Glossary · Phase 1 · Building with LLMs

Approximate nearest neighbor

Also written: approximate nearest-neighbor, ANN, approximate nearest neighbors

Finding vectors that are very probably the closest, much faster than checking every one. Vector databases use it to search millions of items.

Try it now

Start with the simplest one that works, and move up when the numbers force you to.

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

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

Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.