This post was originally published on Rivestack .

Most pgvector tutorials are written for Python. That makes sense: Python dominates the AI tooling ecosystem and most RAG frameworks are Python-first. But a large share of production web applications are built with Node.js, and those applications need vector search too. If you are building an API with Express, a full-stack app with Next.js, or a background worker with plain Node.js, this guide has everything you need to get pgvector working.

We will cover connecting with node-postgres , inserting and querying embeddings, building an HNSW index, and wiring it all into a functional RAG pipeline.…