Integrate Langfuse with Semantic Kernel

This notebook provides a step-by-step guide on integrating Langfuse with Semantic Kernel to achieve observability and debugging for your LLM applications. By following this tutorial, you will learn how to trace your Semantic Kernel applications using Langfuse, manage your prompts in one place and evaluate your application to make it production-ready.

What is Semantic Kernel? Semantic Kernel (GitHub) is a powerful open-source SDK from Microsoft. It facilitates the combination of LLMs with popular programming languages like C#, Python, and Java. Semantic Kernel empowers developers to build sophisticated AI applications by seamlessly integrating AI services, data sources, and custom logic, accelerating the delivery of enterprise-grade AI solutions.

What is Langfuse? Langfuse is an open-source platform dedicated to LLM observability. It offers robust tracing and monitoring capabilities tailored for AI applications. Langfuse helps developers debug, analyze, and optimize their AI systems by providing detailed insights and integrating with a wide array of tools and frameworks through native integrations, OpenTelemetry, and dedicated SDKs.

Note: This guide focuses on the Python implementation. However, the principles of this Langfuse integration apply to other languages supported by Semantic Kernel, including C# and Java.

Getting Started

Let's walk through a practical example of using Semantic Kernel and integrating it with Langfuse for comprehensive tracing.

Step 1: Install Dependencies

Step 2: Configure Langfuse SDK

Next, set up your Langfuse API keys. You can get these keys by signing up for a free Langfuse Cloud account or by self-hosting Langfuse. These environment variables are essential for the Langfuse client to authenticate and send data to your Langfuse project.

With the environment variables set, we can now initialize the Langfuse client. get_client() initializes the Langfuse client using the credentials provided in the environment variables.

Step 3: Initialize OpenLit for Instrumentation

Now, we initialize the OpenLit instrumentation SDK. OpenLit automatically instruments Semantic Kernel and exports OpenTelemetry (OTel) spans to Langfuse.

Step 4: Basic Semantic Kernel Application

Let's create a straightforward Semantic Kernel application. In this example, an Assistant agent will answer a user's question. This will serve as the foundation for demonstrating Langfuse tracing.

Step 5: Run the Application

With the Semantic Kernel application set up, let's invoke it with a sample question and print the response. OpenLit will automatically capture this interaction and send the trace data to Langfuse.

Step 6: View Traces in Langfuse

After executing the application, navigate to your Langfuse Trace Table. You will find detailed traces of the application's execution, providing insights into the LLM calls, inputs, outputs, and performance metrics. Below is an example screenshot illustrating how a trace appears in Langfuse:

For a live example, you can explore this public trace: Langfuse Semantic Kernel Trace Example