Skip to main content
This example shows how to use intermediate steps in an agent.

​
Code

cookbook/agent_concepts/other/intermediate_steps.py
from typing import Iterator
from agno.agent import Agent, RunResponse
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from rich.pretty import pprint

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    tools=[DuckDuckGoTools(search=True, news=True)],
    markdown=True,
    show_tool_calls=True,
)

run_stream: Iterator[RunResponse] = agent.run(
    "What are the latest developments in renewable energy?", stream=True, stream_intermediate_steps=True
)
for chunk in run_stream:
    pprint(chunk.to_dict())
    print("---" * 20)

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2

Set your API key

export OPENAI_API_KEY=xxx
3

Install libraries

pip install -U openai agno ddgs rich
4

Run Agent

python cookbook/agent_concepts/other/intermediate_steps.py