PDF Input File Upload

Upload a PDF to the Gemini Files API, then ask an agent to summarize it and suggest a recipe from it.

In this example, we upload a PDF file to Google GenAI directly and then use it as an input to an agent.

pdf_input_file_upload.py

"""
In this example, we upload a PDF file to Google GenAI directly and then use it as an input to an agent.

Note: If the size of the file is greater than 20MB, and a file path is provided, the file automatically gets uploaded to Google GenAI.
"""

from pathlib import Path
from time import sleep

from agno.agent import Agent
from agno.media import File
from agno.models.google import Gemini
from google import genai

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

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

client = genai.Client()

# Upload the file to Google GenAI
upload_result = client.files.upload(file=pdf_path)

# Get the file from Google GenAI
if upload_result and upload_result.name:
    retrieved_file = client.files.get(name=upload_result.name)
else:
    retrieved_file = None

# Retry up to 3 times if file is not ready
retries = 0
wait_time = 5
while retrieved_file is None and retries < 3:
    retries += 1
    sleep(wait_time)
    if upload_result and upload_result.name:
        retrieved_file = client.files.get(name=upload_result.name)
    else:
        retrieved_file = None

if retrieved_file is not None:
    agent = Agent(
        model=Gemini(id="gemini-3.5-flash"),
        markdown=True,
        add_history_to_context=True,
    )

    agent.print_response(
        "Summarize the contents of the attached file.",
        files=[File(external=retrieved_file)],
    )

    agent.print_response(
        "Suggest me a recipe from the attached file.",
    )
else:
    print("Error: File was not ready after multiple attempts.")

# ---------------------------------------------------------------------------
# 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 google-genai
   
3. Export your Google API key

   Mac/Linux

   export GOOGLE_API_KEY="your_google_api_key_here"
   

   $Env:GOOGLE_API_KEY="your_google_api_key_here"
   
4. Run the example

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

   python pdf_input_file_upload.py
   

Full source: cookbook/90_models/google/gemini/pdf_input_file_upload.py