Agent Using Multimodal Tool Response in Runs

This example demonstrates how to create an agent that uses DALL-E to generate images and maintains conversation history across multiple runs, allowing the agent to remember previous interactions and images generated.

Code

agent_using_multimodal_tool_response_in_runs.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.tools.dalle import DalleTools

# Create an Agent with the DALL-E tool
agent = Agent(
    tools=[DalleTools()],
    name="DALL-E Image Generator",
    add_history_to_context=True,
    db=SqliteDb(db_file="tmp/test.db"),
)

agent.print_response(
    "Generate an image of a Siamese white furry cat sitting on a couch?",
    markdown=True,
)

agent.print_response(
    "Which type of animal and the breed are we talking about?", markdown=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. Install dependencies

   uv pip install -U openai agno
   
3. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   

     $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run Agent

   python agent_using_multimodal_tool_response_in_runs.py