Skip to main content

OpenTelemetry openai instrumentation

Project description

opentelemetry-instrument-openai

It's OpenTelemetry instrumentation (python) for OpenAI's library.

How to use it

Simple! First, install this package.

Autoinstrumentation

opentelemetry-bootstrap -a install
opentelemetry-instrument \
  --traces_exporter console \
  --metrics_exporter none \
  --logs_exporter none \
  python chat.py

If you're using poetry, put poetry run before each command.

In code

It's one line of code too:

import openai
from dotenv import load_dotenv
from opentelemetry.instrument.openai import OpenAIInstrumentor

OpenAIInstrumentor().instrument()

load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")

openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[{"role":"user", "content":"Tell me a joke about opentelemetry"}],
)

How to develop

Get poetry. Python build and dependency management is fucked but this is about as good as it gets.

Now install and run tests:

poetry install
poetry run pytest

Now you can develop and run tests as you go!

How to run the example

Click the example folder and read the README.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

opentelemetry_instrument_openai-0.1.0.tar.gz (7.0 kB view hashes)

Uploaded Source

Built Distribution

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page