Data & retrieval
Vector Database
A database optimised for storing and searching embeddings (numerical representations of text or images) by similarity.
01 ——
In plain English
A vector database stores data as high-dimensional vectors (lists of numbers) and lets you search by similarity rather than exact match. It's the storage layer that makes semantic search and RAG possible at scale.
How it works:
- You convert your documents into embeddings (vectors)
- Those vectors are stored in the vector database
- At query time, your question is also converted to a vector
- The database returns the stored vectors closest to your query vector
Popular vector databases:
- Pinecone, Weaviate, Qdrant, Milvus (dedicated vector DBs)
- pgvector (Postgres extension)
- Chroma (lightweight, local-friendly)
Without a vector database, RAG pipelines would be too slow to use in production.
02 ——
Related terms
Embeddings
A way of converting text (or images) into lists of numbers so an AI can measure how similar two pieces of content are.
RAG
Retrieval-Augmented Generation — a technique that gives an AI model access to external documents before it answers, so it can cite real, up-to-date sources.
Semantic Search
Search that finds results by meaning rather than exact keyword matches — so "car" finds results about "automobile" too.
Back to glossaryLast reviewed May 2026