faiss

A library for efficient similarity search and clustering of dense vectors.

View on GitHub↗Upstream facebookresearch/faiss↗

Builder

Meta Research

facebookresearch • ai-lab

Stars

39,587

Using upstream star count

Forks

4,311

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Feb 7, 2017

Project creation date

README Summary

Faiss is a library developed by Facebook Research for efficient similarity search and clustering of dense vectors. It provides both exact and approximate nearest neighbor search algorithms optimized for large-scale datasets. The library supports GPU acceleration and is available in multiple programming languages including Python and C++.

AI Dev Skills

Unmapped

Tags

Vector Similarity SearchApproximate Nearest Neighbors (ANN)High-Dimensional Vector IndexingVector ClusteringGPU-Accelerated ComputingMemory-Efficient AlgorithmsLarge-Scale Vector DatabasesVector QuantizationEmbedding SearchDense Vector RetrievalInformation Retrieval SystemsSelf-hostedContent-Based FilteringDocument RetrievalLarge-Scale AI InfrastructureImage Similarity SearchImage EmbeddingsCloud APIDuplicate DetectionDense VectorsMultimodal EmbeddingsOn-premiseSemantic SearchRetrieval-Augmented GenerationGPU-Accelerated AIText EmbeddingsVector DatabasesLarge-Scale ClusteringVector Database OperationsRecommendation SystemsGPU ClustersEmbedding-based SearchEmbedding-based AIC++

Recent Activity

Updated 23 days ago

7 Days

30 Days

90 Days

Quality

production

Quality: high
Maturity: production

PM Skills

Developer Platform

Languages

C++100.0%

Timeline

Project created: Feb 7, 2017
Forked: Mar 22, 2026
Your last push: 23 days ago
Upstream last push: 7 days ago
Tracked since: Mar 21, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…