Skip to main content

AI courses

Building Agentic RAG with LlamaIndex

A focused DeepLearning.AI course on building agentic retrieval-augmented generation workflows with the LlamaIndex framework.

Provider
DeepLearning.AI
Level
Beginner

About

Building Agentic RAG with LlamaIndex is a short developer course that combines retrieval-augmented generation with agentic workflow design in the LlamaIndex framework. It is more specific than a general RAG explanation: learners approach retrieval through the decisions an agent can make inside an application workflow. The recommendation profile expects basic coding comfort, making this a practical next step for developers who already understand the purpose of RAG. Its narrow framework and short-course scope do not provide a complete survey of retrieval architectures or production deployment practices.

View course on provider website

Opens an external website in a new tab.

Learning Outcomes

  • ✓Explain how agentic decisions can extend a retrieval-augmented generation workflow
  • ✓Relate LlamaIndex framework concepts to the construction of an agentic RAG application
  • ✓Distinguish a focused framework implementation from broader RAG architecture and production work

Syllabus

1. RAG and agentic context

Connects the purpose of retrieval-augmented generation with the additional choices introduced by an agentic workflow.

2. Building with LlamaIndex

Places the implementation inside LlamaIndex and focuses on how a developer can structure an agentic retrieval workflow.

3. Architecture boundaries

Identifies what the focused example covers and what remains for wider architecture comparison, evaluation, and deployment.

Skills Covered

🧠 Agentic RAG🧠 LlamaIndex🧠 Retrieval-Augmented Generation