Agent with Structured Outputs

Agno attempts to parse the response into MovieScript. If parsing fails, RunOutput.content can remain a string; check isinstance(response.content, MovieScript) before using typed fields. A completed run alone does not prove schema validation succeeded.

Code

import os
from typing import List

from agno.agent import Agent, RunOutput  # noqa
from agno.models.nebius import Nebius
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 a structured output
structured_output_agent = Agent(
    model=Nebius(id=os.environ["NEBIUS_MODEL_ID"]),
    description="You are a helpful assistant. Summarize the movie script based on the location in a JSON object.",
    output_schema=MovieScript,
)

structured_output_agent.print_response("New York")

Select a text-generation model with JSON mode support for this example.

Usage

Set up your virtual environment

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

Export environment variables

Select an available text-generation model ID from the Nebius model-list API.

export NEBIUS_API_KEY="your_nebius_api_key"
export NEBIUS_MODEL_ID="your_current_text_model_id"

Install dependencies

uv pip install -U openai agno

Run Agent

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

python structured_output.py