OpenAI Tracing

Phoenix provides auto-instrumentation for the OpenAI Python Library.

Note*: This instrumentation also works with Azure OpenAI

Install

pip install openinference-instrumentation-openai openai

Setup

Add your OpenAI API key as an environment variable:

export OPENAI_API_KEY=[your_key_here]

Connect your application to Phoenix with the register function:

Run OpenAI

import openai

client = openai.OpenAI()
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a haiku."}],
)
print(response.choices[0].message.content)

Observe

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

Resources

• Example notebook

• OpenInference package

• Working examples