Azure OpenAI

Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses Azure OpenAI. Azure OpenAI uses the same openai SDK under the hood, so the "openai" instrumentation handles it automatically.

You’ll keep calling Azure OpenAI exactly as you do today. Telemetry simply observes and enriches those calls.

Requirements

A Latitude account and API key
A Latitude project slug
A project that uses the Azure OpenAI SDK (via the openai package)

Steps

Install

TypeScript
Python

npm install @latitude-data/telemetry

pnpm add @latitude-data/telemetry

yarn add @latitude-data/telemetry

bun add @latitude-data/telemetry

pip install latitude-telemetry

uv add latitude-telemetry

poetry add latitude-telemetry

Initialize and use

Azure OpenAI uses the "openai" instrumentation: the same one used for standard OpenAI.

TypeScript
Python

import { Latitude, capture } from "@latitude-data/telemetry"
import { AzureOpenAI, OpenAI } from "openai"

const latitude = new Latitude({
  apiKey: process.env.LATITUDE_API_KEY!,
  project: process.env.LATITUDE_PROJECT_SLUG!,
  instrumentations: { openai: OpenAI },
})


const client = new AzureOpenAI({
  endpoint: process.env.AZURE_OPENAI_ENDPOINT,
  apiKey: process.env.AZURE_OPENAI_API_KEY,
  apiVersion: "2024-02-01",
})

await capture("generate-support-reply", async () => {
  const completion = await client.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: "Hello" }],
  })
  return completion.choices[0].message.content
})

await latitude.shutdown()

import openai
from openai import AzureOpenAI

from latitude_telemetry import Latitude, capture

latitude = Latitude(
    api_key="your-api-key",
    project="your-project-slug",
    instrumentations={"openai": openai},
)

client = AzureOpenAI(
    azure_endpoint="https://your-resource.openai.azure.com/",
    api_key="your-azure-api-key",
    api_version="2024-02-01",
)

def generate_support_reply():
    completion = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Hello"}],
    )
    return completion.choices[0].message.content

capture("generate-support-reply", generate_support_reply)

latitude.shutdown()

Streaming

When streaming, consume the stream inside capture() so the span covers the full operation:

TypeScript
Python

await capture("stream-reply", async () => {
  const stream = await client.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: input }],
    stream: true,
  })

  for await (const chunk of stream) {
    const content = chunk.choices[0]?.delta?.content
    if (content) res.write(content)
  }
  res.end()
})

def stream_reply():
    stream = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": input}],
        stream=True,
    )
    chunks = []
    for chunk in stream:
        if chunk.choices[0].delta.content:
            chunks.append(chunk.choices[0].delta.content)
    return "".join(chunks)

capture("stream-reply", stream_reply)

Seeing Your Traces

Once connected, traces appear automatically in Latitude:

Open your project in the Latitude dashboard
Each execution shows input/output messages, model, token usage, latency, and errors

Overview

Getting Started

Observe

Understand

Refine

Security and Compliance

Deployment

Development

More

Overview

Requirements

Steps

Streaming

Seeing Your Traces

​Overview

​Requirements

​Steps

​Streaming

​Seeing Your Traces

Overview

Requirements

Steps

Streaming

Seeing Your Traces