← Concept IndexDEFINITION WHY IT MATTERS COMMONLY CONFUSED WITH
Embeddings & vector search
Also called: semantic search, vector database
An embedding turns text into a list of numbers that captures its meaning, so passages with similar meaning sit close together. Retrieval finds relevant text by nearness in that space, not by keyword match.
It's why a good system can find the right passage even when your words differ from the document's. It also explains failure: if meaning is captured poorly, retrieval returns plausible-but-wrong context.
Keyword search. Embeddings match on meaning, which is more flexible but can also miss exact terms that a keyword search would catch.