All terms
Patterns
Vector Database
A database optimized for storing embeddings and finding nearest neighbors fast.
Definition
A vector database stores embeddings — long lists of numbers that capture the meaning of text, images, or other data — and quickly finds the items whose numbers are closest to a query, meaning closest in meaning. It is the search backbone of most retrieval-based (RAG) systems. Examples include Pinecone, Weaviate, Milvus, Qdrant, and pgvector.