🤖 Your First AI Endpoint

Time for the exciting part - making your server intelligent! 🧠

You’re about to create an API endpoint that sends messages to OpenAI and gets smart responses back. This is the foundation of every AI application.

🔍 OpenAI API Options (Quick Overview)

OpenAI gives you three ways to interact with their models:

💬 Chat Completion API - The classic way (still great for many apps)
🤖 Agent SDK - For advanced AI agents (we’ll use this later)
⚡ Response API - The newest, simplest approach (we’re starting here)

Why Response API? It’s cleaner, more flexible, and gives you access to the latest features. Perfect for learning.

// This is all you need for AI responses!
const response = await client.responses.create({
  model: "gpt-4o-mini",
  input: "Your message here"
});

---

🛠️ Step 1: Add OpenAI to Your Server

Open your index.js file and add the OpenAI import:

import express from "express";
import { config } from "dotenv";
import cors from "cors";
import OpenAI from "openai"; // 👈 Add this line

config();

Why at the top? ES6 imports must go at the beginning of your file.

---

🔧 Step 2: Create the OpenAI Client

Add this after your Express app setup, but before your routes:

const app = express();
const PORT = process.env.PORT || 8000;

// Create OpenAI client (do this once!)
const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

app.use(cors());
app.use(express.json());

Important: Create the client once when your server starts, not on every request. This is much more efficient.

---

🤖 Step 3: Create Your AI Chat Endpoint

Now for the main event - add this endpoint:

// AI Chat endpoint
app.post("/api/chat", async (req, res) => {
  try {
    // Get the message from the request
    const { message } = req.body;

    // Make sure we have a message
    if (!message) {
      return res.status(400).json({ error: "Message is required" });
    }

    // Call OpenAI and get a response
    const response = await openai.responses.create({
      model: "gpt-4o-mini", // Start with the cheaper model
      input: message,
    });

    // Send the AI's response back
    res.json({
      response: response.output_text,
      model: "gpt-4o-mini",
      success: true
    });

  } catch (error) {
    console.error("OpenAI Error:", error);
    res.status(500).json({
      error: "Failed to get AI response",
      success: false
    });
  }
});

What each part does:

• POST /api/chat - Your frontend will send messages here
• { message } - Extract the user’s message from the request
• openai.responses.create() - Send message to OpenAI, get AI response
• response.output_text - The actual AI response text
• try/catch - Handle errors gracefully (API issues, network problems, etc.)

---

📝 Your Complete index.js File

Here’s how your complete index.js should look:

import express from "express";
import { config } from "dotenv";
import cors from "cors";
import OpenAI from "openai";

config();

const app = express();
const PORT = process.env.PORT || 8000;

// Create OpenAI client once
const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

// Middleware
app.use(cors());
app.use(express.json());

// Test route
app.get("/", (req, res) => {
  res.json({
    message: "🤖 OpenAI Backend is running!",
    status: "ready"
  });
});

// AI Chat endpoint
app.post("/api/chat", async (req, res) => {
  try {
    const { message } = req.body;

    if (!message) {
      return res.status(400).json({ error: "Message is required" });
    }

    const response = await openai.responses.create({
      model: "gpt-4o-mini",
      input: message,
    });

    res.json({
      response: response.output_text,
      model: "gpt-4o-mini",
      success: true
    });

  } catch (error) {
    console.error("OpenAI Error:", error);
    res.status(500).json({
      error: "Failed to get AI response",
      success: false
    });
  }
});

// Start server
app.listen(PORT, () => {
  console.log(`🚀 Server running on http://localhost:${PORT}`);
  console.log(`🤖 AI endpoint ready at /api/chat`);
});

---

🧪 Test Your AI Endpoint

Start your server:

npm run dev

Test with curl:

curl -X POST http://localhost:8000/api/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello! Tell me a fun fact about space."}'

Success looks like:

{
  "response": "Did you know that one day on Venus (243 Earth days) is longer than one Venus year (225 Earth days)? This means a day on Venus lasts longer than its year!",
  "model": "gpt-4o-mini",
  "success": true
}

Using Postman/Insomnia:

• Method: POST
• URL: http://localhost:8000/api/chat
• Headers: Content-Type: application/json
• Body: {"message": "Your question here"}

---

🔧 Common Issues & Solutions

❌ “401 Unauthorized”

• Check your API key in .env
• Make sure there are no extra spaces around the key

❌ “insufficient_quota”

• Add more credits to your OpenAI account
• Remember, you need at least $5 to start

❌ “Cannot POST /api/chat”

• Make sure your server is running (npm run dev)
• Check you’re using the correct URL and method (POST)

❌ Server crashes

• Check the console for error details
• Make sure your .env file exists and has the API key

---

Congratulations! 🎉 Your server can now talk to AI!

This is huge - you’ve just created the foundation for any AI application. Your backend can now:

• Receive messages from users
• Send them to OpenAI
• Return intelligent responses
• Handle errors gracefully

👉 Next: Building the Chat Interface - Let’s create a beautiful frontend!