 18, 2025 CPython 3.9manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

gensim-4.4.0-cp39-cp39-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (27.6 MB view details)

Uploaded Oct 18, 2025 CPython 3.9manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

gensim-4.4.0-cp39-cp39-macosx_11_0_arm64.whl (24.4 MB view details)

Uploaded Oct 18, 2025 CPython 3.9macOS 11.0+ ARM64

gensim-4.4.0-cp39-cp39-macosx_10_9_x86_64.whl (24.5 MB view details)

Uploaded Oct 18, 2025 CPython 3.9macOS 10.9+ x86-64

File details

Details for the file gensim-4.4.0.tar.gz.

File metadata

Download URL: gensim-4.4.0.tar.gz
Upload date: Oct 18, 2025
Size: 23.3 MB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.11.13

File hashes

Hashes for gensim-4.4.0.tar.gz
Algorithm	Hash digest
SHA256	`a3f5b626da5518e79a479140361c663089fe7998df8ba52d56e1ded71ac5bdf5`
MD5	`17bc0b1e2f4bd50aae7a657f0abbb7d9`
BLAKE2b-256	`1a80fe9d2e1ace968041814dbcfce4e8499a643a36c41267fa4b6c4f54cce420`

Algorithm	Hash digest
SHA256	`6ecb7aed37fb92d24e15a6adbabe693074003263db0fd9ce97c9f4234a9edc1b`
MD5	`4c71ffb0d06782393d8770c0c30b0f9e`
BLAKE2b-256	`82f34f8f4d478ce69af812c6002b513c5ad3242976923d172dbe5814903be22f`

Algorithm	Hash digest
SHA256	`9033b18920b7774e68eafacdbd87252ffa29382ec465ddb88bd036e00fc86365`
MD5	`26bcfb62c0b92a5dce21d149b032a3d8`
BLAKE2b-256	`b3b9ee43ef9c391857232603a9ee281e9c5953f7922d70c98c2296a037d1c0b7`

Algorithm	Hash digest
SHA256	`3bec3e6a1ecaa6439b21a3e42ceb0ca67ffabc114b646f89b1aab5fe69a39ffc`
MD5	`2351a59c57876cd7bd6762056f14eec6`
BLAKE2b-256	`d9ef1675e1a3a04f7d0293a21082f57f4a6a8bf0a9e387da58b71db648b663de`

Algorithm	Hash digest
SHA256	`59d0d29099a76dd97d4563e002f3488a43e51f99d46387025da38007ebfeeff9`
MD5	`e1af2755dceb1237b4f5b4af4ccf18e2`
BLAKE2b-256	`cc6a593107ee98331128ed20e5d074865587558a0766659be787a40550ab66df`

Algorithm	Hash digest
SHA256	`b8961b7a2bb5190b46bc6cd26c29d5bfea22f99123ed5f506ebd0aaf65996758`
MD5	`4010c520b934ba93dd3d8b6654899dca`
BLAKE2b-256	`806c4e522973e07ca491d33cc7829996b9e8c8663a16b3f87f580cbdc2732d97`

Algorithm	Hash digest
SHA256	`b3a3f9bc8d4178b01d114e1c58c5ab2333f131c7415fb3d8ec8f1ecfe4c5b544`
MD5	`27911153bbf45bdd26f551e2f8e8db18`
BLAKE2b-256	`fdf29ec6863143888bf390cdc5261f6d9e71d79bc95d98fb815679dba478d5f6`

Algorithm	Hash digest
SHA256	`4b73ff30af6ddd0d2ddf9473b1eb44603cd79ec14c87d93b75291802b991916c`
MD5	`b91c61b682d582f4009ca45532185a88`
BLAKE2b-256	`972cc29701826c963b04a43d5d7b87573a74040387ab9219e65b10f377d22b5b`

Algorithm	Hash digest
SHA256	`23a2a4260f01c8f71bae5dd0e8a01bb247a2c789480c033e0eaba100b0ad4239`
MD5	`f9f005d02184d9af7e740ce14f5c17b9`
BLAKE2b-256	`f0b89b0ba15756e41ccfdd852f9c65cd2b552f240c201dc3237ad8c178642e80`

Algorithm	Hash digest
SHA256	`1853fc5be730f692c444a826041fef9a2fc8d74c73bb59748904b2e3221daa86`
MD5	`473eeb68636cf08664b3e7f6a61d3aec`
BLAKE2b-256	`3259f0ea443cbfb3b06e1d2e060217bb91f954845f6df38cbc9c5468b6c9c638`

Algorithm	Hash digest
SHA256	`0845b2fa039dbea5667fb278b5414e70f6d48fd208ef51f33e84a78444288d8d`
MD5	`b214371f03937335233db31f14a3b927`
BLAKE2b-256	`4f65d5285865ca54b93d41ccd8683c2d79952434957c76b411283c7a6c66ca69`

Algorithm	Hash digest
SHA256	`5e2c1d584d1c7d16b2a0fe7d2f6f59a451422df7b5edb7e3ca46c8e462782127`
MD5	`c8bcb9060f5b6a31accf41ac43bf42ff`
BLAKE2b-256	`10c37e22d6f7d88c4ea6a3a84481f00538252659d285713c3b7e2e1537b0e7e1`

Algorithm	Hash digest
SHA256	`91a7fa5e814e7b1bad4b2dffa8d62c1e55410d5cbdf930714c1997ffb4404db8`
MD5	`3837f1a564c35624d7eb23de3c99cc41`
BLAKE2b-256	`d9fa85531b39c1beb5a4203929ba83d94d886cec40d0fb0bef8ca05fd1cc7a38`

Algorithm	Hash digest
SHA256	`7e110e2d3533f5b35239850a96cb2016a586ecd85671d655079b3048332b7169`
MD5	`e720035c225092c7280a63e95460ca07`
BLAKE2b-256	`68886bd6919d31bdd473472ce1c18c24fcab5869b8b15166a424d11ce33a5eab`

Algorithm	Hash digest
SHA256	`05a027238b5eb544a17afe73ec227d6a7e0c6b4e2108b1131c0b8f291a0e0e2e`
MD5	`0109a3626dfc98e04d63c2053b4d99f4`
BLAKE2b-256	`387c18d40f341276a7461962512ca1fb716d5982db57615dfa272f651ecb96d7`

Algorithm	Hash digest
SHA256	`7590e7313848ca8f3ff064898bcd6ecf6ec71c752cf4d3ec83f7ac992bc7c088`
MD5	`b401f2ab45245294aa536b76d202b604`
BLAKE2b-256	`527b81b6c74b32700ee63f6720a60ca0c89ab59b12933257b47572c8af017658`

Algorithm	Hash digest
SHA256	`724b93c9b6e92cd15837048c71b7fdd38059276c85dd1f9c0375576f0aea153f`
MD5	`ada41205b53771783383093ca454c4b6`
BLAKE2b-256	`53fee483909cfbfa8cc4bfd30aa9fb5170c04316cc22f23c9906529f08fb9095`

Algorithm	Hash digest
SHA256	`d56613fcb77d4068c1be845843508dcd9d384ede34700a61bbeac32b947d1fc3`
MD5	`70b0930da00ca47e2b0a10f51cd1e86e`
BLAKE2b-256	`7a6e9b835483f776ad0ab6fd1197441000c4005b0a3219d456b25296966f0107`

Algorithm	Hash digest
SHA256	`f0977e5e5df03f829f322662e37ac973b93272c526f1432f865d214c0b573f98`
MD5	`bea4b45506ab2a42be336cc7b8f9e63b`
BLAKE2b-256	`a3d8ea8f98e198d8682c0d82cba04303d26f646ef2592a558739d812bfe02a3f`

Algorithm	Hash digest
SHA256	`5c4d8f2a5e69bc246931dfd8e03d0ce3f3bcf82adbbdbcf20dfc35c43b8e1035`
MD5	`368f7b21c045d257e4f2f48f32e201c6`
BLAKE2b-256	`ab2f46a661db005730de7455090cb980b70147f04a3d162b49171582987d634e`

Algorithm	Hash digest
SHA256	`e29a2109819fdf5ff59bef670c8c22c1690d52239fe172b43e408908871de5f6`
MD5	`d93fd1f12e8ae57aae409d3d82f23446`
BLAKE2b-256	`08881e7c7abf79cf88faca3d713fbb7068f58c9f44c77a3e72031cb3e40e43c3`

gensim 4.4.0

Navigation

Verified details

Project links

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

Features

Installation

How come gensim is so fast and memory efficient? Isn’t it pure Python, and isn’t Python slow and greedy?

Documentation

Citing gensim

Project details

Verified details

Project links

Maintainers

Unverified details

Project links

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

Algorithm	Hash digest
SHA256	`06704acd354728262f9f32a9435c70945930f8d11b58531b3cb5c699f4757ad4`
MD5	`17eef1a73fc8a9666f45a5577d3696a4`
BLAKE2b-256	`f189f9d895ce5773f467a9174ac5e4f0da20efa74a4b732626b5018f679e07bd`

Algorithm	Hash digest
SHA256	`120d58351f67ef38f3b102a724fb2ece298b20a06fbeae02797f18c1087591ca`
MD5	`95654e9273ffc89f3d4dab8af52586d8`
BLAKE2b-256	`46bb00d474f93413ad96600bf3aa26fd8a0b9b37f93de04d30997129ff573a54`

Algorithm	Hash digest
SHA256	`484286ff973c77d262776e44e0bc3b958331b7b0f5d61f83014f6cc12f1a814f`
MD5	`1c356d5ca106b817dc2d6e46078c75a9`
BLAKE2b-256	`cc3f8f93f37b3e784a4b3d9fd544ea1783afb5e2effeffb744b5566d0434bd6e`

Algorithm	Hash digest
SHA256	`54a32a196502bf0e376cd7ef935be97f7ca96cc0f90ee9514d48406b7bd21bad`
MD5	`9bc6aad225c1a61ff5b5f51fafc87bad`
BLAKE2b-256	`f02a4f564aab5b032078f66e9a109495825d67d06b6a5617269194c109ec634d`

Algorithm	Hash digest
SHA256	`de863f72b97ee142e7ce1c28da8f8e5473b76064ecbfe139da62127f46ab5c07`
MD5	`5a7d212b675f5bd54bfecbff07003134`
BLAKE2b-256	`84ea656913d4ea4fd775e420c8c1fbc501d8cffbd070656dcdd70bcfba3e6805`