1

Setup the SDK

2

Monitor OpenAI

With our SDKs, tracking OpenAI calls is super simple.

import OpenAI from "openai"
import { monitorOpenAI } from "lunary/openai"

// Simply call monitor() on the OpenAIApi class to automatically track requests
const openai = new OpenAI()
const openai = monitorOpenAI(new OpenAI())

3

Tag requests and identify users

You can now tag requests and identify users.

const result = await openai.chat.completions.create({
  model: "gpt-4o",
  temperature: 0.9,
  tags: ["chat", "support"],  // Optional: tags
  user: "user_123",  // Optional: user ID
  userProps: { name: "John Doe" },  // Optional: user properties
  messages: [
    { role: "system", content: "You are an helpful assistant" },
    { role: "user", content: "Hello friend" },
  ],
})