Llmman Structured Outputs

Parse local model output into a Pydantic schema.

Complete the Llmman server setup first. Keep the server running while using a second terminal with an activated Python environment:

uv pip install -U agno openai

Code

structured_output.py
"""
Llmman Structured Output
========================

Cookbook example for `llmman/structured_output.py`.
"""

from typing import List

from agno.agent import Agent
from agno.models.llmman import Llmman
from agno.run.agent import RunOutput
from pydantic import BaseModel, Field
from rich.pretty import pprint  # noqa

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


class MovieScript(BaseModel):
    name: str = Field(..., description="Give a name to this movie")
    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.",
    )
    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 returns a structured output
structured_output_agent = Agent(
    model=Llmman(id="qwen3:0.6b-q4_K_M"),
    description="You write movie scripts.",
    output_schema=MovieScript,
)

# Run the agent synchronously
structured_output_response: RunOutput = structured_output_agent.run("New York")
pprint(structured_output_response.content)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

Save the code as structured_output.py and run:

python structured_output.py

Agno passes the output schema through the JSON-schema path and parses the response. A valid result depends on the model producing schema-compatible output.