What is vector database?

A vector database indexes high-dimensional embedding vectors and answers nearest-neighbour queries: given a query vector, return the most semantically similar stored items. This is the retrieval engine behind semantic search, recommendations, and RAG pipelines.

Open-source options range from purpose-built vector stores to vector extensions bolted onto existing databases. The trade-offs are recall vs. latency, index type (HNSW, IVF), and how well it scales with your corpus.

Best vector databases →