OpenAI

Connect your OpenAI-powered application to Latitude for observability.

Work in progress: Telemetry documentation is still being updated. Integration steps and APIs may be incomplete or out of date. Verify against your SDK versions and check back for revisions.

Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses the OpenAI SDK.

You’ll keep calling 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 OpenAI SDK

---

Steps

1. Install

   TypeScript

   npm

   npm install @latitude-data/telemetry
   

   Python

   pip

   pip install latitude-telemetry
   
2. Initialize and use

   TypeScript

   import { initLatitude, capture } from "@latitude-data/telemetry"
   import OpenAI from "openai"
   
   const latitude = initLatitude({
     apiKey: process.env.LATITUDE_API_KEY!,
     projectSlug: process.env.LATITUDE_PROJECT_SLUG!,
     instrumentations: ["openai"],
   })
   
   await latitude.ready
   
   const openai = new OpenAI()
   
   await capture("generate-support-reply", async () => {
     const completion = await openai.chat.completions.create({
       model: "gpt-4o",
       messages: [{ role: "user", content: "Hello" }],
     })
     return completion.choices[0].message.content
   })
   
   await latitude.shutdown()
   

   Python

   from latitude_telemetry import init_latitude, capture
   from openai import OpenAI
   
   latitude = init_latitude(
       api_key="your-api-key",
       project_slug="your-project-slug",
       instrumentations=["openai"],
   )
   
   client = OpenAI()
   
   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

await capture("stream-reply", async () => {
  const stream = await openai.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()
})

Python

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

capture("stream-reply", stream_reply)

---

Seeing Your Traces

Once connected, traces appear automatically in Latitude:

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

---

That’s It

No changes to your OpenAI calls: just initialize Latitude and your LLM calls are traced.