WhatsApp Image Generation Agent (Tool-based)

WhatsApp agent that generates images using OpenAI’s image generation tools

Code

cookbook/os/interfaces/whatsapp/image_generation_tools.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.os import AgentOS
from agno.os.interfaces.whatsapp import Whatsapp
from agno.tools.openai import OpenAITools

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

image_agent = Agent(
    id="image_generation_tools",
    db=agent_db,
    model=OpenAIChat(id="gpt-4o"),
    tools=[OpenAITools(image_model="gpt-image-1")],
    markdown=True,
    add_history_to_context=True,
)

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_tools: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 OPENAI_API_KEY=your_openai_api_key
   export APP_ENV=development
   
3. Install dependencies

   uv pip install -U agno
   
4. Run Example

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

Key Features

• Tool-based Generation: OpenAI’s GPT Image-1 model via external tools
• High-Quality Images: Professional-grade image generation sent as WhatsApp photos
• Conversational Interface: Natural language interaction for image requests
• History Context: Remembers previous images and conversations