# Vector Database

> A vector database stores data as high-dimensional numerical embeddings and retrieves items by semantic similarity rather than exact keywords. It's the memory layer behind semantic search and RAG.

*Source: https://www.lazlosoftwaresolution.com/glossary/vector-database*

Vector databases (e.g. Pinecone, Weaviate, pgvector) index embeddings so you can ask "what is similar in meaning to this?" — the foundation of semantic search, recommendations and retrieval-augmented AI.