Capturing Agent Response as Variable

This example demonstrates how to capture and work with agent responses as variables, enabling programmatic access to response data and metadata.

Code

response_as_variable.py

from typing import Iterator  # noqa
from rich.pretty import pprint
from agno.agent import Agent, RunOutput
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools


agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[
        DuckDuckGoTools(
            stock_price=True,
            analyst_recommendations=True,
            company_info=True,
            company_news=True,
        )
    ],
    instructions=["Use tables where possible"],
    markdown=True,
)

run_response: RunOutput = agent.run("What is the stock price of NVDA")
pprint(run_response)

# run_response_strem: Iterator[RunOutputEvent] = agent.run("What is the stock price of NVDA", stream=True)
# for response in run_response_strem:
#     pprint(response)

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 response_as_variable.py
   
5. Run Agent

   Mac

   python response_as_variable.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