FAISS

Faiss is a library for efficient similarity search and clustering of dense vectors, containing algorithms that search vector sets of any size, including sizes that may not fit in RAM. It also includes code for evaluation and parameter tuning. It is written in C++ with complete Python (numpy) wrappers, and some of the most useful algorithms are implemented on the GPU. It is developed mainly by Meta's Fundamental AI Research team (FAIR).

• k-nearest-neighbor search and batch search of multiple vectors
• Approximate search that trades accuracy for speed and memory
• Maximum inner product search and range search within a radius
• Stores the index on disk instead of RAM
• Binary vector indexing
• CUDA and AMD ROCm GPU support (single and multiple GPUs)
• Various index methods such as HNSW, NSG, and product quantization (PQ)

Open source + paid cloud-managed plans

Open-source self-hosting is free, managed cloud is priced by storage/query volume

Estimate based on AI knowledge - please verify on the official site

• One of 12 AI tools in the Vector & Search field.
• Connected to 2 other tools — #7 in its field.