@waylaidwanderer/chatgpt-api

ChatGPT API Server

This is a simple API server wrapper for ChatGPT. It supports multiple OpenAI accounts, setting proxies for each account, and load-balancing requests between accounts.

Getting Started

Prerequisites

• Node.js
• npm
• An account with ChatGPT
• A valid NopeCHA API key
• xvfb (for headless Chrome)

Installation

You can install the package using

npm i -g @waylaidwanderer/chatgpt-api

then run it using chatgpt-api (or xvfb-run chatgpt-api for headless servers).
This takes an optional --settings=<path_to_settings.js> parameter, or looks for settings.js in the current directory if not set, with the following contents:

module.exports = {
    accounts: [
        {
            email: '[e-mail]',
            password: 'password1',
        },
        {
            email: '[e-mail]',
            password: 'password2',
            proxy: 'user:pass@ip:port',
        },
        {
            email: '[e-mail]',
            password: 'password3',
            proxy: 'ip:port',
        },
        // add more accounts as needed...
    ],
    port: 3000, // the port the server will run on (optional, defaults to 3000)
    nopechaKey: 'nopechaKey', // your NopeCHA API key
};

Alternatively, you can install the package locally and run it using node index.js:

1. Clone this repository
2. Install dependencies with npm install
3. Rename settings.example.js to settings.js in the root directory and change the settings where required.
4. Start the server using xvfb-run node index.js (for headless servers) or node index.js

Usage

To start a conversation with ChatGPT, send a POST request to the server's /conversation endpoint with a JSON body in the following format:

{
    "message": "Hello, how are you today?",
    "conversationId": "your-conversation-id (optional)",
    "parentMessageId": "your-parent-message-id (optional)"
}

The server will return a JSON object containing ChatGPT's response:

{
    "response": "I'm doing well, thank you! How are you?",
    "conversationId": "your-conversation-id",
    "messageId": "your-message-id"
}

If the request is unsuccessful, the server will return a JSON object with an error message and a status code of 503.

If no sessions have finished initializing yet:

{
    "error": "No sessions available."
}

If there was an error sending the message to ChatGPT:

{
    "error": "There was an error communicating with ChatGPT."
}

Contributing

If you'd like to contribute to this project, please create a pull request with a detailed description of your changes.

Acknowledgments

This API server is powered by @transitive-bullshit's chatgpt-api (chatgpt on npm).

License

This project is licensed under the MIT License.