🔬 Core Vector Search Libraries (The Math & Algorithms)
- FAISS (
facebookresearch/faiss): Developed by Meta AI Research, Faiss (Facebook AI Similarity Search) is the gold-standard library for efficient similarity search and clustering of dense vectors. It contains algorithms that search sets of vectors of any size, including those that may not fit in RAM, with excellent GPU acceleration.
👉 facebookresearch/faiss GitHub Repository [1, 2, 3, 4, 5] - USearch (
unum-cloud/usearch): A smaller, faster, single-header alternative to Faiss designed for hardware-accelerated neighborhood search. It is highly optimized for modern CPU and GPU architectures.
👉 unum-cloud/usearch GitHub Repository [1, 2, 3]