vectors

What problem does it solve?

Persisting high-dimensional representations in a database enables fast similarity search, semantic retrieval, and retrieval-augmented generation over large corpora without leaving the data layer.

Core Features & Use Cases

• Store embeddings in vector(N) columns using the pgvector extension
• Build and query HNSW indexes for fast, scalable similarity search
• Enable RAG pipelines and semantic search across documents, images, or other content

Quick Start

Embed a sample text, store the embedding in a vector column, and query with another embedding to retrieve similar documents.