Vector Databases

A vector database stores embeddings and finds the most similar ones fast, making it the memory layer behind semantic search and RAG.

Vector search finds the stored items whose embeddings are closest to a query embedding — the nearest-neighbor operation behind semantic search.

Exact search compares every vector and is always right but slow; approximate (ANN) search checks a smart subset for huge speed with a small recall trade-off.

HNSW is a graph-based ANN index that searches from sparse top layers down to dense bottom layers, giving fast, high-recall nearest-neighbor search.

IVF narrows search to a few clusters; Product Quantization compresses vectors into compact codes — together they make billion-scale vector search fit in memory.

Metadata filtering restricts vector search to items matching structured rules (tags, dates, permissions), so results are both semantically relevant and valid.

Hybrid search combines dense (semantic) and sparse (keyword) retrieval and fuses their rankings, getting meaning-based recall plus exact-term precision.