domains / families / data / faiss

faiss

separate

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

When to use

• Need fast similarity search on large vector datasets (millions/billions)
• GPU acceleration required
• Pure vector similarity (no metadata filtering needed)
• High throughput, low latency critical
• Offline/batch processing of embeddings
• **31,700+ GitHub stars**
• Meta/Facebook AI Research
• **Handles billions of vectors**

When not to use

• tasks requiring metadata filtering
• tasks requiring full database features
• simpler tasks with fewer feature requirements

Skill page

Source