Vector databases store embeddings — fixed-length numerical representations of text or other content — and retrieve nearest-neighbours efficiently. Used in RAG, semantic search, recommendation. Common 2026 choices for self-hosted setups: Postgres with pgvector (simplest), Qdrant (fast), Chroma (Python-friendly).
Related terms
Found a definition that's wrong, dated or could be sharper? Email us — we update with attribution unless you'd rather we didn't.