LiteLLM PDF Input Bytes

Pass a downloaded PDF as raw bytes to a LiteLLM agent and summarize its contents.

pdf_input_bytes.py

"""
Litellm Pdf Input Bytes
=======================

Cookbook example for `litellm/pdf_input_bytes.py`.
"""

from pathlib import Path

from agno.agent import Agent
from agno.media import File
from agno.models.litellm import LiteLLM
from agno.utils.media import download_file

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

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

download_file(
    "https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf", str(pdf_path)
)

agent = Agent(
    model=LiteLLM(id="openai/gpt-4o"),
    markdown=True,
)

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

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

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno litellm
   
3. Export your LiteLLM API key

   Mac/Linux

   export LITELLM_API_KEY="your_litellm_api_key_here"
   

   $Env:LITELLM_API_KEY="your_litellm_api_key_here"
   
4. Run the example

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

   python pdf_input_bytes.py
   

Full source: cookbook/90_models/litellm/pdf_input_bytes.py