# Faiss

Faiss is a library for efficient similarity search and clustering of dense vectors. It is written in C++ with complete Python wrappers and can search sets of vectors that may not fit in RAM. Some of its algorithms run on the GPU, and it can store indexes on disk. It runs inside the calling process and is not a hosted service or a full vector database.

Page: https://slateindex.ai/brand/faiss · data of 2026-11-02

## Facts

- Founded: 2017
- Company type: Division of Meta Platforms
- Deployment: Self-hosted library that runs inside the calling process on a local machine.
- Best for: Developers who need fast vector search inside their own application and can handle low-level setup.

## Products

- Faiss: Open-source C++ library with Python wrappers for similarity search and clustering of dense vectors, with some algorithms on the GPU.
- faiss-cpu: CPU package for installing Faiss through Conda or PyPI.
- faiss-gpu: Package providing CUDA-enabled Faiss indexes, installed through Conda.

## Rankings

| Category | Rank | Visibility | Mentions |
|---|---|---|---|
| Vector Databases | 13 of 30 | 5.4 | 8 |

## By engine

| Engine | Visibility | Mention rate |
|---|---|---|
| chatgpt | 3.7 | 11.1% |
| google_ai_mode | 8.3 | 11.1% |
| perplexity | 4.1 | 7.4% |

## Definitions

- Visibility (0–100): how often and how high AI answers name the brand, weighted by position.
- Mention rate: share of collected AI answers that name the brand.
- Share of voice: the brand's mentions as a share of all brand mentions in the category.
- Citation authority: share of answers naming the brand that cite the brand's own site.

Cite as: SlateIndex, “Faiss AI visibility profile”, https://slateindex.ai/brand/faiss, data of 2026-11-02. Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/).