← Glossary

Glossary

Vector database

A vector database stores data as embeddings and retrieves it by semantic similarity — finding the items closest in meaning to a query rather than matching keywords. It is the common backbone of retrieval in RAG systems.


When a RAG system retrieves, it embeds the query and asks the vector database for the nearest passages. Most production systems combine vector search with keyword search and re-ranking.

Vector search excels at fuzzy, semantic recall over unstructured text; a knowledge graph is the complement when explicit relationships and multi-hop reasoning matter.

Related terms

Learn more