FAISS
A library for efficient similarity search and clustering of dense vectors, scaling to billions of vectors on a single server.
What is FAISS?
Faiss is a library for efficient similarity search and clustering of dense vectors. It solves the problem of quickly finding similar vectors in large datasets, which is fundamental to applications like recommendation systems, image retrieval, and natural language processing. The library scales to billions of vectors and supports both CPU and GPU acceleration.
Machine learning engineers, data scientists, and researchers working with large-scale vector embeddings who need fast and scalable similarity search or clustering capabilities.
Developers choose Faiss for its performance—it offers some of the fastest known implementations for exact and approximate nearest neighbor search, especially on GPUs. Its flexibility in supporting various algorithms and trade-offs makes it suitable for a wide range of production and research scenarios.
Overview
A library for efficient similarity search and clustering of dense vectors.
Use Cases
Best For
- Building recommendation systems that require fast nearest neighbor lookups
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
