Quickstart

Launch a local version of Phoenix

You can use Phoenix's open-source package to launch a local instance of Phoenix on your machine. For more info on other self-hosting options, like Docker, see Self-hosting

First, install the Phoenix package:

pip install arize-phoenix

Then launch your instance in terminal:

phoenix serve

Connect your app to Phoenix

To collect traces from your application, you must configure an OpenTelemetry TracerProvider to send traces to Phoenix. The register utility from the phoenix module streamlines this process.

Connect your application to your cloud instance using:

import os
from phoenix.otel import register

# Add Phoenix API Key for tracing
PHOENIX_API_KEY = "ADD YOUR API KEY"
os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={PHOENIX_API_KEY}"

# configure the Phoenix tracer
tracer_provider = register(
  endpoint="http://localhost:4317",  # Sends traces using gRPC
) 

Your app is now connected to Phoenix! Any OpenTelemetry traces you generate will be sent to your Phoenix instance.

Instrument your app and trace a request

Let's generate some of those traces now. We'll use OpenAI in this example, but Phoenix has dozens of other integrations to choose from as well.

First we'll import our instrumentor and the OpenAI package:

pip install openinference-instrumentation-openai openai 'httpx<0.28'

Then enable our OpenAI integration:

from openinference.instrumentation.openai import OpenAIInstrumentor

OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)

And finally send a request to OpenAI:

import openai
import os

os.environ["OPENAI_API_KEY"] = "YOUR OPENAI API KEY"

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

View traces in Phoenix

You should now see traces in Phoenix!