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.
Explained in context
Context cards connect this term with others to answer one question. Also in British English and German.
- Semantic platform operator: the functional roleWho runs the graphs, the inference, the semantic view and the vector index — and keeps them in step with the approved model?UKDeutsch
- From knowledge graphs to adaptive semantics: the pathway mapHow does a DITA and iiRDS knowledge architecture get from governed semantics to a model that learns from AI agent use — and who does what on the way?UKDeutsch
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.