Section: Making Secure API Calls with Express and Fetch API

Objective

This section guides you through using Express to securely make API calls to OpenAI's GPT-3.5-turbo model, receive JSON results, and parse them.

Prerequisites

• Basic knowledge of Express and Node.js.
• node-fetch package installed for using Fetch API in Node.js.
• An API key from OpenAI.

Steps

1. Environment Setup:

   • Install node-fetch using npm install node-fetch.
   • Store your OpenAI API key in an environment variable (e.g., OPENAI_API_KEY).

2. Creating an Express Route:

   const express = require('express');
   const fetch = require('node-fetch');
   const app = express();
   
   app.get('/api/gpt', async (req, res) => {
       // API call will be made here
   });
   
   const PORT = process.env.PORT || 3000;
   app.listen(PORT, () => console.log(`Server running on port ${PORT}`));
   

3. Making an API Call to OpenAI:

   app.get('/api/gpt', async (req, res) => {
       try {
           const response = await fetch('<https://api.openai.com/v1/engines/gpt-3.5-turbo/completions>', {
               method: 'POST',
               headers: {
                   'Content-Type': 'application/json',
                   'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`
               },
               body: JSON.stringify({ prompt: "Translate the following English text to French: 'Hello, world!'", max_tokens: 60 })
           });
   
           if (!response.ok) {
               throw new Error(`Error: ${response.status}`);
           }
   
           const data = await response.json();
           res.json(data);
       } catch (error) {
           res.status(500).json({ message: error.message });
       }
   });
   

4. Running the Server:

   • Start your Express server.
   • Access the route (e.g., http://localhost:3000/api/gpt) to make the API call.