This project provides a Discord bot that integrates with OpenAI's ChatGPT and other AI models for text generation and image creation. It targets Discord server administrators and users who want to leverage advanced AI capabilities within their communities. The bot offers features like persona switching, private/public replies, and image generation via multiple AI services.

How It Works

The bot utilizes Python and interacts with various AI APIs, including OpenAI for ChatGPT and potentially others for image generation (Bing, Gemini). Users configure API keys and bot tokens via a .env file. The core functionality involves processing Discord commands to send prompts to the respective AI services and relaying the responses back to the Discord channel. It supports different modes like private replies and a "replyall" mode that responds to all messages without explicit commands.

Quick Start & Requirements

• Install: pip3 install -r requirements.txt or via Docker (docker compose up -d).
• Prerequisites: Python 3.9+, Discord bot token with MESSAGE CONTENT INTENT enabled, OpenAI API key (optional), Microsoft Bing and Google Gemini cookies for image generation (optional). Google Chrome is recommended for image generation setup.
• Setup: Requires obtaining API keys and tokens, configuring the .env file, and inviting the bot to a Discord server.
• Docs: https://discord.com/developers/applications

Highlighted Details

• Supports GPT-4 for free (via API configuration).
• Image generation via Microsoft Bing and Google Gemini.
• Multiple ChatGPT personas including DAN and AIM.
• Modes for private replies and replying to all messages.
• Commands for switching models, personas, and resetting conversation history.

Maintenance & Community

No specific information on contributors, sponsorships, or community channels (like Discord/Slack) is provided in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The "replyall" mode is noted as potentially unstable and prone to triggering program failures. Certain personas may generate offensive content. GPT-4 API access is subject to OpenAI's restrictions.