Agent Intermediate Steps Streaming

This example demonstrates how to stream intermediate steps during agent execution, providing visibility into tool calls and execution events.

Code

intermediate_steps.py

from typing import Iterator

from agno.agent import Agent, RunOutputEvent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from rich.pretty import pprint

agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[DuckDuckGoTools(stock_price=True)],
    markdown=True,
)

run_stream: Iterator[RunOutputEvent] = agent.run(
    "What is the stock price of NVDA", stream=True, stream_events=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.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Install libraries

   pip install -U agno openai ddgs rich
   
3. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Create a Python file

   Create a Python file and add the above code.

   touch intermediate_steps.py
   
5. Run Agent

   Mac

   python intermediate_steps.py
   
6. Find All Cookbooks

   Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

   Agno Cookbooks on GitHub