Quickstart#

Via AgentChat, you can build applications quickly using preset agents. To illustrate this, we will begin with creating a single tool-use agent.

pip install -U "autogen-ext[openai,azure]"

To use Azure OpenAI models and AAD authentication, you can follow the instructions here.

To use other models, see Models.

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient


# Define a tool
async def get_weather(city: str) -> str:
    """Get the weather for a given city."""
    return f"The weather in {city} is 73 degrees and Sunny."


async def main() -> None:
    agent = AssistantAgent(
        name="weather_agent",
        model_client=OpenAIChatCompletionClient(
            model="gpt-4o",
            # api_key="YOUR_API_KEY",
        ),
        tools=[get_weather],
        system_message="You are a helpful assistant.",
        reflect_on_tool_use=True,
    )
    await Console(agent.run_stream(task="What is the weather in New York?"))


# NOTE: if running this inside a Python script you'll need to use asyncio.run(main()).
await main()
---------- user ----------
What is the weather in New York?
---------- weather_agent ----------
[FunctionCall(id='call_ciy1Ecys9LH201cyim10xlnQ', arguments='{"city":"New York"}', name='get_weather')]
---------- weather_agent ----------
[FunctionExecutionResult(content='The weather in New York is 73 degrees and Sunny.', call_id='call_ciy1Ecys9LH201cyim10xlnQ')]
---------- weather_agent ----------
The weather in New York is currently 73 degrees and sunny.

What’s Next?#

Now that you have a basic understanding of how to define an agent, consider following the tutorial for a walkthrough on other features of AgentChat.