Skip to content

HNSW Index

An indexing method that uses a hierarchical graph structure for fast approximate neighbor search in high-dimensional vectors.

HNSW is one of the most widely used indexing strategies in modern vector search systems. It builds a multi-layer graph of neighborhood relationships among vectors, significantly reducing search time. This structure provides a strong balance between retrieval quality and speed. It becomes especially critical for scalable retrieval across large embedding collections. HNSW is one of the key data structures behind vector database performance.