Description
Building Agentic RAG with LlamaIndex is a course offered by DeepLearning.AI, designed to teach participants how to create autonomous agents capable of navigating and analyzing data intelligently. The course is led by Jerry Liu, co-founder and CEO of LlamaIndex, and focuses on developing agentic RAG systems. Participants will learn to build a router agent that can handle Q&A and summarization tasks, and extend it to manage argument passing. The course also covers designing a research agent for multi-document handling and debugging. Unlike standard RAG pipelines, this approach adapts based on initial findings to enhance data retrieval. Participants will practice building agents that can navigate, summarize, and compare information across multiple research papers from arXiv. The course is suitable for anyone with basic Python knowledge looking to quickly build agents that can reason over documents. The course includes 6 video lessons, 4 code examples, and 1 graded assignment, all accessible for free during the DeepLearning.AI platform beta.
- CategoryEducation & Research
- Pricing ModelFree
Building Agentic RAG with LlamaIndex's Core Features
Build autonomous agents with LlamaIndex
Develop agentic RAG systems
Enable document Q&A and summarization
Guide agent reasoning and debugging
Design a router agent for Q&A tasks
Extend agents for argument passing
Create research agents for multi-document handling
Practice with real-world data from arXiv
How to use Building Agentic RAG with LlamaIndex?
Learn: Watch video lessons
Practice: Complete code examples
Apply: Build agents using LlamaIndex
Debug: Guide agent actions effectively
Building Agentic RAG with LlamaIndex's Use Cases
- Document Q&A
- Data Summarization
- Multi-Document Analysis
- Agent Debugging
- Research Assistance
