Blog
Tutorials, guides, and insights on PostgreSQL, pgvector, and AI infrastructure.
pgvector with LlamaIndex: Build a RAG Pipeline on PostgreSQL
Learn how to use pgvector with LlamaIndex to build a production-ready RAG pipeline on PostgreSQL. Covers setup, document ingestion, querying, metadata filtering, and multi-document retrieval.
Building a RAG Application with pgvector and the OpenAI API
Build a production-ready RAG pipeline using pgvector and OpenAI embeddings, without LangChain. Covers chunking, embedding, storing vectors in PostgreSQL, retrieval, and answer generation with full Python code.
pgvector with Node.js: Build Semantic Search on PostgreSQL
Learn how to use pgvector with Node.js to store and query vector embeddings in PostgreSQL. Covers node-postgres, Drizzle ORM, OpenAI embeddings, HNSW indexes, and a complete RAG pipeline.
Hybrid Search with pgvector and PostgreSQL Full-Text Search
Learn how to combine pgvector semantic search with PostgreSQL full-text search for better results. Covers reciprocal rank fusion, scoring, and production patterns.
Supabase pgvector Alternative: When to Move Vector Search to Managed PostgreSQL
Compare Supabase pgvector with focused managed PostgreSQL for vector-heavy workloads, including cost, latency, HNSW tuning, and migration paths.
pgvector Hosting Guide: How to Choose Managed PostgreSQL for Vector Search
A practical pgvector hosting checklist for production teams: storage, memory, HNSW indexes, backups, high availability, pricing, and migration support.
pgvector HNSW Tuning on Managed PostgreSQL
Learn how to tune pgvector HNSW indexes on managed PostgreSQL, including ef_search, m, ef_construction, memory, filters, and storage latency.