This tutorial demonstrates a fully integrated workflow that sets up a Retrieval-Augmented Generation (RAG) agent using a relational database and a vector store. In the video, Nate Herk shows how to configure Postgres as chat memory and Supabase as a vector database using PG Vector for similarity search. The system is implemented within n8n by establishing credentials, configuring both database and tool nodes, and leveraging recursive text splitting for document ingestion. Detailed technical steps include setting up Supabase, connecting to Postgres, and embedding documents for AI-driven query responses.

Category: