AI glossary
Vector search
Vector search finds the stored items whose embeddings are closest to the embedding of a query, so it matches by meaning rather than by exact words.
You embed every document chunk once and store the vectors. At question time you embed the question and ask for the nearest few vectors, usually by cosine similarity.
Over millions of vectors an exact search is slow, so vector stores use approximate indexes that are much faster and occasionally miss a close match.
Meaning search is weak on exact strings: an error code, a part number or a rare name. That is why many systems pair it with keyword search.
Learn it hands-on
These free lessons teach it with commands to run in a lab and checked tasks. Read them whole with no account.