Agents#
An “agent” is an automated reasoning and decision engine. It takes in a user input/query and can make internal decisions for executing that query in order to return the correct result. The key agent components can include, but are not limited to:
Breaking down a complex question into smaller ones
Choosing an external Tool to use + coming up with parameters for calling the Tool
Planning out a set of tasks
Storing previously completed tasks in a memory module
Research developments in LLMs (e.g. ChatGPT Plugins), LLM research (ReAct, Toolformer) and LLM tooling (LangChain, Semantic Kernel) have popularized the concept of agents.
Agents + LlamaIndex#
LlamaIndex provides some amazing tools to manage and interact with your data within your LLM application. And it is a core tool that you use while building an agent-based app.
On one hand, many components within LlamaIndex are “agentic” - these make automated decisions to help a particular use case over your data. This ranges from simple reasoning (routing) to reasoning loops with memory (ReAct).
On the other hand, LlamaIndex can be used as a core Tool within another agent framework.
Resources#
If you’ve built a RAG pipeline already and want to extend it with agentic behavior, check out the below resources
If you want to check out our standalone documentation hubs on agents and tools, check out the following module guides: