AutoGen AgentChat Tracing

AutoGen AgentChat is the framework within Microsoft’s AutoGen that enables robust multi-agent application.

Launch Phoenix#

uvx arize-phoenix serve

No uv? pip install arize-phoenix && phoenix serve does the same thing. See Terminal setup for customization.

docker run -p 6006:6006 -p 4317:4317 arizephoenix/phoenix:latest

Images are published to Docker Hub. See Docker for volumes, PostgreSQL, and other options.

Phoenix serves its UI and OTLP HTTP on port 6006, and OTLP gRPC on port 4317. For a local instance that’s http://localhost:6006. Leave it running while you work.

Install packages:

pip install arize-phoenix-otel

Point your code at the Phoenix instance you started. The endpoint below is the default for a local phoenix serve; for a deployment running elsewhere, use its hostname instead.

import osos.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "http://localhost:6006"# Only if the deployment has authentication enabled# os.environ["PHOENIX_API_KEY"] = "your-api-key"

Install#

pip install openinference-instrumentation-autogen-agentchat autogen-agentchat autogen_ext

Setup#

Connect your application to Phoenix with the register function:

from phoenix.otel import register# configure the Phoenix tracertracer_provider = register(project_name="agentchat-agent", # Default is 'default'auto_instrument=True # Auto-instrument your app based on installed OI dependencies)

Run AutoGen AgentChat#

We’re going to run an AgentChat example using a multi-agent team. To get started, install the required packages to use your LLMs with AgentChat. In this example, we’ll use OpenAI as the LLM provider.

pip install autogen_ext openai

import asyncioimport osfrom autogen_agentchat.agents import AssistantAgentfrom autogen_agentchat.conditions import TextMentionTerminationfrom autogen_agentchat.teams import RoundRobinGroupChatfrom autogen_ext.models.openai._openai_client import OpenAIChatCompletionClientos.environ["OPENAI_API_KEY"] = "your-api-key"async def main():    model_client = OpenAIChatCompletionClient(        model="gpt-4",    )    # Create two agents: a primary and a critic    primary_agent = AssistantAgent(        "primary",        model_client=model_client,        system_message="You are a helpful AI assistant.",    )    critic_agent = AssistantAgent(        "critic",        model_client=model_client,        system_message="""        Provide constructive feedback.        Respond with 'APPROVE' when your feedbacks are addressed.        """,    )    # Termination condition: stop when the critic says "APPROVE"    text_termination = TextMentionTermination("APPROVE")    # Create a team with both agents    team = RoundRobinGroupChat(        [primary_agent, critic_agent],        termination_condition=text_termination    )    # Run the team on a task    result = await team.run(task="Write a short poem about the fall season.")    await model_client.close()    print(result)if __name__ == "__main__":    asyncio.run(main())

Observe#

Phoenix provides visibility into your AgentChat operations by automatically tracing all interactions.

Launch Phoenix#

Install#

Setup#

Run AutoGen AgentChat#

Observe#

Resources#