> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-service-account.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AWS Image Agent

> Describe an image URL with Claude on Bedrock and enrich it with web search.

```python image_agent.py theme={null}
"""
Aws Image Agent
===============

Cookbook example for `aws/claude/image_agent.py`.
"""

from agno.agent import Agent
from agno.media import Image
from agno.models.aws import Claude
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=Claude(id="global.anthropic.claude-sonnet-4-5-20250929-v1:0"),
    tools=[WebSearchTools()],
    markdown=True,
)

agent.print_response(
    "Tell me about this image and search the web for more information.",
    images=[
        Image(
            url="https://fastly.picsum.photos/id/237/200/300.jpg?hmac=TmmQSbShHz9CdQm0NkEjx1Dyh_Y984R9LpNrpvH2D_U"
        ),
    ],
    stream=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno aioboto3 boto3 ddgs
    ```
  </Step>

  <Step title="Export environment variables">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export AWS_ACCESS_KEY_ID="your_aws_access_key_id_here"
      export AWS_SECRET_ACCESS_KEY="your_aws_secret_access_key_here"
      ```

      ```bash Windows theme={null}
      $Env:AWS_ACCESS_KEY_ID="your_aws_access_key_id_here"
      $Env:AWS_SECRET_ACCESS_KEY="your_aws_secret_access_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `image_agent.py`, then run:

    ```bash theme={null}
    python image_agent.py
    ```
  </Step>
</Steps>

Full source: [cookbook/90\_models/aws/claude/image\_agent.py](https://github.com/agno-agi/agno/blob/main/cookbook/90_models/aws/claude/image_agent.py)