Agent with Structured Output

Request JSON Schema output from a Perplexity agent and inspect the parsed result.

output_schema describes the expected type. If parsing or validation fails, result.content can remain a string. Before accessing schema fields in a run result, use isinstance(result.content, YourSchema), replacing YourSchema with the class you passed as output_schema.

Code

from typing import List

from agno.agent import Agent, RunOutput  # noqa
from agno.models.perplexity import Perplexity
from pydantic import BaseModel, Field

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 requests JSON Schema output
structured_output_agent = Agent(
    model=Perplexity(id="sonar-pro"),
    description="You write movie scripts.",
    output_schema=MovieScript,
    markdown=True,
)

# Get the response in a variable
# structured_output_response: RunOutput = structured_output_agent.run("New York")
# pprint(structured_output_response.content)

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 PERPLEXITY_API_KEY=xxx

Install dependencies

uv pip install -U agno openai

Run Agent

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

python structured_output.py