How to Create Your Own ChatGPT in HTML CSS and JavaScript
9 min readJul 27, 2023
ChatGPT has grown significantly in popularity over the past few months or years, completely changing the way we interact with automated chatbots. As a beginner web developer, you might be curious to create your own ChatGPT. The good news is that it is possible to create a ChatGPT clone using standard HTML, CSS and JavaScript.
If you are not familiar: ChatGPT is an advanced chatbot template developed by Open AI. It uses artificial intelligence to generate human-like responses in a conversational format. ChatGPT has grown tremendously in popularity due to its ability to simulate natural conversations.
In this blog post, we’ll walk you through the steps to create your own ChatGPT using HTML, CSS, and JavaScript. By creating a ChatGPT clone project, budding web developers can gain hands-on experience and apply their HTML, CSS, and JavaScript skills to real projects.
This ChatGPT clone project lets you ask questions and get answers instantly. Moreover, you have the option to switch between dark and light themes. Your chat history is stored in the browser’s local storage, so it persists even if you refresh the page. However, you can easily delete chats by clicking the corresponding Delete Chat button.
Read More: Frequently Asked Questions: Interview Questions for JavaScript
Steps to create a ChatGPT clone using HTML and JavaScript
To create your own ChatGPT using HTML, CSS and JavaScript, follow these steps — step — detailed instructions:
- Create a folder. You can name this folder whatever you want and create the named files in this folder.
- Create an index.html file. The file name should be index and its extension .html.
- Create a style.css file. The file name should be “style” and the extension should be “.css”.
- Create a script.js file. The file name should be “script” with the extension “.js”.
- Download the images folder and place it in your project directory. This folder contains the user’s avatar and the chatbot’s logo.
- First add the following HTML codes to your index.html file: in this code snippet, you will find a “Container of cat” -Div. Later we will use JavaScript to dynamically add the “chat” div which contains all the chat details.
<!DOCTYPE html>
<html lang="en" dir="ltr">
<head>
<meta charset="utf-8">
<title>ChatGPT Clone in JavaScript | CodingNepal</title>
<link rel="stylesheet" href="style.css">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<!-- Google Fonts Link For Icons -->
<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Material+Symbols+Rounded:opsz,wght,FILL,GRAD@20..48,100..700,0..1,-50..200" />
<script src="script.js" defer></script>
</head>
<body>
<!-- Chats container -->
<div class="chat-container"></div>
<!-- Typing container -->
<div class="typing-container">
<div class="typing-content">
<div class="typing-textarea">
<textarea id="chat-input" spellcheck="false" placeholder="Enter a prompt here" required></textarea>
<span id="send-btn" class="material-symbols-rounded">send</span>
</div>
<div class="typing-controls">
<span id="theme-btn" class="material-symbols-rounded">light_mode</span>
<span id="delete-btn" class="material-symbols-rounded">delete</span>
</div>
</div>
</body>
</html>Then, add the accompanying CSS codes to your style.css document to apply visual styling to your ChatGPT interface. Presently, in the event that you load the website page in your program, you will see ChatGPT showed with a message input box and a few symbols at the base.
/* Import Google font - Poppins */
@import url('https://fonts.googleapis.com/css2?family=Poppins:wght@400;500;600&display=swap');
* {
margin: 0;
padding: 0;
box-sizing: border-box;
font-family: "Poppins", sans-serif;
}
:root {
--text-color: #FFFFFF;
--icon-color: #ACACBE;
--icon-hover-bg: #5b5e71;
--placeholder-color: #dcdcdc;
--outgoing-chat-bg: #343541;
--incoming-chat-bg: #444654;
--outgoing-chat-border: #343541;
--incoming-chat-border: #444654;
}
.light-mode {
--text-color: #343541;
--icon-color: #a9a9bc;
--icon-hover-bg: #f1f1f3;
--placeholder-color: #6c6c6c;
--outgoing-chat-bg: #FFFFFF;
--incoming-chat-bg: #F7F7F8;
--outgoing-chat-border: #FFFFFF;
--incoming-chat-border: #D9D9E3;
}
body {
background: var(--outgoing-chat-bg);
}
/* Chats container styling */
.chat-container {
overflow-y: auto;
max-height: 100vh;
padding-bottom: 150px;
}
:where(.chat-container, textarea)::-webkit-scrollbar {
width: 6px;
}
:where(.chat-container, textarea)::-webkit-scrollbar-track {
background: var(--incoming-chat-bg);
border-radius: 25px;
}
:where(.chat-container, textarea)::-webkit-scrollbar-thumb {
background: var(--icon-color);
border-radius: 25px;
}
.default-text {
display: flex;
align-items: center;
justify-content: center;
flex-direction: column;
height: 70vh;
padding: 0 10px;
text-align: center;
color: var(--text-color);
}
.default-text h1 {
font-size: 3.3rem;
}
.default-text p {
margin-top: 10px;
font-size: 1.1rem;
}
.chat-container .chat {
padding: 25px 10px;
display: flex;
justify-content: center;
color: var(--text-color);
}
.chat-container .chat.outgoing {
background: var(--outgoing-chat-bg);
border: 1px solid var(--outgoing-chat-border);
}
.chat-container .chat.incoming {
background: var(--incoming-chat-bg);
border: 1px solid var(--incoming-chat-border);
}
.chat .chat-content {
display: flex;
max-width: 1200px;
width: 100%;
align-items: flex-start;
justify-content: space-between;
}
span.material-symbols-rounded {
user-select: none;
cursor: pointer;
}
.chat .chat-content span {
cursor: pointer;
font-size: 1.3rem;
color: var(--icon-color);
visibility: hidden;
}
.chat:hover .chat-content:not(:has(.typing-animation), :has(.error)) span {
visibility: visible;
}
.chat .chat-details {
display: flex;
align-items: center;
}
.chat .chat-details img {
width: 35px;
height: 35px;
align-self: flex-start;
object-fit: cover;
border-radius: 2px;
}
.chat .chat-details p {
white-space: pre-wrap;
font-size: 1.05rem;
padding: 0 50px 0 25px;
color: var(--text-color);
word-break: break-word;
}
.chat .chat-details p.error {
color: #e55865;
}
.chat .typing-animation {
padding-left: 25px;
display: inline-flex;
}
.typing-animation .typing-dot {
height: 7px;
width: 7px;
border-radius: 50%;
margin: 0 3px;
opacity: 0.7;
background: var(--text-color);
animation: animateDots 1.5s var(--delay) ease-in-out infinite;
}
.typing-animation .typing-dot:first-child {
margin-left: 0;
}
@keyframes animateDots {
0%,44% {
transform: translateY(0px);
}
28% {
opacity: 0.4;
transform: translateY(-6px);
}
44% {
opacity: 0.2;
}
}
/* Typing container styling */
.typing-container {
position: fixed;
bottom: 0;
width: 100%;
display: flex;
padding: 20px 10px;
justify-content: center;
background: var(--outgoing-chat-bg);
border-top: 1px solid var(--incoming-chat-border);
}
.typing-container .typing-content {
display: flex;
max-width: 950px;
width: 100%;
align-items: flex-end;
}
.typing-container .typing-textarea {
width: 100%;
display: flex;
position: relative;
}
.typing-textarea textarea {
resize: none;
height: 55px;
width: 100%;
border: none;
padding: 15px 45px 15px 20px;
color: var(--text-color);
font-size: 1rem;
border-radius: 4px;
max-height: 250px;
overflow-y: auto;
background: var(--incoming-chat-bg);
outline: 1px solid var(--incoming-chat-border);
}
.typing-textarea textarea::placeholder {
color: var(--placeholder-color);
}
.typing-content span {
width: 55px;
height: 55px;
display: flex;
border-radius: 4px;
font-size: 1.35rem;
align-items: center;
justify-content: center;
color: var(--icon-color);
}
.typing-textarea span {
position: absolute;
right: 0;
bottom: 0;
visibility: hidden;
}
.typing-textarea textarea:valid ~ span {
visibility: visible;
}
.typing-controls {
display: flex;
}
.typing-controls span {
margin-left: 7px;
font-size: 1.4rem;
background: var(--incoming-chat-bg);
outline: 1px solid var(--incoming-chat-border);
}
.typing-controls span:hover {
background: var(--icon-hover-bg);
}
/* Reponsive Media Query */
@media screen and (max-width: 600px) {
.default-text h1 {
font-size: 2.3rem;
}
:where(.default-text p, textarea, .chat p) {
font-size: 0.95rem!important;
}
.chat-container .chat {
padding: 20px 10px;
}
.chat-container .chat img {
height: 32px;
width: 32px;
}
.chat-container .chat p {
padding: 0 20px;
}
.chat .chat-content:not(:has(.typing-animation), :has(.error)) span {
visibility: visible;
}
.typing-container {
padding: 15px 10px;
}
.typing-textarea textarea {
height: 45px;
padding: 10px 40px 10px 10px;
}
.typing-content span {
height: 45px;
width: 45px;
margin-left: 5px;
}
span.material-symbols-rounded {
font-size: 1.25rem!important;
}
}At last, add the accompanying JavaScript code to your script.js record. This content code will make your ChatGPT practical by empowering highlights, for example, visiting, exchanging among dull and light subjects, and saving talk history in the program.
const chatInput = document.querySelector("#chat-input");
const sendButton = document.querySelector("#send-btn");
const chatContainer = document.querySelector(".chat-container");
const themeButton = document.querySelector("#theme-btn");
const deleteButton = document.querySelector("#delete-btn");
let userText = null;
const API_KEY = "PASTE-YOUR-API-KEY-HERE"; // Paste your API key here
const loadDataFromLocalstorage = () => {
// Load saved chats and theme from local storage and apply/add on the page
const themeColor = localStorage.getItem("themeColor");
document.body.classList.toggle("light-mode", themeColor === "light_mode");
themeButton.innerText = document.body.classList.contains("light-mode") ? "dark_mode" : "light_mode";
const defaultText = `<div class="default-text">
<h1>ChatGPT Clone</h1>
<p>Start a conversation and explore the power of AI.<br> Your chat history will be displayed here.</p>
</div>`
chatContainer.innerHTML = localStorage.getItem("all-chats") || defaultText;
chatContainer.scrollTo(0, chatContainer.scrollHeight); // Scroll to bottom of the chat container
}
const createChatElement = (content, className) => {
// Create new div and apply chat, specified class and set html content of div
const chatDiv = document.createElement("div");
chatDiv.classList.add("chat", className);
chatDiv.innerHTML = content;
return chatDiv; // Return the created chat div
}
const getChatResponse = async (incomingChatDiv) => {
const API_URL = "https://api.openai.com/v1/completions";
const pElement = document.createElement("p");
// Define the properties and data for the API request
const requestOptions = {
method: "POST",
headers: {
"Content-Type": "application/json",
"Authorization": `Bearer ${API_KEY}`
},
body: JSON.stringify({
model: "text-davinci-003",
prompt: userText,
max_tokens: 2048,
temperature: 0.2,
n: 1,
stop: null
})
}
// Send POST request to API, get response and set the reponse as paragraph element text
try {
const response = await (await fetch(API_URL, requestOptions)).json();
pElement.textContent = response.choices[0].text.trim();
} catch (error) { // Add error class to the paragraph element and set error text
pElement.classList.add("error");
pElement.textContent = "Oops! Something went wrong while retrieving the response. Please try again.";
}
// Remove the typing animation, append the paragraph element and save the chats to local storage
incomingChatDiv.querySelector(".typing-animation").remove();
incomingChatDiv.querySelector(".chat-details").appendChild(pElement);
localStorage.setItem("all-chats", chatContainer.innerHTML);
chatContainer.scrollTo(0, chatContainer.scrollHeight);
}
const copyResponse = (copyBtn) => {
// Copy the text content of the response to the clipboard
const reponseTextElement = copyBtn.parentElement.querySelector("p");
navigator.clipboard.writeText(reponseTextElement.textContent);
copyBtn.textContent = "done";
setTimeout(() => copyBtn.textContent = "content_copy", 1000);
}
const showTypingAnimation = () => {
// Display the typing animation and call the getChatResponse function
const html = `<div class="chat-content">
<div class="chat-details">
<img src="images/chatbot.jpg" alt="chatbot-img">
<div class="typing-animation">
<div class="typing-dot" style="--delay: 0.2s"></div>
<div class="typing-dot" style="--delay: 0.3s"></div>
<div class="typing-dot" style="--delay: 0.4s"></div>
</div>
</div>
<span onclick="copyResponse(this)" class="material-symbols-rounded">content_copy</span>
</div>`;
// Create an incoming chat div with typing animation and append it to chat container
const incomingChatDiv = createChatElement(html, "incoming");
chatContainer.appendChild(incomingChatDiv);
chatContainer.scrollTo(0, chatContainer.scrollHeight);
getChatResponse(incomingChatDiv);
}
const handleOutgoingChat = () => {
userText = chatInput.value.trim(); // Get chatInput value and remove extra spaces
if(!userText) return; // If chatInput is empty return from here
// Clear the input field and reset its height
chatInput.value = "";
chatInput.style.height = `${initialInputHeight}px`;
const html = `<div class="chat-content">
<div class="chat-details">
<img src="images/user.jpg" alt="user-img">
<p>${userText}</p>
</div>
</div>`;
// Create an outgoing chat div with user's message and append it to chat container
const outgoingChatDiv = createChatElement(html, "outgoing");
chatContainer.querySelector(".default-text")?.remove();
chatContainer.appendChild(outgoingChatDiv);
chatContainer.scrollTo(0, chatContainer.scrollHeight);
setTimeout(showTypingAnimation, 500);
}
deleteButton.addEventListener("click", () => {
// Remove the chats from local storage and call loadDataFromLocalstorage function
if(confirm("Are you sure you want to delete all the chats?")) {
localStorage.removeItem("all-chats");
loadDataFromLocalstorage();
}
});
themeButton.addEventListener("click", () => {
// Toggle body's class for the theme mode and save the updated theme to the local storage
document.body.classList.toggle("light-mode");
localStorage.setItem("themeColor", themeButton.innerText);
themeButton.innerText = document.body.classList.contains("light-mode") ? "dark_mode" : "light_mode";
});
const initialInputHeight = chatInput.scrollHeight;
chatInput.addEventListener("input", () => {
// Adjust the height of the input field dynamically based on its content
chatInput.style.height = `${initialInputHeight}px`;
chatInput.style.height = `${chatInput.scrollHeight}px`;
});
chatInput.addEventListener("keydown", (e) => {
// If the Enter key is pressed without Shift and the window width is larger
// than 800 pixels, handle the outgoing chat
if (e.key === "Enter" && !e.shiftKey && window.innerWidth > 800) {
e.preventDefault();
handleOutgoingChat();
}
});
loadDataFromLocalstorage();
sendButton.addEventListener("click", handleOutgoingChat);Keep in mind, your ChatGPT isn’t yet prepared to produce visits in view of prompts. To make it useful, you want to focus on a pivotal detail in the code. Investigate, and you’ll see that you need to glue an “OpenAI Programming interface key” into the API_KEY variable.
To get your Programming interface key, visit the accompanying URL: https://platform.openai.com/account/programming interface keys. When there, sign in to your record, and you will actually want to create a free Programming interface key. To grasp different things in the code. I suggest watching the instructional exercise video, perusing the code remarks, and exploring different avenues regarding the code.
Conclusion
Congrats! You have effectively made a ChatGPT clone project utilizing HTML, CSS, and vanilla JavaScript and incorporated it with the OpenAI Programming interface. Presently, you can participate in significant discussions and exhibit your ability to companions and then some.
