Abstract

PigPig: Advanced Multi-modal LLM Discord Bot

English | 繁體中文

PigPig is a powerful Discord bot based on multi-modal Large Language Models (LLM), designed to interact with users through natural language. It combines advanced AI capabilities with practical features, offering a rich experience for Discord communities.

Invite PigPig to your server

🌟 Key Features

• 🧠 AI-Powered Conversations: Utilizes LLMs and LangChain for natural language understanding and generation.
• 🖼️ Multi-modal Capabilities: Visual question answering and image generation.
• 🍽️ Practical Features: Set reminders, get recommendations, and perform calculations.
• 👤 User Information Management: Create and maintain user profiles.
• 📊 Channel Data RAG: Use channel history for context-aware responses.
• 💭 Chain of Thought Reasoning: Employs Chain of Thought reasoning to provide detailed, step-by-step explanations of its thought process, enhancing transparency and understanding. This feature allows the bot to break down complex problems into smaller, manageable steps, providing a more comprehensive and insightful response.

🖥️ System Requirements

• Python 3.10+
• Lavalink Server (4.0.0+)
• Modules in requirements
• NVIDIA GPU with at least 12GB VRAM (required for optimal AI performance)

📸 Feature Showcase

Discord Bot

🚀 Quick Start

git clone https://github.com/starpig1129/discord-LLM-bot-PigPig.git  #Clone the repository
cd PigPig-discord-LLM-bot                                        #Go to the directory
python -m pip install -r requirements.txt          #Install required packages

After installing all packages, you must configure the bot before to start! How To Configure

Start your bot with python main.py

⚙️ Configuration

1. Rename .env Example to .env and fill all the values

TOKEN = XXXXXXXXXXXXXXXXXXXXXXXX.XXXXXX.XXXXXXXXXXXXXXXXXXXXXXXXXXX
CLIENT_ID = 123456789012345678
CLIENT_SECRET_ID = XXXXXXXXXX-XXXXXXXXXXXXXXXXXXXXX
SERCET_KEY = DASHBOARD_SERCET_KEY

BUG_REPORT_CHANNEL_ID = 123456789012345678

LLM_MODEL_NAME = shenzhi-wang/Llama3-8B-Chinese-Chat
VQA_MODEL_NAME = openbmb/MiniCPM-Llama3-V-2_5-int4
ANTHROPIC_API_KEY = XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
OPENAI_API_KEY = XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
GEMINI_API_KEY = XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

1. Rename settings Example.json to settings.json and customize your settings
   (Note: Do not change any keys from settings.json)

{
    "prefix": "/",
    "activity": [
        {
            "paly": "\u5b78\u7fd2\u8aaa\u8a71"
        }
    ],
    "ipc_server": {
        "host": "127.0.0.1",
        "port": 8000,
        "enable": false
    },
    "version": "v1.2.0"
}

Cogs Overview

This bot utilizes a modular design with several cogs (modules) to handle different functionalities. Here's a brief overview:

• CoT_AI: Implements Chain of Thought reasoning for detailed, step-by-step responses.
• Channel Manager: Manages channel-specific settings and permissions.
• Image Generation: Generates images based on text prompts.
• Help: Provides a list of available commands.
• Internet Search: Performs various web searches (general, image, YouTube, URL content).
• Math: Performs mathematical calculations.
• Model Management: Loads and unloads language models.
• Reminder: Sets reminders for users.
• Schedule: Manages user schedules.
• User Data: Manages user-specific data.
• Eat: Provides food recommendations.

License

This project is licensed under the MIT License - see the LICENSE file for details.