Light-GPT is a lightweight, pure front-end web application that provides an interactive chat interface powered by OpenAI's GPT-3.5-Turbo model. It is designed for users who want a private, client-side solution for interacting with AI, offering features like streaming responses, code highlighting, and data export.

How It Works

This project leverages Next.js for its front-end architecture and makes direct API calls to OpenAI using a user-provided API key. Responses are streamed to the client and displayed with a typewriter effect. All chat history and user preferences are stored locally in the browser's IndexedDB, ensuring no data leaves the user's machine.

Quick Start & Requirements

• Local Deployment: git clone https://github.com/riwigefi/light-gpt.git, cd light-gpt, pnpm install, pnpm run dev. Requires Node.js 16.14.2 or higher.
• Docker Deployment: docker pull whynotisme/light-gpt:latest, docker run -p 3000:3000 whynotisme/light-gpt.
• Prerequisites: OpenAI API Key, stable internet connection for API calls.
• Demo: https://light-gpt.vercel.app

Highlighted Details

• Pure front-end architecture with client-side API key storage for enhanced privacy.
• Supports streaming responses, typewriter effect, code syntax highlighting, and one-click code copying.
• Local storage of dialogue history via IndexedDB.
• Features include image generation, dialogue export (PDF, image), and customizable avatars.

Maintenance & Community

The project is hosted on GitHub. No specific community channels or active maintenance signals are detailed in the README.

Licensing & Compatibility

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

Limitations & Caveats

The application's functionality is entirely dependent on the user's ability to access OpenAI's API, requiring a stable and compliant internet connection. OpenAI's risk control policies may affect usability if the connection is not properly configured.