Add LLM info into main Readme

Invalid json

.github/workflows/dotnet.yml

@@ -30,7 +30,7 @@ jobs:
       run: dotnet publish ./Bot/Lunaris2.csproj --configuration Release --output ./out
 
     - name: Zip the build
-      run: 7z a -tzip ./out/Bot.zip ./out/*
+      run: 7z a -tzip ./out/Lunaris.zip ./out/*
 
     - name: Get previous tag
       id: previoustag
@@ -62,6 +62,6 @@ jobs:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       with:
         upload_url: ${{ steps.create_release.outputs.upload_url }}
-        asset_path: ./out/Bot.zip
+        asset_path: ./out/Lunaris.zip
-        asset_name: Bot.zip
+        asset_name: Lunaris.zip
         asset_content_type: application/zip

Bot/appsettings.json

@@ -9,7 +9,7 @@
     "Token": "discordToken",
     "LavaLinkPassword": "youshallnotpass",
     "LavaLinkHostname": "127.0.0.1",
-    "LavaLinkPort": 2333
+    "LavaLinkPort": 2333,
     "LLM": {
         "Url": "http://192.168.50.54:11434",
         "Model": "gemma"

README.md

@@ -7,6 +7,7 @@ Lunaris2 is a Discord bot designed to play music in your server's voice channels
 - Play music from YouTube directly in your Discord server.
 - Skip tracks, pause, and resume playback.
 - Queue system to line up your favorite tracks.
+- Local LLM (AI chatbot) that answers on @mentions in Discord chat. See more about it below.
 
 ## Setup
 
@@ -17,6 +18,11 @@ Lunaris2 is a Discord bot designed to play music in your server's voice channels
 5. Make sure you got docker installed. And run the file ``start-services.sh``, make sure you got git-bash installed.
 6. Now you can start the project and run the application.
 
+## LLM
+Lunaris supports AI chat using a large language model, this is done by hosting the LLM locally, in this case Docker will set it up for you when you run the start-services script.
+
+The LLM is run using Ollama see more about Ollama [here](https://ollama.com/). Running LLM locally requires much resources from your system, minimum requirements is at least 8GB of ram. If your don't have enought ram, select a LLM model in the [appsettings file](https://github.com/Myxelium/Lunaris2.0/blob/master/Bot/appsettings.json#L15) that requires less of your system.
+
 ## Usage
 
 - `/play <song>`: Plays the specified song in the voice channel you're currently in.

docker-compose.yml

@@ -24,6 +24,40 @@ services:
     ports:
       # you only need this if you want to make your lavalink accessible from outside of containers
       - "2333:2333"
+      
+  ollama:
+    volumes:
+      - ollama:/root/.ollama
+    # comment below to not expose Ollama API outside the container stack
+    ports:
+      - 11434:11434
+    container_name: ollama
+    pull_policy: always
+    tty: true
+    restart: unless-stopped
+    image: ollama/ollama:latest
+
+  ollama-webui:
+    build:
+      context: .
+      args:
+        OLLAMA_API_BASE_URL: '/ollama/api'
+      dockerfile: Dockerfile
+    image: ollama-webui:latest
+    container_name: ollama-webui
+    depends_on:
+      - ollama
+    ports:
+      - 3000:8080
+    environment:
+      - "OLLAMA_API_BASE_URL=http://ollama:11434/api"
+    extra_hosts:
+      - host.docker.internal:host-gateway
+    restart: unless-stopped
+
+volumes:
+  ollama: {}
+
 networks:
   # create a lavalink network you can add other containers to, to give them access to Lavalink
   lavalink: