This project provides a web-based interface for interacting with OpenAI's GPT-3.5 Turbo API, specifically tailored for language learning with a unique "national essence" (脏话) persona. It allows users to practice Chinese slang and profanity in a controlled, conversational manner, offering a novel approach to language immersion for advanced learners.

How It Works

The core functionality is driven by a pre-defined system prompt that instructs the GPT model to respond exclusively in Chinese profanity, while simultaneously concealing its role as a profanity-learning assistant. This creates a unique conversational dynamic for users aiming to master colloquial and potentially offensive language. The application is built using Node.js and leverages the OpenAI API.

Quick Start & Requirements

• Install: pnpm install
• Prerequisites: Node.js v18+, PNPM, OpenAI API Key.
• Setup: Copy .env.example to .env and add your OpenAI API key.
• Run: pnpm run dev (runs on http://localhost:3000/)
• Demo: https://chatgpt.ddiu.me (currently unavailable due to API key limits).

Highlighted Details

• Offers a unique, albeit controversial, language learning persona.
• Supports deployment via Vercel, Netlify, Docker, and Sealos.
• Environment variables allow customization of API keys, proxies, and site passwords.
• Includes troubleshooting tips for common connection and Node.js version issues.

Maintenance & Community

The project is maintained by vastxie and ddiu8081. Further discussions and feature requests can be found in the project's GitHub discussions.

Licensing & Compatibility

• License: MIT
• Compatibility: The MIT license permits commercial use and integration with closed-source projects.

Limitations & Caveats

The live demo is currently unavailable due to API key limitations. The core "profanity" persona may be offensive and is intended strictly for entertainment and specific language learning goals. Users should be aware of the potential for inappropriate content.