Postgres RAG Stack: Embedding, Chunking & Vector Search

This is Part 2 of a three-part series (links at the bottom). The GitHub repo can be checked out here.

Postgres RAG Stack brings together Postgres, pgVector, and TypeScript to power fast, semantic search. In Part One, we covered the theory behind semantic search: how embeddings convert meaning into vectors, how vector databases and indexes enable fast similarity search, and how RAG combines retrieval with language models for grounded, accurate responses. In this guide, you’ll scaffold your project, set up Docker with pgVector, and build ingestion and query scripts for embedding and chunking your data.

Now we will begin setting up the foundation for our RAG application:

• Next.js 15 project scaffold with environment files and directory layout
• PostgreSQL 17 + pgvector in a Docker container
• content_chunks table with an HNSW index
• An ingestion script that chunks any text corpus and stores embeddings
• Commands to validate cosine search plus troubleshooting ...