Agent with PDF Input (Local file)

Pass a local PDF to a Gemini agent with File(filepath=...).

Code

from pathlib import Path
from agno.agent import Agent
from agno.db.in_memory import InMemoryDb
from agno.media import File
from agno.models.google import Gemini
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=Gemini(id="gemini-3.5-flash"),
    markdown=True,
    add_history_to_context=True,
    db=InMemoryDb(),
)

agent.print_response(
    "Summarize the contents of the attached file.",
    files=[File(filepath=pdf_path)],
)
agent.print_response("Suggest me a recipe from the attached file.")

The in-memory database retains the PDF and conversation for the follow-up in this process. Use a persistent database for history across restarts.

Usage

Set up your virtual environment

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

Set your API key

export GOOGLE_API_KEY=xxx

Install dependencies

uv pip install -U google-genai agno

Run Agent

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

python pdf_input_local.py