Skip to main content
Use output_schema to ensure team responses are structured as Pydantic models. This provides type-safe, validated output.

​
Code

pydantic_model_output.py
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.yfinance import YFinanceTools
from pydantic import BaseModel


class StockAnalysis(BaseModel):
    symbol: str
    company_name: str
    analysis: str


class NewsAnalysis(BaseModel):
    topic: str
    summary: str


class ResearchReport(BaseModel):
    title: str
    stock_analysis: str
    news_summary: str


news_agent = Agent(
    name="News Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[HackerNewsTools()],
    role="Research tech news from HackerNews",
    output_schema=NewsAnalysis,
)

stock_agent = Agent(
    name="Stock Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[YFinanceTools()],
    role="Analyze stock prices and financial data",
    output_schema=StockAnalysis,
)

team = Team(
    name="Research Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[news_agent, stock_agent],
    output_schema=ResearchReport,
    markdown=True,
)

response = team.run("Research NVIDIA - get stock data and recent news")
print(f"Title: {response.content.title}")
print(f"Stock Analysis: {response.content.stock_analysis}")
print(f"News Summary: {response.content.news_summary}")

​
Usage

1

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
2

Install dependencies

uv pip install -U agno openai yfinance
3

Export your OpenAI API key

export OPENAI_API_KEY="your_openai_api_key_here"
4

Run Team

python pydantic_model_output.py