1. Home
  2. Glossary
  3. Vector database
AI glossary · Models & training

Vector database

Vector database: A vector database stores embeddings, the numeric representations of text, images, or other content, and finds the items closest in meaning to a query quickly. It is the storage layer behind semantic search and most document-aware AI assistants.

Once your documents are converted to embeddings, you need somewhere to keep millions of these numeric vectors and a fast way to ask 'which ones are nearest to this new vector?' That nearest-neighbor search is what a vector database is built for. A regular database can filter by exact values; a vector database ranks by similarity.

Products in this space include dedicated services such as Pinecone, Weaviate, Qdrant, and Milvus, plus extensions like pgvector that add vector search to a standard Postgres database. Many teams start with the extension because they already run Postgres.

The database is only as good as what you put in it. Chunking documents sensibly, keeping metadata like source, date, and department attached to each vector, and re-indexing when documents change all matter more than which product you pick. Stale vectors return stale answers.

Example at work

A law firm's knowledge team indexes ten years of internal memos and precedent summaries into a vector database with metadata for practice area and date. Attorneys ask questions in plain language, retrieve the closest passages, and get citations back to the original documents, all inside a tool the firm controls for confidentiality.

Why it matters

If your company builds or buys a document-aware AI assistant, a vector database will be part of it. Knowing what it does helps you ask practical questions about what gets indexed, how often it refreshes, and who can see which documents.

Related terms