pgvector adds vector data types and similarity search to PostgreSQL. Store embeddings alongside relational data without a separate vector database. Supports L2, inner product, and cosine distance. IVFFlat and HNSW indexes accelerate approximate nearest neighbor search. Ideal for RAG, recommendation, and semantic search.
The 5-Mode Loop
5 of 5 modes available
Read · See · Animate · Test · Build
Before this, understand: postgresql
Where this topic shows up outside its home domain: