Semantic Kernel

Trace Microsoft Semantic Kernel applications in Muster via OpenLit instrumentation.

Semantic Kernel is an open-source SDK from Microsoft that integrates LLMs with C#, Python, and Java codebases. Muster captures Semantic Kernel runs through OpenLit instrumentation.

Setup

1. Install dependencies

pip install langfuse openlit semantic-kernel

2. Configure credentials

import os

os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..."
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
os.environ["LANGFUSE_BASE_URL"] = "https://app.getmuster.io"
os.environ["OPENAI_API_KEY"] = "sk-proj-..."

from langfuse import get_client

langfuse = get_client()

if langfuse.auth_check():
    print("Muster client is authenticated and ready!")

3. Initialize OpenLit instrumentation

import openlit

openlit.init()

OpenLit automatically instruments Semantic Kernel and exports OpenTelemetry spans to Muster.

4. Build and invoke a kernel

from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion
from semantic_kernel.functions import KernelArguments

kernel = Kernel()
kernel.add_service(OpenAIChatCompletion(
    service_id="default",
    ai_model_id="gpt-4o-mini",
))

answer = await kernel.invoke_prompt("What is Muster?")
print(answer)

Add user/session attributes

from langfuse import propagate_attributes

with propagate_attributes(user_id="user_123", session_id="sess_abc", tags=["semantic-kernel"]):
    await kernel.invoke_prompt(...)

Troubleshooting

Enable debug mode and verify instrumentation runs before application code.
Filter unrelated OTel spans from other libraries.
Some attributes are stored in metadata rather than mapped fields.