Understanding Agentic RAG

In this video, Trevor LaViale, ML Solutions Engineer at Arize, introduces Agentic RAG and its applications for enhancing AI-powered retrieval systems. Learn how Agentic RAG differs from standard RAG by incorporating AI agents to intelligently manage queries across multiple data sources. Whether you’re a developer working on complex applications or someone curious about improving AI workflows, this tutorial offers a clear walkthrough of the concepts and practical implementation.

0:00 Introduction to Agentic RAG
2:55 Building an Agentic RAG Application
3:55 Demo Starts

🛠 Tools & Frameworks Covered:
In this example, we build an Agentic RAG system using LlamaIndex with a Chroma vector database, and a Postgres database. We use Phoenix for observability, tracing queries, and debugging retrieval results.

🎥 Why Watch?
This video is a quick and practical guide to building intelligent retrieval systems with just 50 lines of code! You’ll also get a hands-on look at improving retrieval workflows and the importance of observability in AI applications.

🖱️ Next Steps: