Judgment Labs Logo
DocumentationSDK ReferenceChangelog
Model Providers

OpenAI

If you use OpenAI models within your application, you can trace, monitor, and analyze them with Judgment. You can do this by either

  1. Judgeval Wrap: Add our wrap around the initialization of your client
  2. OpenTelemetry: Use the OpenAIInstrumentor library to wrap OpenAI SDK calls and send Otel spans to Judgment.

Judgeval Wrap

from openai import OpenAI
from judgeval import Judgeval

client = Judgeval(project_name="openai_project")
tracer = client.tracer.create()

openai_client = OpenAI()
wrapped_client = tracer.wrap(openai_client)  # Use wrapped_client from here on

OpenTelemetry

from judgeval import Judgeval
# Make sure you installed the dependency: opentelemetry-instrumentation-openai
from opentelemetry.instrumentation.openai import OpenAIInstrumentor

client = Judgeval(project_name="openai_project")
tracer = client.tracer.create()
OpenAIInstrumentor().instrument()

Always initialize the Tracer before calling OpenAIInstrumentor().instrument() to ensure proper trace routing.

Only use one of these options to trace OpenAI calls or you may see duplicate tracing.

Anthropic

Previous Page

OpenRouter

Next Page

Last updated on

On this page

Judgeval WrapOpenTelemetry