chatgpt chatbot python的进一步展开说明

Build Your Own Chatbot With ChatGPT API (2023)

In a recent breakthrough, OpenAI made a significant announcement about the release of the ChatGPT API to the public and developers. The introduction of the new “gpt⑶.5-turbo” model, which powers ChatGPT Plus, has made building chatbots much more affordable and responsive. OpenAI has paved the way for endless possibilities, enabling even non-coders to create their own AI chatbots using the ChatGPT API. In this article, we will provide a step-by-step tutorial on how to build your own AI chatbot using the ChatGPT API. We have also incorporated a Gradio interface for easy demonstration and sharing of the AI model with friends and family. So, let’s get started and learn how to create a personalized AI with the ChatGPT API.

Things to Remember Before You Build an AI Chatbot

1. You can build a ChatGPT chatbot on any platform, whether it’s Windows, macOS, Linux, or ChromeOS. The steps in this article are primarily focused on Windows 11, but they are nearly identical for other platforms.
2. This guide is designed for general users and provides clear instructions with examples. Even if you have limited computer knowledge, you can easily create your own AI chatbot.
3. You do not need a powerful computer with a high-performance CPU or GPU to create an AI chatbot. The heavy lifting is done by OpenAI’s API in the cloud.

Set Up the Software Environment to Create an AI Chatbot

Before you can create an AI chatbot powered by ChatGPT, you need to set up the software environment. This involves installing Python, Pip, OpenAI and Gradio libraries, as well as obtaining an OpenAI API key and a code editor like Notepad++. Although these tools may seem intimidating at first, the steps to install them are straightforward and can be followed by anyone. Let’s proceed with the following steps:

Install Python

1. Begin by downloading and installing Python on your computer. Go to this link and download the setup file for your respective platform.
2. Run the setup file and ensure that the “Add Python.exe to PATH” checkbox is selected. This step is crucial. Then, click on “Install Now” and follow the standard installation steps for Python.
3. To verify that Python has been properly installed, open the Terminal on your computer. In this example, we are using Windows Terminal on Windows. However, you can also use the Command Prompt. Once the Terminal is open, enter the following command to display the installed version of Python. On Linux or other platforms, you may need to use “python3 –version” instead of “python –version”.

python --version

Upgrade Pip

In addition to Python, Pip is also installed on your system. In this section, we will discuss how to upgrade Pip to the latest version. If you are unfamiliar, Pip is the package manager for Python, allowing you to install numerous Python libraries from the Terminal. With Pip, we can install the OpenAI and Gradio libraries. Here’s what you need to do:

1. Open the Terminal of your choice on your PC. In this example, we are using the Windows Terminal. Run the command below to update Pip. On Linux or other platforms, you may need to use “python3” and “pip3” instead of “python” and “pip”.

python -m pip install -U pip

Install OpenAI and Gradio Libraries

1. Now, let’s install the OpenAI library, which allows us to interact with ChatGPT through their API. In the Terminal, run the command below to install the OpenAI library using Pip. If the command does not work, try running it with “pip3”.

pip install openai

2. Once the installation is complete, let’s install Gradio. Gradio is a library that enables rapid development of user-friendly web interfaces for AI demos. It also provides an easy way to share the chatbot on the internet via a shareable link.

pip install gradio

Download a Code Editor

Finally, you will need a code editor to modify the code. For Windows, we recommend using Notepad++ (Download). Simply download and install the program using the provided link. If you prefer a more powerful integrated development environment (IDE), you can use Visual Studio Code (VS Code) on any platform. Sublime Text (Download) is another option available for macOS and Linux.

For ChromeOS users, the Caret app (Download) is an excellent code editor. With that, we have almost completed the software environment setup. Now, let’s proceed to obtain the OpenAI API key.

Get the OpenAI API Key For Free

To create a ChatGPT-powered AI chatbot, you need an API key from OpenAI. The API key allows you to call ChatGPT in your own interface and display the results seamlessly. Currently, OpenAI offers free API keys with $5 worth of free credit for the first three months. If you created your OpenAI account earlier, you may have free credit worth $18. After the free credit is used up, you will need to pay for API access. However, it is currently available for free to all users.

1. Go to platform.openai.com/signup and create a free account. If you already have an OpenAI account, simply log in.
2. After logging in, click on your profile in the top-right corner, and select “View API keys” from the drop-down menu.
3. On the API keys page, click on “Create new secret key” and copy the API key. Keep in mind that you will not be able to view or copy the full API key later on, so it is strongly recommended to immediately save it in a Notepad file.
4. Remember to keep the API key private and avoid sharing or displaying it publicly. This key is intended solely for accessing your own OpenAI account. You can also delete API keys and create multiple private keys, up to a maximum of five.

Create Your Personalized AI Chatbot With ChatGPT API and Gradio

Finally, it’s time to deploy the AI chatbot. For this purpose, we will be using OpenAI’s latest “gpt⑶.5-turbo” model, which powers GPT⑶.5. This model is more powerful than Davinci, has been trained up until September 2023, and offers improved cost-effectiveness, responsivity, and context-awareness. We will also utilize Gradio to create a simple web interface that can be accessed locally and shared online.

1. In your chosen code editor, such as Notepad++, paste the code provided below. We have repurposed the code from armrrs on GitHub and implemented 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="gpt⑶.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)

2. Make sure to replace the “Your API key” placeholder text with your actual OpenAI API key generated earlier. This is the only change you need to make in the code.
3. Click on “File” in the top menu of the code editor and choose “Save As…” from the drop-down menu.
4. Save the file with the name “app.py” and select “All types” from the “Save as type” drop-down menu. Save the file to a convenient location, such as the Desktop. You can change the name if desired, but ensure to add the “.py” extension.
5. Locate the saved file (app.py), right-click on it, and choose “Copy as path”.
6. Open the Terminal and run the command below. Type “python”, leave a space, paste the file path (right-click to paste quickly), and press Enter. Remember, the file path will differ on your computer. On Linux systems, you may need to use “python3”.

python "C:UsersmearjDesktoppp.py"

7. Ignore any warnings that may appear. At the bottom of the Terminal, you will see a local URL and a public URL. Copy the local URL and paste it into your web browser.
8. You have successfully built your own AI chatbot with the ChatGPT API. Your ChatGPT-powered AI chatbot is now live. You can ask any questions and receive instant answers. In addition to using ChatGPT alternatives, you can use your own chatbot instead of relying on the official website.
9. Copy the public URL and share it with your friends and family. The link will remain live for 72 hours; however, you must keep your computer running as the server instance runs on your computer.
10. To stop the server, go back to the Terminal and press “Ctrl + C”. If that doesn’t work, press “Ctrl + C” again.
11. To restart the AI chatbot server, simply copy the file path again and rerun the command from step 6. Remember, the local URL will remain the same, but the public URL will change each time the server restarts.

Create Your Personalized ChatGPT API-Powered Chatbot

The “gpt⑶.5-turbo” model allows you to assign a role or persona to your AI chatbot. You can customize it to be funny, angry, or a specialist in a particular field such as food, tech, or health. By making a minor modification in the code, you can personalize your AI chatbot based on your preferences. Here’s an example of creating a Food AI:

1. Right-click on the “app.py” file and choose “Edit with Notepad++”.
2. Locate the following code in the file and modify it according to your desired persona. This informs the AI about its specialized role. 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."},
]

3. Open the Terminal and run the “app.py” file as you did previously. You will receive a local and public URL. Copy the local URL. If a server is already running, press “Ctrl + C” to stop it. Then, restart the server. You will need to restart the server after every change made to the “app.py” file.

python "C:UsersmearjDesktoppp.py"

4. Open the local URL in your web browser, and you will have a personalized AI chatbot that only answers food-related queries. You can create a Doctor AI, an AI that speaks like Shakespeare, an AI that communicates in Morse code, or anything you can imagine!

Make Your Own AI Chatbot With ChatGPT 3.5 Model

This is how you can build your own AI chatbot using the ChatGPT 3.5 model. Additionally, you can customize the “gpt⑶.5-turbo” model with your preferred persona. The possibilities with AI are limitless, and you can create anything you desire. We have come to the end of this tutorial. If you want to learn how to use ChatGPT on Android and iOS, refer to our linked article. To discover more cool things you can do with ChatGPT, check out our curated article. If you encounter any issues, feel free to let us know in the comment section below. We will be happy to assist you.

chatgpt chatbot python的常见问答Q&A