Instructor Tracing

Install#

pip install openinference-instrumentation-instructor instructor

Be sure you also install the OpenInference library for the underlying model you’re using along with Instructor. For example, if you’re using OpenAI calls directly, you would also add: openinference-instrumentation-openai

Setup#

Connect your application to Phoenix with the register function:

from phoenix.otel import register# configure the Phoenix tracertracer_provider = register(project_name="my-llm-app", # Default is 'default'auto_instrument=True # Auto-instrument your app based on installed OI dependencies)

Run Instructor#

From here you can use instructor as normal.

import instructorfrom pydantic import BaseModelfrom openai import OpenAI# Define your desired output structureclass UserInfo(BaseModel):    name: str    age: int# Patch the OpenAI clientclient = instructor.from_openai(OpenAI())# Extract structured data from natural languageuser_info = client.chat.completions.create(    model="gpt-3.5-turbo",    response_model=UserInfo,    messages=[{"role": "user", "content": "John Doe is 30 years old."}],)print(user_info.name)#> John Doeprint(user_info.age)#> 30

Observe#

Now that you have tracing setup, all invocations of your underlying model (completions, chat completions, embeddings) and instructor triggers will be streamed to your running Phoenix for observability and evaluation.