How to Use ChatGPT API in NodeJS?

ChatGPT is a very powerful chatbot by OpenAI that uses Natural Language Processing to interact like humans. It has become very popular among developers and is being widely used for some of its state-of-the-art features, like understanding and interpreting code, and even generating code based on textual requirements. OpenAI has not only provided its functionality as a chatbot on the website but has also provided an API to help integrate ChatGPT into our applications and projects, using which we can make an HTTP request and utilize the response appropriately.

In this article, we will have a look at the step-by-step procedure to integrate ChatGPT API in the Node.js project.

Using ChatGPT in Node.js Application

Adding ChatGPT functionalities to our large-scale NodeJS Application will make that more efficient for the users. So in this article, we will see step by step implementation of where to retrieve the API key, and how to create a NodeJS application that uses OpenAI API, that will work similarly to ChatGPT, and you can make conversation with ChatGPT using that application. Here are the complete steps for using ChatGPT in NodeJS Application.

1. Creating a Node.js Application

First of all, we will create a directory for the project say, chatgpt-api-nodejs, either using GUI or by pasting the below command in the terminal at the desired location in our machine:

mkdir chatgpt-api-nodejs

Now, change the directory to the newly created folder:

cd chatgpt-api-nodejs

To initialize the node.js project, run the below command which creates a package.json file to keep track of project details

npm init -y

We will use axios for making HTTP requests and dotenv for managing environment variables.

npm install axios dotenv

2. Retrieving the OPENAI API Key

To use the API, we need to generate the API keys.

A. For that, go to OpenAI and either sign up or login (if you already have an account).

B. Then click on the API option

C. On the left corner you will see API keys, click on it and it will open API keys section. Click on 'Create new secret key, to crate a new one.

D. Click on the 'Create new secret key' button. It will open up a dialog box asking for the name of the key which is optional. After you are done, click 'Create secret key'.

E. A dialog box will appear displaying your secret key/API key. Copy it and 'done'. Save the key safely and do not share it with anyone.

Create a new file to create an environment variable for storing the API key

touch .env

In the file, create a variable OPENAI_API_KEY and replace "YOUR OPEN AI API KEY" with your API key (keeping the quotes)

OPENAI_API_KEY="YOUR OPEN AI API KEY"

3. Implementing NodeJS Application

Create a javascript file say, index.js, and paste the below code inside it.

require('dotenv').config();
const axios = require('axios');

const API_URL = 'https://api.openai.com/v1/chat/completions';
const API_KEY = process.env.OPENAI_API_KEY;

async function getChatResponse(prompt) {
    try {
        const response = await axios.post(
            API_URL,
            {
                model: "gpt-3.5-turbo",
                messages: [{ role: "user", content: prompt }],
                max_tokens: 100,
            },
            {
                headers: {
                    'Authorization': `Bearer ${API_KEY}`,
                    'Content-Type': 'application/json',
                },
            }
        );
        return response.data.choices[0].message.content;
    } catch (error) {
        console.error("Error calling ChatGPT API:", error.response ? error.response.data : error.message);
    }
}

(async () => {
    const response = await getChatResponse("What is ChatGPT?");
    console.log("ChatGPT Response:", response);
})();

4. Run the Application

To run the app, run the below command in terminal

node index.js

The above code takes the input prompt through the command line and prints the response generated by the ChatGPT model.

Output