Creating your own AI ChatBot might seem hard if you don’t know how to code. But now, with tools like the ChatGPT API, it’s easier than before.

In this guide, we’ll show you step by step how to make your own AI ChatBot for free using the ChatGPT API. We’ll help you set it up, figure out what you want it to do, and add it to your favourite platform. Let’s get started on making your very own AI ChatBot.

What are AI ChatBots.

Chatbots are computer programs that use artificial intelligence (AI) to simulate human conversation or interaction. These chatbots are designed to understand and respond to user queries or commands in a natural language format.

They can be used for various purposes, such as

• Customer service
• Information retrieval
• Entertainment.
• Education Purposes

An example of the most popular AI Chatbot is ChatGPT and Google Bard.

Read also ;

• What is Google Bard?; Everything you need to know.
• Comprehensive differences between Google Bard and ChatGPT

Understanding ChatGPT API .

Before we begin, let’s understand what the ChatGPT API is. Developed by OpenAI, it’s a powerful tool for creating human-like text responses based on the input you provide, using advanced machine learning to simulate human interaction.

Things To remember Before You Start to Create Your AI ChatBot.

• This guide is for everyone, with clear instructions and examples, making it easy for even basic computer users to create their own AI chatbot.
• You don’t need a powerful computer for creating an AI chatbot. OpenAI’s API does the heavy lifting in the cloud.
• Explain clearly what the chatbot is for and why it’s helpful to users.
• Learn a lot about the people you want to use the chatbot, like what they like, how they talk, and what they need.
• Think about things like how old they are, how well they speak the language, and anything else that could affect how the chatbot works.
• Decide where the chatbot will work best, like on a website, a phone app, messaging apps like Facebook Messenger or Slack, or voice assistants like Amazon Alexa or Google Assistant.
• Think about what they can do, how many people use them, and how well they can work together with other things.
• You can create a ChatGPT chatbot on various platforms, including Windows, macOS, Linux, or ChromeOS.

Let’s now dive into the Step by Step tutorial.

Set Up the Software Environment to Create an AI Chatbot.

You need a few things to start making an AI chatbot with ChatGPT. You’ll need

• Python
• Pip
• OpenAI
• Gradio libraries,
• OpenAI API key
• Code editor like Notepad++

But don’t worry, setting it all up is easy, and I’ll show you how.

Install Python

• To begin, ensure that Python is installed on your computer. Access the provided link and download the setup file compatible with your platform.

• After downloading, open the setup file and check the box that says “Add Python.exe to PATH.” This step is crucial. Then, select “Install Now” and follow the regular installation process for Python.

• To verify if Python is correctly installed, open the Terminal on your computer. If you are using Windows, you can use either Windows Terminal or Command Prompt. Once in the Terminal, execute the command below, and it will display the Python version. On Linux or other platforms, you might need to use python3 --version instead of python --versio .

python --version

Upgrade Pip.

Besides Python, you will also have Pip installed on your system automatically. In this part, we’ll see how to update it to the latest version.

Pip is a tool that helps you install many useful libraries for Python from the Terminal. With Pip, you can install libraries like OpenAI and Gradio. Here’s what you need to do.

• Launch the Terminal on your PC. I’m using the Windows Terminal. Then, execute the command below to update Pip. Remember, on Linux or other platforms, you might need to use python3 and pip3 .

python -m pip install -U pip

Install OpenAI and Gradio Libraries.

• Let’s proceed to install the OpenAI library, which will enable us to engage with ChatGPT through their API. In the Terminal, run the command below to install the OpenAI library using Pip. If the command doesn’t work, try using  pip3.

pip install openai

• Once the installation is complete, we’ll install Gradio. Gradio enables you to swiftly create a user-friendly web interface to showcase your AI chatbot. It also simplifies the process of sharing your chatbot online via link to share.

pip install gradio

Download a Code Editor.

• Lastly, you’ll need a code editor to modify some of the code. For Windows, I suggest using Notepad++ (Download here). Just download and install the program from the provided link. If you prefer robust IDEs, you can use VS Code on any platform. Apart from VS Code, you can also install Sublime Text (Download here ) on macOS and Linux.
• On ChromeOS, you can utilize the excellent Caret app (Download here) for code editing. We’re nearly finished setting up the software environment, and it’s time to acquire the OpenAI API key.

Get the OpenAI API Key For Free.

To build a ChatGPT-driven AI chatbot, you’ll need an OpenAI API key. This key allows you to integrate ChatGPT into your interface and display results.

OpenAI currently offers free API keys with $5 credit for three months, or $18 for early account holders. After the credit runs out, payment is required for API access, but it’s currently free for all users.

• Feel free to visit https://platform.openai.com/signup  to create a new account or log in if you already have ChatGPT account.

You can also check how to use ChatGPT and ChatGPT-4 in this easy step by step guide.

• Afterward, click on your profile located in the top-right corner and choose “View API keys” from the drop-down menu.

• At this stage, select “Create new secret key” and copy the API key. Please keep in mind that you won’t be able to view or copy the complete API key later, so it’s crucial to immediately paste it into a Notepad file for safekeeping.

• Furthermore, avoid sharing the API key publicly, as it’s meant for your account access only. You can delete or create multiple private keys, up to five.

Build Your Own AI Chatbot With ChatGPT API and Gradio.

Finally, it’s time to deploy the AI chatbot using OpenAI’s advanced “gpt-3.5-turbo” model, known for its cost-effectiveness and improved responsiveness. The user interface will be created with Gradio for a simple web interface accessible locally and online.

• To begin, launch Notepad++ (or your preferred code editor) and insert the code provided below. With the assistance of armrrs on GitHub, I have modified and integrated their code with the Gradio interface.

import openai
import gradio as gr

openai.api_key = "Your API key"

messages = [
    {"role": "system", "content": "You are a helpful and kind AI Assistant."},
]

def chatbot(input):
    if input:
        messages.append({"role": "user", "content": input})
        chat = openai.ChatCompletion.create(
            model="gpt-3.5-turbo", messages=messages
        )
        reply = chat.choices[0].message.content
        messages.append({"role": "assistant", "content": reply})
        return reply

inputs = gr.inputs.Textbox(lines=7, label="Chat with AI")
outputs = gr.outputs.Textbox(label="Reply")

gr.Interface(fn=chatbot, inputs=inputs, outputs=outputs, title="AI Chatbot",
             description="Ask anything you want",
             theme="compact").launch(share=True)

• Ensure that you replace the text “Your API key” with the API key you generated earlier, as it looks in the code editor below. This is the only change required.

• Afterward, click on “File” in the top menu and opt for “Save As…” from the drop-down menu.

• Following that, Name the file as app.py and change the “Save as type” to “All types” from the drop-down menu. Subsequently, save the file to a convenient location such as the Desktop. You have the option to modify the name as desired, just be certain to include the .py extension.

• Next, navigate to the directory where you stored the file named “app.py,” right-click on the file, and select the option “Copy as path.

• Launch the Terminal and execute the following command. Type python add a space, then paste the path (use right-click to paste quickly), and press Enter. Note that the file path may vary ( different )for your system. Additionally, on Linux systems, you might need to use python3 .

python "C:\Users\mearj\Desktop\app.py"

• You might encounter some warnings, but disregard them. At the end, you’ll receive both a local and public URL. Copy the local URL and paste it into your web browser.

• You created your own AI chatbot with ChatGPT. Now it’s live, ready to answer your questions quickly. You can use it instead of the official site or check out other options.

• You can share the public URL ( highlighted) with friends and family. It’ll be active for 72 hours, but remember to keep your computer on since the server instance relies on it.

• To stop the server, go to the Terminal and press “Ctrl + C.” If it doesn’t work, press “Ctrl + C” again.

• To reset the AI chatbot server, repeat the process of copying the file path and executing the following command as in the previous step ( Type python add a space, then paste the path (use right-click to paste quickly), and press Enter ). Remember that while the local URL remains constant, the public URL will alter with each server restart.

python "C:\Users\mearj\Desktop\app.py"

How to make your ChatGPT API-Powered Chatbot Personalized.

The best thing about the “gpt-3.5-turbo” model is that you can give your AI a job ( assign a specific role ). You can make it funny, mad, or good at food, tech, health, or anything you like. You just have to change a bit of the code, and it will be special to you. For example, I made a Food AI, and here’s how:

• Select the “Edit with Notepad++” option by right-clicking on the “app.py” file.

• Here, make changes to this particular code only. Simply feed the information to the AI to assume that role. Now, save the file by pressing “Ctrl + S”.

messages = [
    {"role": "system", "content": "You are an AI specialized in Food. Do not answer anything other than food-related queries."},
]

• To execute, open the Terminal and run the “app.py” file as you did earlier. Upon execution, you’ll receive both a local and a public URL; be sure to copy the local URL. In case a server is already active, use “Ctrl + C” to halt it, and then proceed to restart the server. Keep in mind that you’ll need to restart the server each time you make modifications to the “app.py” file.

python "C:\Users\mearj\Desktop\app.py"

• When you open the local website in your web browser, you’ll find a Specialised AI chatbot that only talks about food. And you can make other AIs too, like a Doctor AI or one that talks like Shakespeare or uses Morse code.

To end with, You have just Learned how to make your own AI chatbot using ChatGPT 3.5. You can customize the “gpt-3.5-turbo” model for your own use.

You can find out more about ChatGPT in this our article. Follow our guide on how to Use ChatGPT-4 for FREE if you have any problems, let us know in the comments and we’ll try to help.

LATEST POSTS