Agent with Structured Output

Code

cookbook/models/ibm/watsonx/structured_output.py

from typing import List

from agno.agent import Agent, RunResponse
from agno.models.ibm import WatsonX
from pydantic import BaseModel, Field
from rich.pretty import pprint


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!"
    )


movie_agent = Agent(
    model=WatsonX(id="ibm/granite-20b-code-instruct"),
    description="You help people write movie scripts.",
    response_model=MovieScript,
)

# Get the response in a variable
# movie_agent: RunResponse = movie_agent.run("New York")
# pprint(movie_agent.content)

movie_agent.print_response("New York")

Usage

1. 创建虚拟环境

   打开 Terminal 并创建一个 python 虚拟环境。

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Set your API key

   export IBM_WATSONX_API_KEY=xxx
   export IBM_WATSONX_PROJECT_ID=xxx
   
3. Install libraries

   pip install -U ibm-watsonx-ai pydantic rich agno
   
4. Run Agent

   Mac

   python cookbook/models/ibm/watsonx/structured_output.py
   

这个示例展示了如何使用结构化输出与 IBM WatsonX 进行交互。它定义了一个名为 MovieScript 的 Pydantic 模型，其中包含各种字段及其描述。然后，使用此模型作为 response_model 创建一个 Agent。该模型将把输出解析为这种结构化格式。