Vector Database
Also known as · vector store · vector DB
A database built to store embeddings and find the most similar ones fast.
A vector database stores embeddings — the numeric vectors that represent meaning — and is optimized to answer one kind of question very quickly: 'which stored vectors are most similar to this one?' Ordinary databases are bad at that; vector databases use specialized indexes to do it across millions of items in milliseconds.
They're the storage layer behind semantic search and retrieval-augmented generation. You embed your documents once, store the vectors, and at query time you embed the user's question and pull back the nearest matches to use as context.
Popular options include Pinecone, Weaviate, and pgvector (a Postgres extension). The right choice depends on scale, latency needs, and whether you want a managed service or to run it yourself.