> ## 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.

# OpenAI PDF Input Bytes

> Attach a PDF as raw bytes and have gpt-5-mini summarize its contents.

```python pdf_input_bytes.py theme={null}
"""
Openai Pdf Input Bytes
=========================
"""

from pathlib import Path

from agno.agent import Agent
from agno.media import File
from agno.models.openai.chat import OpenAIChat
from agno.utils.media import download_file

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

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=OpenAIChat(id="gpt-5-mini"),
    markdown=True,
)

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

## Run the Example

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

**1. Install dependencies**

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

**2. Export your OpenAI API key**

```bash Mac/Linux theme={null}
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

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

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

Full source: [cookbook/90\_models/openai/chat/pdf\_input\_bytes.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/openai/chat/pdf_input_bytes.py)


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