AI & LLMs
Vector search
Also known as: Nearest-neighbour search, ANN
Vector search finds the items whose embeddings are closest to a query embedding, ranking by meaning rather than exact word matches.
Vector search (also called nearest-neighbour or ANN search) ranks results by distance between embedding vectors. You embed the query, then ask the index for the vectors nearest to it.
Because it compares meaning rather than characters, vector search retrieves relevant results even when they share no keywords with the query. Specialized vector databases make this fast at scale using approximate nearest-neighbour indexes.
See also
Related terms
Last reviewed 2026-07-09