langchain/docs/extras/integrations/providers/facebook_faiss.mdx
Leonid Ganeline e1f4f9ac3e
docs: integrations/providers (#9631)
Added missed pages for `integrations/providers` from `vectorstores`.
Updated several `vectorstores` notebooks.
2023-08-22 20:28:11 -07:00

33 lines
817 B
Plaintext

# Facebook Faiss
>[Facebook AI Similarity Search (Faiss)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/)
> 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 documentation](https://faiss.ai/).
## Installation and Setup
We need to install `faiss` python package.
```bash
pip install faiss-gpu # For CUDA 7.5+ supported GPU's.
```
OR
```bash
pip install faiss-cpu # For CPU Installation
```
## Vector Store
See a [usage example](/docs/integrations/vectorstores/faiss).
```python
from langchain.vectorstores import FAISS
```