Observability for Baseten with Langfuse

This guide shows you how to integrate Baseten with Langfuse. Baseten's inference API is fully compatible with OpenAI's client libraries, allowing us to use the Langfuse OpenAI drop-in replacement to trace all parts of your application.

What is Baseten? Baseten is an inference platform that enables developers to deploy and scale machine learning models in production. It provides fast, reliable model inference with support for popular open-source models through an OpenAI-compatible API.

What is Langfuse? Langfuse is an open source LLM engineering platform that helps teams trace API calls, monitor performance, and debug issues in their AI applications.

Step 1: Install Dependencies

Make sure you have installed the necessary Python packages:

Step 2: Set Up Environment Variables

Step 3: Langfuse OpenAI drop-in Replacement

In this step we use the native OpenAI drop-in replacement by importing from langfuse.openai import openai.

To start using Baseten with OpenAI's client libraries, pass in your Baseten API key to the api_key option, and change the base_url to https://inference.baseten.co/v1:

Step 4: Run An Example

The following cell demonstrates how to call Baseten's chat model using the traced OpenAI client. All API calls will be automatically traced by Langfuse.

Step 5: See Traces in Langfuse

After running the example model call, you can see the traces in Langfuse. You will see detailed information about your Baseten API calls, including:

• Request parameters (model, messages, temperature, etc.)
• Response content
• Token usage statistics
• Latency metrics

Public example trace link in Langfuse