Trace AutoGen with BotGauge

Records AutoGen AgentChat agent runs.


Extra	`[autogen-agentchat]`
Verified framework versions	autogen-agentchat 0.7.5
Instrumentor installed by the extra	`openinference-instrumentation-autogen-agentchat 0.1.22`
Zero-code run	Traced

Also verified: autogen-agentchat 0.7.5 with instrumentor 0.1.18. The extra no longer installs that older instrumentor. See supported frameworks for how verification works.

In code

Call tracing.init(), attach the framework instrumentor to the provider it returns, and wrap the work in tracing.turn() and tracing.agent().

Install

terminal

pip install "botgauge[autogen-agentchat]" autogen-agentchat==0.7.5 "autogen-ext[openai]==0.7.5"

Add the code

app.py

import asyncio
import os

from botgauge import tracing
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from openinference.instrumentation.autogen_agentchat import AutogenAgentChatInstrumentor

provider = tracing.init()
AutogenAgentChatInstrumentor().instrument(tracer_provider=provider)

client = OpenAIChatCompletionClient(
    model=os.environ["OPENAI_MODEL"],
    base_url=os.environ["OPENAI_BASE_URL"],
    api_key=os.environ["OPENAI_API_KEY"],
    model_info={
        "vision": False,
        "function_calling": True,
        "json_output": False,
        "family": "unknown",
        "structured_output": False,
    },
)

async def main():
    with tracing.turn(session_id="ses_autogen"), tracing.agent("autogen-agent"):
        agent = AssistantAgent(name="assistant", model_client=client)
        result = await agent.run(task="In one sentence, what is OpenTelemetry?")
    print(result.messages[-1].content)

asyncio.run(main())

tracing.shutdown()

Run

terminal

python app.py

Needs BOTGAUGE_API_KEY, OPENAI_MODEL, OPENAI_BASE_URL, OPENAI_API_KEY.

Zero-code

Leave your app unchanged and start it with botgauge instrument. The sample still wraps the work in tracing.turn() and tracing.agent() so spans carry session and agent ids.

Install

terminal

pip install "botgauge[autogen-agentchat]" autogen-agentchat==0.7.5 "autogen-ext[openai]==0.7.5"

Add the code

app.py

import asyncio
import os

from botgauge import tracing
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

client = OpenAIChatCompletionClient(
    model=os.environ["OPENAI_MODEL"],
    base_url=os.environ["OPENAI_BASE_URL"],
    api_key=os.environ["OPENAI_API_KEY"],
    model_info={
        "vision": False,
        "function_calling": True,
        "json_output": False,
        "family": "unknown",
        "structured_output": False,
    },
)

async def main():
    with tracing.turn(session_id="ses_autogen"), tracing.agent("autogen-agent"):
        agent = AssistantAgent(name="assistant", model_client=client)
        result = await agent.run(task="In one sentence, what is OpenTelemetry?")
    print(result.messages[-1].content)

asyncio.run(main())

Run

terminal

botgauge instrument python app.py

Needs BOTGAUGE_API_KEY, OPENAI_MODEL, OPENAI_BASE_URL, OPENAI_API_KEY.

View AutoGen spans live

Watch your AutoGen AgentChat runs appear in BotGauge.

Try BotGauge →

See versions not verified if you run a different version, capture and redaction to control exported content, and troubleshooting if spans are missing.

Frameworks

More

Trace AutoGen with BotGauge

In code

Zero-code

​In code

​Zero-code

​Related

In code

Zero-code

Related