> ## 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.

# 流式处理基础 Agent

## 代码

```python cookbook/models/ibm/watsonx/basic_stream.py theme={null}
from typing import Iterator
from agno.agent import Agent, RunResponse
from agno.models.ibm import WatsonX

agent = Agent(model=WatsonX(id="ibm/granite-20b-code-instruct"), markdown=True)

# 将响应存储在变量中
# run_response: Iterator[RunResponse] = agent.run("Share a 2 sentence horror story", stream=True)
# for chunk in run_response:
#     print(chunk.content)

# 在终端中打印响应
agent.print_response("Share a 2 sentence horror story", stream=True)
```

## 用法

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="设置您的 API 密钥">
    ```bash theme={null}
    export IBM_WATSONX_API_KEY=xxx
    export IBM_WATSONX_PROJECT_ID=xxx
    ```
  </Step>

  <Step title="安装库">
    ```bash theme={null}
    pip install -U ibm-watsonx-ai agno
    ```
  </Step>

  <Step title="运行 Agent">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/models/ibm/watsonx/basic_stream.py
      ```

      ```bash Windows theme={null}
      python cookbook\models\ibm\watsonx\basic_stream.py
      ```
    </CodeGroup>
  </Step>
</Steps>

此示例演示了如何使用 IBM WatsonX 进行流式处理。在调用 `print_response()` 或 `run()` 时设置 `stream=True` 可以启用逐个 token 的流式传输，从而提供更具交互性的用户体验。