Agent Input as Messages List

This example demonstrates how to pass input to an agent as a list of Message objects, allowing for multi-turn conversations and context setup.

Code

input_as_messages_list.py

from agno.agent import Agent, Message
from agno.models.openai import OpenAIChat

Agent(model=OpenAIChat(id="gpt-5-mini")).print_response(
    input=[
        Message(
            role="user",
            content="I'm preparing a presentation for my company about renewable energy adoption.",
        ),
        Message(
            role="assistant",
            content="I'd be happy to help with your renewable energy presentation. What specific aspects would you like me to focus on?",
        ),
        Message(
            role="user",
            content="Could you research the latest solar panel efficiency improvements in 2024?",
        ),
        Message(
            role="user",
            content="Also, please summarize the key findings in bullet points for my slides.",
        ),
    ],
    stream=True,
    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 agno openai
   
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 input_as_messages_list.py
   
5. Run Agent

   Mac

   python input_as_messages_list.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