Glossary
Vector database
A store optimized for similarity search over embeddings.
What it is
A vector database indexes embeddings and returns the nearest vectors to a query using approximate nearest-neighbor search. It's the retrieval layer in most RAG systems (e.g. pgvector, Pinecone, Qdrant, Weaviate).
Why it matters in production
This is a production choice, not a toy one: it determines your metadata filtering, backup story, latency, and operational load. If you already run Postgres, pgvector often removes a whole service from your stack.
In practice
Storing document chunk embeddings in pgvector and querying with ORDER BY embedding <=> $queryEmbedding LIMIT 8, with a WHERE clause on tenant metadata.
Related terms
Production AI Notes
One practical AI engineering email each week
One concept, one architecture, one project idea, and one interview question — written for developers who want to build and ship real AI systems.