Creating a Contact Form API with Spam Detection Using ChatGPT

Creating a Contact Form API with Spam Detection Using ChatGPT

Introduction

In this tutorial, we will create an open-source API that allows users to submit a contact form from a web page. One of the main challenges of handling contact form submissions is dealing with spam. To address this, we will integrate ChatGPT's API to detect and prevent spam submissions. By the end of this tutorial, you'll have a fully functional API that evaluates contact form submissions for spam before accepting them.

Source Code

You can find the code files for this project here: Contact API Source Code

Setting Up the Project

First, let's set up our project. We'll use Node.js with Express for the server, and we'll need a few other dependencies for handling CORS, parsing request bodies, and making HTTP requests.

1. Initialize the Project

   mkdir contact-form-api
   cd contact-form-api
   npm init -y
   

2. Install Dependencies

   npm install express cors body-parser axios dotenv
   

Environment Configuration

Next, we need to configure our environment variables. Create a .env file in the root of your project and add the following variables:

PORT=5000
OPENAI_API_KEY=your_openai_api_key
ALLOWED_ORIGINS=http://localhost:3000,http://example.com

Replace your_openai_api_key with your actual OpenAI API key, and adjust ALLOWED_ORIGINS to include the origins you want to allow.

Creating the Express Server

Let's create our server using Express. We'll configure CORS to allow requests from specified origins and set up the body-parser middleware to parse JSON request bodies.

Create a file named app.js and add the following code:

require('dotenv').config();
const express = require('express');
const cors = require('cors');
const bodyParser = require('body-parser');
const axios = require('axios');

const app = express();
const port = process.env.PORT || 5000;

app.use(bodyParser.json());

const allowedOrigins = process.env.ALLOWED_ORIGINS.split(',');

const corsOptions = {
  origin: function (origin, callback) {
    if (allowedOrigins.indexOf(origin) !== -1 || !origin) {
      callback(null, true);
    } else {
      callback(new Error('Not allowed by CORS'));
    }
  },
  optionsSuccessStatus: 200
};

app.use(cors(corsOptions));

Implementing the Spam Check

We will use ChatGPT's API to evaluate the content of the contact form submissions for potential spam. Here is the function that performs the spam check:

const checkForSpam = async (content) => {
  const prompt = `
  Evaluate the following contact form submission for potential spam, risky information, or suspicious content:

  "${content}"

  Respond with "safe" if it appears to be legitimate, or "spam" if it appears to be spam or risky.
  `;

  const response = await axios.post(
    'https://api.openai.com/v1/chat/completions',
    {
      model: 'gpt-3.5-turbo',
      messages: [{ role: 'system', content: prompt }],
    },
    {
      headers: {
        'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`,
        'Content-Type': 'application/json',
      },
    }
  );

  return response.data.choices[0].message.content.trim().toLowerCase();
};

Handling Form Submissions

Now, let's set up the /api/contact endpoint to handle form submissions. We will validate the input, check for spam, and respond accordingly.

app.post('/api/contact', async (req, res) => {
  const { name, email, subject, message } = req.body;
  if (!name || !email || !subject || !message) {
    return res.status(400).json({ error: 'All fields are required' });
  }

  const contactContent = `Name: ${name}, Email: ${email}, Subject: ${subject}, Message: ${message}`;

  try {
    const result = await checkForSpam(contactContent);

    if (result === 'spam') {
      return res.status(400).json({ error: 'Your message was identified as spam or risky content.' });
    }

    res.status(200).json({ message: 'Form submitted successfully' });
  } catch (error) {
    console.error('Error processing contact form:', error);
    res.status(500).json({ error: 'Internal server error' });
  }
});

Running and Testing the API

Finally, let's add code to start the server and provide instructions on how to run and test the API.

app.listen(port, () => {
  console.log(`Server is running on port ${port}`);
});

1. Start the Server

   npm start
   

2. Test the API

   You can use Postman or any other API testing tool to test the API. Send a POST request to http://localhost:5000/api/contact with a JSON body containing name, email, subject, and message.

   Example request body:

   {
     "name": "John Doe",
     "email": "john.doe@example.com",
     "subject": "Inquiry",
     "message": "I would like to know more about your services."
   }
   

   The server will evaluate the submission and respond with either a success message or an error message if the submission is identified as spam.

Conclusion

In this tutorial, we created a contact form API that uses ChatGPT's API to detect and prevent spam submissions. This approach helps ensure that only legitimate messages are processed, reducing the risk of spam and malicious content. This API can be further enhanced with additional features such as email notifications or saving submissions to a database. The possibilities are endless, and you are encouraged to experiment and build upon this foundation. Happy coding!