Agent with Structured Outputs

The selected provider and model must support the requested output format. Set the model capability flag as shown: the adapter otherwise omits response_format, even when the agent has use_json_mode=True. JSON mode requests JSON and Agno parses it into the Pydantic model; native structured output requests the schema from the provider. Check the returned content type before consuming it in application code.

Code

from typing import List

from agno.agent import Agent, RunOutput  # noqa
from agno.models.litellm import LiteLLM
from pydantic import BaseModel, Field
from rich.pretty import pprint  # noqa

class MovieScript(BaseModel):
    setting: str = Field(
        ..., description="Provide a nice setting for a blockbuster movie."
    )
    ending: str = Field(
        ...,
        description="Ending of the movie. If not available, provide a happy ending.",
    )
    genre: str = Field(
        ...,
        description="Genre of the movie. If not available, select action, thriller or romantic comedy.",
    )
    name: str = Field(..., description="Give a name to this movie")
    characters: List[str] = Field(..., description="Name of characters for this movie.")
    storyline: str = Field(
        ..., description="3 sentence storyline for the movie. Make it exciting!"
    )

# Agent that uses JSON mode
json_mode_agent = Agent(
    model=LiteLLM(id="gpt-4o", supports_native_structured_outputs=True),
    description="You write movie scripts.",
    output_schema=MovieScript,
    use_json_mode=True,
)

# Agent that uses native structured outputs.
# Set supports_native_structured_outputs=True for the providers that support it.
structured_output_agent = Agent(
    model=LiteLLM(id="gpt-4o", supports_native_structured_outputs=True),
    description="You write movie scripts.",
    output_schema=MovieScript,
    structured_outputs=True,
)

json_mode_agent.print_response("New York")
structured_output_agent.print_response("New York")

Usage

Set up your virtual environment

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

Set your API key

export LITELLM_API_KEY=xxx

Install dependencies

uv pip install -U "litellm>=1.83.0" openai agno

Run Agent

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

python structured_output.py