Skip to main content
Python auto-instrumentation library for OpenAI’s Python SDK. The traces emitted by this instrumentation are fully OpenTelemetry compatible and can be sent to an OpenTelemetry collector for viewing, such as Arize Phoenix.

Installation

pip install openinference-instrumentation-openai

Quickstart

This example shows how to instrument a program that uses OpenAI and observe the traces via Arize Phoenix.

Install packages

pip install openinference-instrumentation-openai "openai>=1.26" arize-phoenix opentelemetry-sdk opentelemetry-exporter-otlp

Start Phoenix server

The Phoenix server runs entirely on your machine and does not send data over the internet.
python -m phoenix.server.main serve

Setup instrumentation

Configure the OpenAIInstrumentor and set up the tracer to send traces to Phoenix:
import openai
from openinference.instrumentation.openai import OpenAIInstrumentor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor

endpoint = "http://127.0.0.1:6006/v1/traces"
tracer_provider = trace_sdk.TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
# Optionally, you can also print the spans to the console.
tracer_provider.add_span_processor(SimpleSpanProcessor(ConsoleSpanExporter()))

OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)


if __name__ == "__main__":
    client = openai.OpenAI()
    response = client.chat.completions.create(
        model="gpt-3.5-turbo",
        messages=[{"role": "user", "content": "Write a haiku."}],
        max_tokens=20,
        stream=True,
        stream_options={"include_usage": True},
    )
    for chunk in response:
        if chunk.choices and (content := chunk.choices[0].delta.content):
            print(content, end="")

Set API key

export OPENAI_API_KEY=your-api-key

Run your application

python your_file.py
Visit the Phoenix app at http://localhost:6006 to see your traces.

Example with context attributes

import openai
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor

from openinference.instrumentation import using_attributes
from openinference.instrumentation.openai import OpenAIInstrumentor

endpoint = "http://127.0.0.1:6006/v1/traces"
tracer_provider = trace_sdk.TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
tracer_provider.add_span_processor(SimpleSpanProcessor(ConsoleSpanExporter()))

OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)


if __name__ == "__main__":
    client = openai.OpenAI()
    with using_attributes(
        session_id="my-test-session",
        user_id="my-test-user",
        metadata={
            "test-int": 1,
            "test-str": "string",
            "test-list": [1, 2, 3],
            "test-dict": {
                "key-1": "val-1",
                "key-2": "val-2",
            },
        },
        tags=["tag-1", "tag-2"],
        prompt_template="Who won the soccer match in {city} on {date}",
        prompt_template_version="v1.0",
        prompt_template_variables={
            "city": "Johannesburg",
            "date": "July 11th",
        },
    ):
        response = client.chat.completions.create(
            model="gpt-3.5-turbo",
            messages=[{"role": "user", "content": "Write a haiku."}],
            max_tokens=20,
        )
        print(response.choices[0].message.content)

FAQ

Q: How to get token counts when streaming? A: To get token counts when streaming, install openai>=1.26 and set stream_options={"include_usage": True} when calling create. See the example shown above. For more info, see OpenAI’s announcement.

More Info

Build docs developers (and LLMs) love