此示例展示了如何使用 WhatsApp 应用进行推理。

​
代码

cookbook/apps/whatsapp/reasoning_agent.py
from agno.agent import Agent
from agno.app.whatsapp.app import WhatsappAPI
from agno.models.anthropic.claude import Claude
from agno.tools.thinking import ThinkingTools
from agno.tools.yfinance import YFinanceTools

reasoning_finance_agent = Agent(
    name="Reasoning Finance Agent",
    model=Claude(id="claude-3-7-sonnet-latest"),
    tools=[
        ThinkingTools(add_instructions=True),
        YFinanceTools(
            stock_price=True,
            analyst_recommendations=True,
            company_info=True,
            company_news=True,
        ),
    ],
    instructions="Use tables to display data. When you use thinking tools, keep the thinking brief.",
    add_datetime_to_instructions=True,
    markdown=True,
)

whatsapp_app = WhatsappAPI(
    agent=reasoning_finance_agent,
    name="Reasoning Finance Agent",
    app_id="reasoning_finance_agent",
    description="A finance agent that uses tables to display data and reasoning tools to reason about the data.",
)

app = whatsapp_app.get_app()

if __name__ == "__main__":
    whatsapp_app.serve(app="reasoning_agent:app", port=8000, reload=True)

​
用法

1

创建虚拟环境

打开 Terminal 并创建一个 python 虚拟环境。

python3 -m venv .venv
source .venv/bin/activate
2

设置您的 API 密钥

export ANTHROPIC_API_KEY=xxx
3

安装库

pip install -U agno anthropic yfinance "uvicorn[standard]"
4

运行代理

python cookbook/apps/whatsapp/reasoning_agent.py