Agents
Structured Output
Examples
- Introduction
- Agents
- Web Search Agent
- AI Recipe Creator Agent
- Finance Agent
- Books Recommendation Agent
- Shopping Agent
- Weekend Planner Agent
- Agent Team
- Reasoning Agent
- Python Agent
- Data Analyst
- Structured Output
- Python Function Agent
- Image Agent
- Generate Image Agent
- Cal.com Agent
- Image to Text Agent
- Research Agent
- ModelsLabs Agent
- Slack Agent
- Discord Agent
- Firecrawl Agent
- Github Agent
- RAG Agent
- Popcorn Pal
- Globe Hopper Agent
- Baidu Search Agent
- Youtube Timestamp Agent
- Study Scout Agent
- Models
- Integrations
- Agent Teams
- Use Cases
How To
Agents
Structured Output
Create a file structured_output.py
with the following code:
structured_output.py
from typing import List
from rich.pretty import pprint # noqa
from pydantic import BaseModel, Field
from phi.agent import Agent, RunResponse # noqa
from phi.model.openai import OpenAIChat
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=OpenAIChat(id="gpt-4o"),
description="You write movie scripts.",
response_model=MovieScript,
)
# Agent that uses structured outputs
structured_output_agent = Agent(
model=OpenAIChat(id="gpt-4o-2024-08-06"),
description="You write movie scripts.",
response_model=MovieScript,
structured_outputs=True,
)
# Get the response in a variable
# json_mode_response: RunResponse = json_mode_agent.run("New York")
# pprint(json_mode_response.content)
# structured_output_response: RunResponse = structured_output_agent.run("New York")
# pprint(structured_output_response.content)
json_mode_agent.print_response("New York")
structured_output_agent.print_response("New York")
Usage
1
Create a virtual environment
Open the Terminal
and create a python virtual environment.
2
Install libraries
pip install openai phidata
3
Run the agent
python structured_output.py
Was this page helpful?
On this page