DEV Community

TopToDay AI
TopToDay AI

Posted on

How to Build an AI Chatbot in 10 Minutes

#crypto #webdev #productivity

How to Build an AI Chatbot in 10 Minutes

Platform: DevTo | Type: article

How to Build an AI Chatbot in 10 Minutes

Building an AI chatbot used to require months of training and complex infrastructure. But with modern APIs and serverless functions, you can ship a fully functional chatbot in under 10 minutes. Let’s do it.

What We’ll Build

A lightweight chatbot that:

  • Accepts natural language queries
  • Returns contextual responses using OpenAI’s GPT model
  • Stores conversation history for continuity
  • Runs on a serverless Node.js backend

Tech stack: Node.js, Express, OpenAI API, Vercel (or any host)

Step 1: Project Setup 

mkdir ai-chatbot
cd ai-chatbot
npm init -y
npm install express openai dotenv cors
touch index.js .env
Enter fullscreen mode Exit fullscreen mode

Add your OpenAI API key to .env:

OPENAI_API_KEY=your-key-here
Enter fullscreen mode Exit fullscreen mode

Step 2: The Core Bot Logic

In index.js, create the chatbot endpoint:

import express from 'express';
import cors from 'cors';
import OpenAI from 'openai';
import 'dotenv/config';

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

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

// In-memory conversation history (for demo)
const conversations = new Map();

app.post('/api/chat', async (req, res) => {
  const { message, sessionId } = req.body;

  // Initialize or get conversation history
  if (!conversations.has(sessionId)) {
    conversations.set(sessionId, [
      { role: 'system', content: 'You are a helpful assistant.' }
    ]);
  }

  const history = conversations.get(sessionId);
  history.push({ role: 'user', content: message });

  try {
    const completion = await openai.chat.completions.create({
      model: 'gpt-3.5-turbo',
      messages: history,
      max_tokens: 300,
    });

    const reply = completion.choices[0].message.content;
    history.push({ role: 'assistant', content: reply });

    res.json({ response: reply });
  } catch (error) {
    console.error(error);
    res.status(500).json({ error: 'Something went wrong' });
  }
});

app.listen(3000, () => console.log('Bot running on port 3000'));
Enter fullscreen mode Exit fullscreen mode

Step 3: The Frontend (5 Lines of HTML) 

<!DOCTYPE html>
<html>
<body>
  <div id="chat"></div>
  <input id="input" placeholder="Type a message..." />
  <button onclick="sendMessage()">Send</button>

  <script>
    const sessionId = crypto.randomUUID();

    async function sendMessage() {
      const msg = document.getElementById('input').value;
      const response = await fetch('/api/chat', {
        method: 'POST',
        headers: { 'Content-Type': 'application/json' },
        body: JSON.stringify({ message: msg, sessionId })
      });
      const data = await response.json();
      document.getElementById('chat').innerHTML += 
        `<p><strong>You:</strong> ${msg}</p>
         <p><strong>Bot:</strong> ${data.response}</p>`;
    }
  </script>
</body>
</html>
Enter fullscreen mode Exit fullscreen mode

Step 4: Deploy in 60 Seconds

For Vercel:

npm install -g vercel
vercel --prod
Enter fullscreen mode Exit fullscreen mode

That’s it. Your API is live. No database? No problem. The conversation history lives in memory for demo purposes—swap it for Redis or PostgreSQL in production.

When to Go Beyond 10 Minutes

This 10-minute bot is perfect for:

  • Internal tools
  • Rapid prototyping
  • Hackathon demos

For production, add:

  • Rate limiting
  • Persistence (Firebase, Supabase)
  • Streaming responses
  • Context window management

The 10-Minute Takeaway

You don’t need a PhD in NLP to build an AI chatbot. With one API call and a handful of lines of code, you can give your users conversational superpowers.

Try it now. Your bot will be answering questions before your coffee gets cold.

🔗 Useful tools (affiliate links)

Top comments (0)