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

# PDF Input URL

> Fetch a PDF from a URL and summarize it with a Vertex AI Claude agent.

Vertex AI accepts only base64-encoded document sources, so fetch the PDF and pass its bytes with `File(content=...)`. `File(url=...)` sends a URL document source, which Vertex AI rejects.

## Code

```python pdf_input_url.py theme={null}
import httpx

from agno.agent import Agent
from agno.media import File
from agno.models.vertexai.claude import Claude

agent = Agent(
    model=Claude(id="claude-sonnet-4@20250514"),
    markdown=True,
)

pdf_bytes = httpx.get(
    "https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
).content

agent.print_response(
    "Summarize the contents of the attached file.",
    files=[
        File(content=pdf_bytes),
    ],
)
```

## Usage

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

  <Step title="Set your environment variables">
    <CodeGroup>
      ```bash Mac theme={null}
      export CLOUD_ML_REGION=xxx
      export GOOGLE_CLOUD_PROJECT=xxx
      ```

      ```bash Windows theme={null}
      setx CLOUD_ML_REGION xxx
      setx GOOGLE_CLOUD_PROJECT xxx
      ```
    </CodeGroup>
  </Step>

  <Step title="Authenticate your CLI session">
    ```bash theme={null}
    gcloud auth application-default login
    ```

    <Note>You don't need to authenticate your CLI every time.</Note>
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U 'anthropic[vertex]' agno
    ```
  </Step>

  <Step title="Run Agent">
    ```bash theme={null}
    python pdf_input_url.py
    ```
  </Step>
</Steps>