Overview

We’ll explore a simple emotional support chat application built with Next.js that:

  1. Provides a chat interface for users seeking emotional support
  2. Uses OpenAI’s GPT model to generate empathetic responses
  3. Traces the entire process with Laminar
  4. Utilizes Vercel’s AI SDK for AI interactions

Setup

You can use the example app from our GitHub repo.

Alternatively, for a clean install, follow these steps:

1

Initialize a Next.js app

npx create-next-app@latest

Learn more in the Next.js docs.

2

Install Dependencies

Let’s now install the required packages:

npm install ai @ai-sdk/openai @lmnr-ai/lmnr
3

Environment Setup

cp .env.local.example .env.local

And then fill in the .env.local file. Get Laminar project API key. Get OpenAI API key

4

Project Structure

The project has the following structure:

nextjs-app/
├── .env.local
├── app/
│   ├── api/
│   │   └── chat/
│   │       └── route.ts
│   ├── page.tsx
│   └── layout.tsx
├── components/
│   └── chat-ui.tsx
├── instrumentation.ts
└── ...

Implementation

Let’s look at the key components of our Next.js application with Laminar tracing:

1. instrumentation.ts

This file is crucial as it initializes Laminar for tracing. Next.js automatically loads this file during initialization.

instrumentation.ts
export async function register() {
  if (process.env.NEXT_RUNTIME === 'nodejs') {
    const { Laminar } = await import('@lmnr-ai/lmnr')
    
    Laminar.initialize({
      apiKey: process.env.LMNR_PROJECT_API_KEY,
      // By default, Laminar filters out Next.js spans.
      // You can preserve them by setting this to true.
      // They are somewhat noisy, but can be useful for debugging.
      // preserveNextJsSpans: true,
    })
  }
}

Laminar only works in the ‘nodejs’ runtime of Next.js.

Learn more about the instrumentation.ts file in the Next.js docs.

Laminar must be initialized at the entry point of the application. For Next.js, the instrumentation.ts file is ideal for this purpose as it’s loaded early in the application lifecycle.

2. app/page.tsx

This file contains the main page layout for our chat application:

app/page.tsx
import ChatUI from "@/components/chat-ui";

export default function Home() {
  return (
    <div className="grid grid-rows-[auto_1fr_auto] min-h-screen p-4 sm:p-6 font-[family-name:var(--font-geist-sans)]">
      <header className="py-4 text-center">
        <h1 className="text-2xl font-bold text-blue-600 mb-1">Therapy Chat</h1>
        <p className="text-sm text-gray-600 dark:text-gray-400 max-w-lg mx-auto">
          A safe space to share your thoughts and receive supportive guidance.
          Your conversation is private and confidential.
        </p>
      </header>
      <main className="w-full max-w-4xl mx-auto my-4">
        <ChatUI />
      </main>
      <footer className="py-4 text-center text-sm text-gray-500 dark:text-gray-400">
        <p>AI-powered support | Not a substitute for professional medical advice</p>
      </footer>
    </div>
  );
}

3. app/api/chat/route.ts

This file contains the API route handler that processes chat messages and communicates with the OpenAI API:

app/api/chat/route.ts
import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";
import { NextRequest, NextResponse } from "next/server";

export async function POST(request: NextRequest) {
  try {
    const body = await request.json();
    const { messages } = body;

    // Create system message with therapeutic instructions
    const systemMessage = {
      role: 'system',
      content: `You are an AI-powered therapist assistant. Respond with empathy, understanding, and professionalism.
Your goal is to provide supportive responses that help the user process their feelings and thoughts.
Never give medical advice or diagnose conditions.`
    };

    // Use the messages parameter directly with the system message as the first element
    const response = await generateText({
      model: openai("gpt-4.1-nano"),
      messages: [systemMessage, ...messages],
      experimental_telemetry: {
        isEnabled: true,
      }
    });

    return NextResponse.json({ message: response.text });
  } catch (error) {
    console.error("Error in chat API:", error);
    return NextResponse.json(
      { error: "Failed to process request" },
      { status: 500 }
    );
  }
}

The experimental_telemetry option is enabled, which allows AI SDK to send telemetry data. This works seamlessly with Laminar’s tracing capabilities.

4. components/chat-ui.tsx

This component handles the chat interface and manages the chat state.

Feel free to modify the UI as you see fit, this is just an example.

Running the Application

Start the Next.js development server:

npm run dev

Testing the Application

  1. Navigate to http://localhost:3000 in your browser
  2. Interact with the chat interface by typing messages

Viewing Traces

After interacting with the chat, you can view the traces in your Laminar dashboard at https://www.lmnr.ai. The trace will show:

  1. The Next.js API route execution
  2. The OpenAI API call made through Vercel’s AI SDK
  3. Token usage and response details

Key Features Demonstrated

  1. Next.js Instrumentation: Using Next.js’s instrumentation API to initialize Laminar
  2. AI SDK Integration: Seamless integration with Vercel’s AI SDK
  3. OpenAI Tracing: Automatic tracing of OpenAI API calls
  4. Token Usage: Automatic calculation of tokens used for each OpenAI call
  5. Cost Estimation: Automatic estimation of the cost of each OpenAI call

Example Traces

A screenshot of a trace from the example app.

A screenshot of the similar trace if you enable `preserveNextJsSpans: true` in the `instrumentation.ts` file.

Troubleshooting

If you encounter issues:

  • Check that your API keys are correctly set in the .env.local file
  • Verify that Laminar is properly initialized in the instrumentation.ts file
  • Ensure all dependencies are installed
  • Review the Next.js development server logs for any application errors