WhatsApp Image Generation Agent (Model-based)

WhatsApp agent that generates images using Gemini’s built-in image generation

Code

cookbook/os/interfaces/whatsapp/image_generation_model.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.google import Gemini
from agno.os import AgentOS
from agno.os.interfaces.whatsapp import Whatsapp

agent_db = SqliteDb(db_file="tmp/persistent_memory.db")

image_agent = Agent(
    id="image_generation_model",
    db=agent_db,
    model=Gemini(
        id="models/gemini-2.5-flash-image",
        response_modalities=["Text", "Image"],
    ),
)

agent_os = AgentOS(
    agents=[image_agent],
    interfaces=[Whatsapp(agent=image_agent)],
)
app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="image_generation_model:app", reload=True)

Usage

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. Set Environment Variables

   export WHATSAPP_ACCESS_TOKEN=your_whatsapp_access_token
   export WHATSAPP_PHONE_NUMBER_ID=your_phone_number_id
   export WHATSAPP_VERIFY_TOKEN=your_verify_token
   export GOOGLE_API_KEY=your_google_api_key
   export APP_ENV=development
   
3. Install dependencies

   uv pip install -U agno
   
4. Run Example

   python cookbook/os/interfaces/whatsapp/image_generation_model.py
   

Key Features

• Native Image Generation: Gemini 2.5 Flash with built-in image generation
• Multimodal Responses: Generates both text and images in a single response
• No External Tools: Image generation is handled directly by the model
• WhatsApp Delivery: Images uploaded and sent as native WhatsApp photos