AI Glossary / Vector database
⚙️ Technical
Vector database
A database storing embeddings and instantly finding semantically similar content.
A vector database is a database specialized in storing embeddings and instantly finding vectors most similar to a query. Instead of asking "where does word X appear", you ask "what means roughly the same as X". It's the engine powering RAG systems: company documents are split into fragments, converted to embeddings and stored in a vector database, and when a user asks a question, semantically matching fragments are retrieved and given to the model as context.