> ## Documentation Index
> Fetch the complete documentation index at: https://ikun.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 通过 OpenInference 使用 Arize Phoenix

## 总览

本示例演示如何使用 OpenInference 为您的 Agno 代理添加观测能力，并将追踪信息发送到 Arize Phoenix。

## 代码

```python theme={null}
import asyncio
import os

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.yfinance import YFinanceTools
from phoenix.otel import register

# 设置 Arize Phoenix 的环境变量
os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={os.getenv('ARIZE_PHOENIX_API_KEY')}"
os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "https://app.phoenix.arize.com"

# 配置 Phoenix trace
tracer_provider = register(
    project_name="agno-stock-price-agent",  # 默认为 'default'
    auto_instrument=True,  # 自动使用已安装的 OpenInference 仪器库
)

# 创建并配置代理
agent = Agent(
    name="Stock Price Agent",
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[YFinanceTools()],
    instructions="你是一名股票价格代理。请以股票分析师的风格回答问题。",
    debug_mode=True,
)

# 使用代理
agent.print_response("特斯拉目前的股价是多少？")
```

## 使用方法

<Steps>
  <Step title="安装依赖">
    ```bash theme={null}
    pip install agno arize-phoenix openai openinference-instrumentation-agno opentelemetry-sdk opentelemetry-exporter-otlp
    ```
  </Step>

  <Step title="设置环境变量">
    ```bash theme={null}
    export ARIZE_PHOENIX_API_KEY=<your-key>
    ```
  </Step>

  <Step title="运行代理">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/observability/arize_phoenix_via_openinference.py
      ```

      ```bash Windows theme={null}
      python cookbook/observability/arize_phoenix_via_openinference.py
      ```
    </CodeGroup>
  </Step>
</Steps>