Glossary · Phase 1 · Building with LLMs

Vector database

Also written: vector databases, vector store

A database built to store embeddings and quickly find the closest ones to a query.

Learn it properly

Vector databases · Store and search millions of embeddings quickly. About 25 minutes.

approximate nearest neighbor: Finding vectors that are very probably the closest, much faster than checking every one. Vector databases use it to search millions of items.
HNSW: A popular index for approximate nearest-neighbor search: a layered graph you hop through, from coarse links to fine ones, toward the closest vectors.