A library for efficient similarity search and clustering of dense vectors
Project Links
Meta
Author: Matthijs Douze, Jeff Johnson, Herve Jegou
Classifiers
Programming Language
- Python :: 2.7
- Python :: 3.5
- Python :: 3.6
- Python :: 3.7
Unofficial prebuilt binary for Linux and MacOS
The repo that builds this project can be found here: https://github.com/onfido/faiss_prebuilt
Original readme:
Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning. Faiss is written in C++ with complete wrappers for Python/numpy. Some of the most useful algorithms are implemented on the GPU. It is developed by Facebook AI Research.
Wheel compatibility matrix
| Platform | CPython 2.7 | CPython 3.5 | CPython 3.6 | CPython 3.7 | CPython (wide) 2.7 |
|---|---|---|---|---|---|
| macosx_10_13_x86_64 | |||||
| manylinux1_x86_64 |
Files in release
faiss-1.5.3-cp27-cp27m-macosx_10_13_x86_64.whl (1.0MiB)
faiss-1.5.3-cp27-cp27mu-manylinux1_x86_64.whl (4.5MiB)
faiss-1.5.3-cp35-cp35m-macosx_10_13_x86_64.whl (1.0MiB)
faiss-1.5.3-cp35-cp35m-manylinux1_x86_64.whl (4.4MiB)
faiss-1.5.3-cp36-cp36m-macosx_10_13_x86_64.whl (1.0MiB)
faiss-1.5.3-cp36-cp36m-manylinux1_x86_64.whl (4.4MiB)
faiss-1.5.3-cp37-cp37m-macosx_10_13_x86_64.whl (1.0MiB)
faiss-1.5.3-cp37-cp37m-manylinux1_x86_64.whl (4.4MiB)
Extras:
None
Dependencies:
numpy