Glossary · 4 · Grounding: content, retrieval and knowledge

Vector database

Also known as: Vector store, Vector index

A vector database stores embeddings together with their source content and metadata and finds the entries most similar to a query vector quickly, which makes it the usual retrieval layer of semantic search and RAG systems.

Intermediate
Technical project managers
Developers

In one sentence

Vector databases explained: storing embeddings and finding similar content fast — the retrieval layer of most RAG systems.

Example

A support assistant turns a user question into an embedding, queries the vector database for the eight closest documentation chunks, filtered by product variant, and passes them to the model.

Why it matters on your learning path

Technical project managers: Many existing databases and search engines now offer vector search; a dedicated product isn’t always needed.
Developers: Store metadata (product, version, audience, language) with each vector so retrieval can filter — this is where iiRDS metadata pays off.