HNSW

HNSW (Hierarchical Navigable Small World) is an approximate nearest-neighbor algorithm introduced by Malkov and Yashunin in 2016, based on hierarchical small-world graphs. It is the most widely used index structure for vector search: it returns queries against millions of Embeddings in milliseconds. Its near-optimal balance between recall and speed has made it the default index in essentially every Vector Database — Pinecone, Weaviate, Qdrant, pgvector. IVF is the main alternative when memory budget is tight.