IVF Vector Search: Search Fewer Vectors
Brute-force vector search compares every embedding. How an IVF index partitions vectors into cells, probes only the nearest, and where the nprobe knob bites.
Brute-force vector search compares every embedding. How an IVF index partitions vectors into cells, probes only the nearest, and where the nprobe knob bites.
HNSW makes vector search fast, but the embeddings still fill your RAM. Product quantization compresses them ~32x with a small recall hit. Here is how it works.