Image Agent with File Upload

Code

cookbook/models/google/gemini/image_input_file_upload.py

from pathlib import Path

from agno.agent import Agent
from agno.media import Image
from agno.models.google import Gemini
from agno.tools.duckduckgo import DuckDuckGoTools
from google.generativeai import upload_file
from google.generativeai.types import file_types

agent = Agent(
    model=Gemini(id="gemini-2.0-flash-exp"),
    tools=[DuckDuckGoTools()],
    markdown=True,
)
# Please download the image using
# wget https://upload.wikimedia.org/wikipedia/commons/b/bf/Krakow_-_Kosciol_Mariacki.jpg
image_path = Path(__file__).parent.joinpath("Krakow_-_Kosciol_Mariacki.jpg")
image_file: file_types.File = upload_file(image_path)
print(f"Uploaded image: {image_file}")

agent.print_response(
    "Tell me about this image and give me the latest news about it.",
    images=[Image(content=image_file)],
    stream=True,
)

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Download the image

   wget https://upload.wikimedia.org/wikipedia/commons/b/bf/Krakow_-_Kosciol_Mariacki.jpg
   
3. Set your API key

   export GOOGLE_API_KEY=xxx
   
4. Install libraries

   pip install -U google-genai ddgs agno
   
5. Run Agent

   Mac

   python cookbook/models/google/gemini/image_input_file_upload.py