02 / Sessions & Context
Vector database
A database built to store embeddings and find the closest matches quickly. Usually the search engine inside a RAG system.
How you’ll hear it
“Where do the documents actually live?”
“Split into passages, stored as embeddings in a vector database.”
Avoid
Assuming you need specialist infrastructure before you have a working prototype.
The longer version
A vector database stores embeddings and retrieves the ones closest to a query. It is a common building block for retrieval, and many ordinary databases now offer the same capability, so it is often a feature rather than a separate purchase.