Agentic strategies

You can build agents on top of your existing LlamaIndex RAG pipeline to empower it with automated decision capabilities. A lot of modules (routing, query transformations, and more) are already agentic in nature in that they use LLMs for decision making.

Simpler Agentic Strategies

These include routing and query transformations.

• Routers
• Query Transformations
• Sub Question Query Engine (Intro)

Data Agents

This guides below show you how to deploy a full agent loop, capable of chain-of-thought and query planning, on top of existing RAG query engines as tools for more advanced decision making.

Make sure to check out our full module guide on Data Agents, which highlight these use cases and much more.

Our lower-level agent API shows you the internals of how an agent works (with step-wise execution).

Example guides below (using OpenAI function calling):

• Build your own OpenAI Agent
• OpenAI Agent with Query Engine Tools
• Retrieval-Augmented OpenAI Agent
• OpenAI Agent + Query Engine Experimental Cookbook
• OpenAI Agent Query Planning
• Context-Augmented OpenAI Agent