Faiss

FAISS is Meta's battle-tested vector similarity search library, and it's what you reach for when you need to handle millions or billions of vectors without everything grinding to a halt. It's pure similarity search, no metadata filtering or fancy database features, just blazing fast k-NN powered by C++ with GPU support that can give you 10-100× speedups. The index variety is solid: Flat for exact search, IVF for speed, HNSW for best quality-to-speed ratio, and PQ when memory gets tight. It integrates cleanly with LangChain and LlamaIndex, and with 31,700+ GitHub stars, you're not exactly beta testing here. If you need metadata filtering alongside search, grab Chroma or Pinecone instead. For pure vector retrieval at scale, this is the standard.