> ## 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.

# 图片代理

## Code

```python cookbook/models/ibm/watsonx/image_agent_bytes.py theme={null}
from pathlib import Path

from agno.agent import Agent
from agno.media import Image
from agno.models.ibm import WatsonX
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=WatsonX(id="meta-llama/llama-3-2-11b-vision-instruct"),
    tools=[DuckDuckGoTools()],
    markdown=True,
)

image_path = Path(__file__).parent.joinpath("sample.jpg")

# Read the image file content as bytes
with open(image_path, "rb") as img_file:
    image_bytes = img_file.read()

agent.print_response(
    "Tell me about this image and give me the latest news about it.",
    images=[
        Image(content=image_bytes),
    ],
    stream=True,
)
```

## Usage

<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 duckduckgo-search agno
    ```
  </Step>

  <Step title="添加示例图片">
    将名为“sample.jpg”的示例图片放在脚本的同一目录下。
  </Step>

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

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

此示例展示了如何使用支持视觉功能的 IBM WatsonX。它从文件中加载一张图片，并将图片与提示一起传递给模型。然后，模型可以分析图片并提供相关信息。

注意：此示例使用了一个支持视觉功能的模型（`meta-llama/llama-3-2-11b-vision-instruct`）并且需要一个示例图片文件。