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

# PDF Input Local

> Send a local PDF file to Claude and read citations from the run output.

Pass a local PDF file path with `File(filepath=...)`. Claude cites the document in `run_response.citations`.

## Code

```python pdf_input_local.py theme={null}
from pathlib import Path

from agno.agent import Agent
from agno.media import File
from agno.models.anthropic import Claude
from agno.utils.media import download_file

pdf_path = Path(__file__).parent.joinpath("ThaiRecipes.pdf")

# Download the file using the download_file function
download_file(
    "https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf", str(pdf_path)
)

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

agent.print_response(
    "Summarize the contents of the attached file.",
    files=[
        File(
            filepath=pdf_path,
        ),
    ],
)
run_response = agent.get_last_run_output()
print("Citations:")
print(run_response.citations)
```

## Usage

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

**1. Set your API key**

```bash theme={null}
export ANTHROPIC_API_KEY=xxx
```

**2. Install dependencies**

```bash theme={null}
uv pip install -U anthropic agno
```

**3. Run Agent**

Save the code above as `pdf_input_local.py`, then run:

```bash theme={null}
python pdf_input_local.py
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.