Retrieval Augmented Generation (RAG): From Zero to Practical

About this course

Retrieval Augmented Generation (RAG): From Zero to Practical

Retrieval Augmented Generation (RAG) is an important technique for building AI applications that can work with your own documents and knowledge bases. In this course, we'll explore how RAG works and build practical workflows using n8n, Supabase, embedding models, and vector databases.

We'll start with the fundamentals and gradually move into hands-on projects. I'll explain each concept in a simple, practical way so you can understand what's happening behind the scenes rather than just connecting nodes and hoping everything works.

What You'll Learn

Understand RAG fundamentals and how it enhances AI applications.

Learn how document ingestion, text splitting, embeddings, and vector storage work together.

Understand how retrieval pipelines find relevant information from a knowledge base.

Build practical RAG workflows using n8n.

Integrate Supabase as a vector database to store and retrieve document embeddings.

Connect Google Drive to use your documents as a knowledge base.

Configure embedding models and understand their role in RAG.Test your workflows and improve the relevance of AI-generated responses.

Update an existing knowledge base safely.

Publish tested workflows for production use.

Monitor and troubleshoot document chunking, embedding, and retrieval operations.

Hands-On Projects

Project 1: Building RAG with a Simple Vector Store

Learn to build ingestion and retrieval pipelines, process documents, store embeddings, and retrieve relevant information to generate responses.

Project 2: Building RAG with Supabase

Take your learning further by integrating Supabase as your vector database.

Read the full description on Udemy on Udemy (opens in a new tab)

Prices, discounts and availability are set by Udemy. We may earn a commission when you purchase through links on this site.