AIChatDiscordBotWeb

AIChatDiscordBotWeb is a local AI-powered Discord bot running on ASP.NET Core. It integrates local LLMs (via Ollama), web search, and image generation into a seamless chat experience.

✨ Features

What can this local AI do in Discord?

• 💬 Chat: Natural conversation with context awareness.
• 📄 File Analysis: Upload PDF, TXT, or DOCX files, and the bot will read and answer questions based on them.
• 👁️ Vision: Upload images and ask the bot to describe or analyze them (requires a Vision model).
• 🌐 Web Search: The bot can search the internet for the latest news and real-time information (requires Serper web api key).
• 🎨 Image Generation: The bot can generate images locally using ComfyUI (requires installed ComfyUI).
• 🗣️ Speaking: The bot can speak in voice channels (requires installed second Discord bot).

---

🛠️ Tech Stack & Libraries

Built with C# ASP.NET Core Web App (MVC) on .NET 9.0.

Nuget Libraries used:

• DSharpPlus (4.5.1)
• DSharpPlus.Interactivity (4.5.1)
• DSharpPlus.SlashCommands (4.5.1)
• Microsoft.SemanticKernel (1.66.0)
• Microsoft.SemanticKernel.Connectors.Ollama (1.66.0-alpha)
• Microsoft.KernelMemory.Core (0.98.250508.3)
• Microsoft.KernelMemory.AI.Ollama (0.98.250508.3)
• DocumentFormat.OpenXml (3.3.0)
• PdfPig (0.1.11)

---

⚙️ Installation & Setup

1. Discord Developer Portal

1. Go to the Discord Developer Portal.
2. Create a new application and go to the Bot tab.
3. Privileged Gateway Intents: Scroll down and enable the intents shown below:
4. Installation: Ensure the bot has the following permissions enabled:
5. Copy your Bot Token. You will need this for the config.

2. Ollama Setup (The Brain)

1. Download and install Ollama.
2. Open your console/terminal and run:

   ollama serve
   

   This must be running in the background for the bot to work.
3. Note the port number (usually the last 5 digits in the error/status message) to put in your config.
4. Download a model (e.g., ollama pull PetrosStav/gemma3-tools:4b) via the command line.
5. Run the list command to get the exact name:

   ollama list
   

   
6. Copy the full model name into your config page.

---

3. Web Search (Optional)

To enable internet access for the bot:

1. Get a free or paid API key from Serper.dev.
2. Paste the API Key into the AIChatDiscordBotWeb Configuration.

---

4. ComfyUI - Image Generation (Optional)

To enable image generation:

1. Download ComfyUI.
2. Recommended Models (Text-to-Image):
   • NetaYume Lumina Text to Image (Search in ComfyUI templates).
   • Lumina Image 2.0 Repackaged.
3. Place models in: C:\Users\YourPCName\Documents\ComfyUI\models\checkpoints.
4. Important: Go to ComfyUI Settings and enable Dev Mode.
   
5. Add your ComfyUI image directory path in the AIChatDiscordBotWeb Configuration.

---

5. Speaking Discord Bot (Optional)

To enable voice capabilities (Voice-to-Text and Text-to-Speech), you must run the secondary Python bot alongside this one.

• Repository: RafiBG/AITalkingDiscordBot
• Role: Handles microphone input and generates voice audio using Whisper STT and Piper TTS.
• Setup: Follow the detailed instructions in the link above to install FFmpeg and Piper TTS.

---

🎮 Slash Commands

Command	Description
/ask [message] (file) (image)	Main command. Chat with AI. Optionally attach a file (PDF/TXT/DOCX) for context or an image for vision analysis.
/ask_multi	Ask three AI models the same question and the main one will summaries the answer.
/forgetme	Starts a fresh conversation loop only for you (clears short-term user memory).
/reset	Global Reset. Resets all chats and starts a new conversation for everyone.
/help	Shows the help menu with these commands.

---

📸 Gallery & Examples

Chat & Vision Capabilities

File Analysis & Web Search

Image Generation

Long term memory