# Faiss

> Faiss (Facebook AI Similarity Search) is a library for efficient similarity search/ clustering of dense vectors, supports GPU/CPU indexes like IVF, PQ, HNSW. Core for building custom VDBs; compares to Annoy by higher perf/scalability. Features: quantization, exact search.

- **URL:** https://faiss.ai/
- **Category:** ANN Indexing Libraries
- **Tags:** Ann Library, Gpu Support
- **Updated:** 2026-04-30 11:38
- **Canonical page:** https://vectordb.ever.works/it/items/faiss

## Details

## Overview

FAISS (Facebook AI Similarity Search) is an open-source library for efficient similarity search and clustering of dense vectors at billion-scale.

## Features

- Multiple index types: Flat, IVF, PQ, HNSW, and more
- GPU/CPU support with CUDA acceleration
- Quantization (PQ, SQ) for memory efficiency
- C++ core with Python bindings
- Built-in clustering (k-means, etc.)

## Use Cases

- Embedding search prototypes
- Recommendation systems
- Large-scale image/video retrieval

## Comparisons

Lower-level than complete vector DBs like Qdrant or Milvus; powers indexing in many production vector stores.

## Pricing

Free, open-source (MIT license).

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/it/items/faiss._