This project provides a web-based interface for interacting with OpenAI's GPT-3.5 API, offering features like multi-user support, conversation management, and formula display. It's designed for users who want a self-hosted or cloud-deployed ChatGPT experience with enhanced usability and data persistence.

How It Works

The application is built using Python with the Flask framework, leveraging the OpenAI API for language generation. It supports streaming responses for a dynamic, word-by-word display, similar to the official ChatGPT interface. Key features include conversation history management, code highlighting, and formula rendering, all accessible via a web browser.

Quick Start & Requirements

• Cloud Deployment (Recommended): Zeabur or Railway. Requires forking the repository and configuring environment variables (OPENAI_API_KEY, PORT, DEPLOY_ON_ZEABUR/DEPLOY_ON_RAILWAY, optional PASSWORD).
• Local Deployment:
  • Install dependencies: pip install -r requirements.txt
  • Configure config.yaml with OPENAI_API_KEY and optionally HTTPS_PROXY.
  • Run: python main.py
  • Access: 127.0.0.1:5000
• Prerequisites: Python 3.7+, OpenAI API key. A proxy may be required for users in regions with restricted access to OpenAI.

Highlighted Details

• Supports cloud deployment on Zeabur and Railway for easy access.
• Features multi-user support and conversation management.
• Renders mathematical formulas and highlights code snippets.
• Provides streaming responses for a dynamic chat experience.

Maintenance & Community

The project is actively developed, with recent updates including password protection, Zeabur deployment support, code highlighting, formula display, and streaming responses. Community links are not explicitly provided in the README.

Licensing & Compatibility

The repository does not explicitly state a license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

Local deployment may require a proxy due to potential IP restrictions. Cloud deployment on Railway has usage limits and requires GitHub account age verification. Some deployment methods (executable, Docker) are marked as "to be supplemented."