Chat-OIO Server

This is the backend server for the Chat-OIO application. It uses Express, Socket.IO, and the OpenAI API to provide a real-time chat service with an AI assistant.

Features

• Real-time communication with Socket.IO
• AI-powered chat using the OpenAI API
• Express server for handling HTTP requests
• CORS support for cross-origin requests

Getting Started

Prerequisites

• Node.js and npm installed on your machine
• An OpenAI API key

Installation

1. Clone the repository:

   git clone https://github.com/your-username/chat-express-oio-openai.git

2. Navigate to the chat-oio-server directory:

   cd chat-express-oio-openai/chat-oio-server

3. Install the dependencies:

   npm install

4. Create a .env file in the root of the chat-oio-server directory and add your OpenAI API key and the base URL for the AI:

   OPEN_AI_API_KEY=your-openai-api-key
   GITHUB_AI_BASE_URL=your-ai-base-url
   

Running the Server

To start the server, run the following command:

npm run server

The server will start on port 8000 by default.

Project Structure

chat-oio-server/
├── config/
│   └── openai.config.js  # OpenAI client configuration
├── socket/
│   ├── handlers.js       # Socket event handlers
│   └── socketServer.js   # Socket.IO server setup
├── .env                  # Environment variables
├── .gitignore            # Git ignore file
├── index.js              # Express server entry point
├── package.json          # Project dependencies and scripts
└── package-lock.json

Dependencies

• express: Web framework for Node.js
• socket.io: Real-time communication library
• openai: OpenAI API client
• cors: Middleware for enabling CORS
• dotenv: Module for loading environment variables
• nodemon: Utility for auto-restarting the server during development

How It Works

1. The Express server is initialized in index.js.
2. The Socket.IO server is registered in socket/socketServer.js and attached to the Express server.
3. When a client connects, the connection event is fired in socket/socketServer.js.
4. The server listens for user-message events from the client.
5. When a user-message is received, the messageHandler in socket/handlers.js is called.
6. The messageHandler sends the message to the OpenAI API to get an AI response.
7. The AI response is streamed back to the client via the ai-response event.
8. If there is an error, the ai-error event is emitted.