Gemini Interactions - Structured Output

Example showing structured output with the Interactions API.

Request JSON matching a Pydantic schema through the Interactions API, then validate the returned data. The example checks the parsed type and prints raw output if parsing fails.

structured_output.py
"""
Gemini Interactions - Structured Output
========================================

Example showing structured output with the Interactions API.
Uses Pydantic models to enforce JSON schema on responses.
"""

from agno.agent import Agent
from agno.models.google import GeminiInteractions
from pydantic import BaseModel, Field

# ---------------------------------------------------------------------------
# Define output schema
# ---------------------------------------------------------------------------


class MovieReview(BaseModel):
    title: str = Field(description="The movie title")
    year: int = Field(description="Release year")
    genre: str = Field(description="Primary genre")
    rating: float = Field(description="Rating out of 10")
    summary: str = Field(description="Brief review summary")


# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=GeminiInteractions(id="gemini-3.7-flash"),
    output_schema=MovieReview,
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    response = agent.run("Write a review of The Matrix (1999)")

    if response.content:
        # When using output_schema, the framework parses the response into
        # the Pydantic model automatically. response.content is a MovieReview object.
        review = response.content
        if isinstance(review, MovieReview):
            print(f"Title: {review.title}")
            print(f"Year: {review.year}")
            print(f"Genre: {review.genre}")
            print(f"Rating: {review.rating}/10")
            print(f"Summary: {review.summary}")
        else:
            print(f"Raw response: {review}")

Run the Example

Set up your virtual environment

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

Install dependencies

uv pip install -U agno google-genai

Export your Google API key

export GOOGLE_API_KEY="your_google_api_key_here"

Run the example

Save the code above as structured_output.py, then run:

python structured_output.py

Full source: cookbook/90_models/google/gemini_interactions/structured_output.py