Integration Google Vertexai
Trace Google Vertex AI Models in Langfuse
This notebook shows how to trace and observe models queried via the Google Vertex API service.
What is Google Vertex AI? Google Vertex AI is Google Cloud’s unified platform for building, deploying, and managing machine learning and generative AI with managed services, SDKs, and APIs. It streamlines everything from data prep and training to tuning and prediction, and provides access to foundation models like Gemini with enterprise-grade security and MLOps tooling.
What is Langfuse? Langfuse is an open source platform for LLM observability and monitoring. It helps you trace and monitor your AI applications by capturing metadata, prompt details, token usage, latency, and more.
Step 1: Install Dependencies
Before you begin, install the necessary packages in your Python environment:
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.
Also set your Google Vertex API credentials which uses Application Default Credentials (ADC) from a service account key file.
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: OpenTelemetry Instrumentation
Use the VertexAIInstrumentor library to wrap Google Vertex SDK calls and send OpenTelemetry spans to Langfuse.
Step 4: Run an Example
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 agent conversations, LLM calls, inputs, outputs, and performance metrics.
