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. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Install libraries

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

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Create a Python file

   Create a Python file and add the above code.

   touch agent_using_multimodal_tool_response_in_runs.py
   
5. Run Agent

   Mac

   python agent_using_multimodal_tool_response_in_runs.py
   
6. Find All Cookbooks

   Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

   Agno Cookbooks on GitHub