Glossary
What is a vector database?
A database built to store embeddings and quickly find the vectors nearest to a query — the retrieval half of a RAG system at scale. It uses an index to avoid comparing against every stored vector on each search.
Once text is turned into embeddings — points in space — you need somewhere to keep millions of them and a fast way to ask “which points are nearest to THIS one?”. A vector database is built exactly for that: nearest-neighbour search, not exact matches.
A question, and its nearest matches
Ask in plain words — it returns the closest MEANINGS (refunds, returns, pricing), not keyword matches, and skips the unrelated ones.
That's the retrieval half of semantic search and RAG: embed the question, fetch the nearest stored chunks, and hand them to the model as grounding so the answer stays on your facts.
Related terms
Appears in these lessons
Search by meaning
Find the nearest neighbours
RAG & Search builds the whole retrieve-then-answer pipeline — free to try in the app.