Implementing a Structured Planning AI Agent with LlamaIndex

1. Set up the environment
   • Skip this step if you have already set up the environment
   bash

   1python -m venv .venv 2source .venv/bin/activate
2. Setup LlamaIndex
   pip install llama-index
3. Create a python file
   touch worker.py
   Or
   echo. > worker.py
4. Open the file in VSCode
   code worker.py
5. Add the needed imports
   python

   1from llama_index.core.tools import FunctionTool 2from llama_index.llms.openai import OpenAI 3from llama_index.core.agent import ( 4 StructuredPlannerAgent, 5 FunctionCallingAgentWorker, 6)
6. Define the function
   python

   1def multiply(a: int, b: int) -> int: 2 """Multiply two integers and returns the result integer""" 3 return a * b
7. Define and configure the worker agent
   python

   1multiply_tool = FunctionTool.from_defaults(fn=multiply) 2llm = OpenAI(model="gpt-4o-mini") 3worker = FunctionCallingAgentWorker.from_tools([multiply_tool], llm=llm, verbose=True) 4worker_agent = StructuredPlannerAgent(worker, [multiply_tool], verbose=True)
8. Test the worker agent
   worker_agent.chat("Solve the equation x = 123 * (x + 2y + 3)")
9. Create .env file & add api key
   OPENAI_API_KEY="<your_api_key>"
10. Run the agent