> ## Documentation Index
> Fetch the complete documentation index at: https://spacesail.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Structured Output Streaming

This example demonstrates streaming structured output from a team, using Pydantic models to ensure validated data structures while providing real-time streaming responses.

## Code

```python cookbook/examples/teams/structured_input_output/04_structured_output_streaming.py theme={null}
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.team import Team
from agno.tools.exa import ExaTools
from pydantic import BaseModel


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


stock_searcher = Agent(
    name="Stock Searcher",
    model=OpenAIChat("gpt-5-mini"),
    output_schema=StockAnalysis,
    role="Searches the web for information on a stock.",
    tools=[
        ExaTools(
            include_domains=["cnbc.com", "reuters.com", "bloomberg.com", "wsj.com"],
            text=False,
            highlights=False,
            show_results=True,
        )
    ],
)


class CompanyAnalysis(BaseModel):
    company_name: str
    analysis: str


company_info_agent = Agent(
    name="Company Info Searcher",
    model=OpenAIChat("gpt-5-mini"),
    role="Searches the web for information on a stock.",
    output_schema=CompanyAnalysis,
    tools=[
        ExaTools(
            include_domains=["cnbc.com", "reuters.com", "bloomberg.com", "wsj.com"],
            text=False,
            highlights=False,
            show_results=True,
        )
    ],
)


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


team = Team(
    name="Stock Research Team",
    model=OpenAIChat("gpt-5-mini"),
    members=[stock_searcher, company_info_agent],
    output_schema=StockReport,
    markdown=True,
    show_members_responses=True,
)

# Run with streaming and consume the generator to get the final response
stream_generator = team.run(
    "Give me a stock report for NVDA",
    stream=True,
    stream_events=True,
)

# Consume the streaming events and get the final response
run_response = None
for event_or_response in stream_generator:
    # The last item in the stream is the final TeamRunOutput
    run_response = event_or_response

assert isinstance(run_response.content, StockReport)
print(
    f"✅ Response content is correctly typed as StockReport: {type(run_response.content)}"
)
print(f"✅ Stock Symbol: {run_response.content.symbol}")
print(f"✅ Company Name: {run_response.content.company_name}")
```

## Usage

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install required libraries">
    ```bash theme={null}
    pip install agno exa_py pydantic
    ```
  </Step>

  <Step title="Set environment variables">
    ```bash theme={null}
    export OPENAI_API_KEY=****
    export EXA_API_KEY=****
    ```
  </Step>

  <Step title="Run the agent">
    ```bash theme={null}
    python cookbook/examples/teams/structured_input_output/04_structured_output_streaming.py
    ```
  </Step>
</Steps>