Skip to content
Sign in
All terms
Glossary · Term

Vector Search

L3 · AdvancedEvolving

In plain terms

Nearest-neighbour search over embeddings.

Technical definition

Finding the items whose vectors are closest to a query vector under a distance such as cosine; exact for small sets, or approximate (ANN, e.g. HNSW/IVF) at scale for speed.

Example

An index that returns the 10 nearest embeddings to a query in milliseconds.

Try it in the Vector Search Simulator labExplore in the AI Universe

Related terms