VertexAI Tracing

Instrument LLM calls made using VertexAI’s SDK via the VertexAIInstrumentor

The VertexAI SDK can be instrumented using the openinference-instrumentation-vertexai package.

Install

pip install openinference-instrumentation-vertexai vertexai

Setup

See Google’s guide on setting up your environment for the Google Cloud AI Platform. You can also store your Project ID in the CLOUD_ML_PROJECT_ID environment variable.

Use the register function to connect your application to Phoenix:

from phoenix.otel import register

# configure the Phoenix tracer
tracer_provider = register(
  project_name="my-llm-app", # Default is 'default'
  auto_instrument=True # Auto-instrument your app based on installed OI dependencies
)

Run VertexAI

import vertexai
from vertexai.generative_models import GenerativeModel

vertexai.init(location="us-central1")
model = GenerativeModel("gemini-1.5-flash")

print(model.generate_content("Why is sky blue?").text)

Observe

Now that you have tracing setup, all invocations of Vertex models will be streamed to your running Phoenix for observability and evaluation.

Resources

• Example notebook

• OpenInference package

• Working examples