Building Agentic RAG From Scratch in Pure Python
Want to start freelancing? Let me help: https://go.datalumina.com/HbJnpc8 Want to learn real AI Engineering? Go here: https://go.datalumina.com/XlYLRjP 🔗 GitHub Repository https://github.com/daveebbelaar/ai-cookbook/tree/main/knowledge/agentic-rag ⏱️ Timestamps 00:00 Introduction to Agentic RAG 00:48 Semantic vs. Agentic RAG 02:12 Tool Definitions and Setup 04:11 Listing Files 06:01 Searching for Patterns 10:19 Reading Files 12:37 Building the Agent 13:31 Debugging the Agent 18:34 Structured Output 20:33 Production Considerations 25:19 Conclusion and Next Steps 📌 Description Learn how to build an agentic RAG system from scratch in pure Python without relying on heavy frameworks. This tutorial walks through creating custom tools for listing, searching, and reading markdown files, then connecting them to an AI agent using Pydantic AI for iterative tool calling and self-correction. Whether you're moving past basic semantic RAG or integrating private company data into LLMs, this hands-on guide covers the full workflow from core code to production deployment. 👋🏻 About Me Hi! I'm Dave, AI Engineer and founder of Datalumina®. On this channel, I share practical tutorials that teach developers how to build production-ready AI systems that actually work in the real world. Beyond these tutorials, I also help people start successful freelancing careers. Check out the links above to learn more!
