> ## 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.

# File Input

> Process files as input with Agno agents.

Agno supports files as input to agents and tools.

Let's create an agent that can understand files.

```python file_input.py theme={null}
from agno.agent import Agent
from agno.media import File
from agno.models.anthropic import Claude
from agno.db.in_memory import InMemoryDb

agent = Agent(
    model=Claude(id="claude-sonnet-4-0"),
    db=InMemoryDb(),
    markdown=True,
)

agent.print_response(
    "Summarize the contents of the attached file.",
    files=[
        File(url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"),
    ],
)
```

## Usage

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

**1. Install dependencies**

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

**2. Export your Anthropic API key**

```bash Mac/Linux theme={null}
  export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
```

```bash Windows theme={null}
  $Env:ANTHROPIC_API_KEY="your_anthropic_api_key_here"
```

**3. Run Agent**

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


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