Working LLM chatbot

.github/workflows/dotnet.yml

@@ -7,13 +7,10 @@ on:
 jobs:
   build:
 
-    runs-on: ubuntu-latest
+    runs-on: windows-latest
 
     steps:
-    - name: Checkout
+    - uses: actions/checkout@v2
-      uses: actions/checkout@v2
-      with:
-        fetch-depth: 0 # required for github-action-get-previous-tag
 
     - name: Setup .NET
       uses: actions/setup-dotnet@v1
@@ -30,19 +27,15 @@ jobs:
       run: dotnet publish ./Bot/Lunaris2.csproj --configuration Release --output ./out
 
     - name: Zip the build
-      run: 7z a -tzip ./out/Lunaris.zip ./out/*
+      run: 7z a -tzip ./out/Bot.zip ./out/*
 
-    - name: Get previous tag
+    - name: Get the tag name
-      id: previoustag
+      id: get_tag
-      uses: 'WyriHaximus/github-action-get-previous-tag@v1'
+      run: echo "::set-output name=tag::${GITHUB_REF#refs/tags/}"
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
-    - name: Get next minor version
+    - name: Get the version
-      id: semver
+      id: get_version
-      uses: 'WyriHaximus/github-action-next-semvers@v1'
+      run: echo "::set-output name=version::$(date +%s).${{ github.run_id }}"
-      with:
-        version: ${{ steps.previoustag.outputs.tag }}
 
     - name: Create Release
       id: create_release
@@ -50,8 +43,8 @@ jobs:
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # This token is provided by Actions, you do not need to create your own token
       with:
-        tag_name: ${{ steps.semver.outputs.patch }}
+        tag_name: ${{ steps.get_version.outputs.version }}
-        release_name: Release ${{ steps.semver.outputs.patch }}
+        release_name: Release v${{ steps.get_version.outputs.version }}
         draft: false
         prerelease: false
 
@@ -62,6 +55,6 @@ jobs:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       with:
         upload_url: ${{ steps.create_release.outputs.upload_url }}
-        asset_path: ./out/Lunaris.zip
+        asset_path: ./out/Bot.zip
-        asset_name: Lunaris.zip
+        asset_name: Bot.zip
         asset_content_type: application/zip

Bot/Handler/ChatCommand/readme.md

@@ -1,8 +0,0 @@
-## Ollama - Large Language Model Chat - Handler
-
-This handler "owns" the logic for accessing the ollama api, which runs the transformer model.
-
-> How to get started with a local chat bot see: [Run LLMs Locally using Ollama](https://marccodess.medium.com/run-llms-locally-using-ollama-8f04dd9b14f9)
-
-Assuming you are on the same network as the Ollama server you should configure it to be accessible to other machines on the network, however this is only required if you aren't running it from localhost relative to the bot.
-See: [How do I configure Ollama server?](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-configure-ollama-server)

Bot/README.md

@@ -2,14 +2,9 @@
 ```mermaid
 flowchart TD
     Program[Program] -->|Register| EventListener
-    EventListener[DiscordEventListener] --> A[MessageReceivedHandler]
+    EventListener[DiscordEventListener] --> A
 
-    EventListener[DiscordEventListener] --> A2[SlashCommandReceivedHandler]
+    A[MessageReceivedHandler] -->|Message| C{Send to correct command by 
-
-    A --> |Message| f{If bot is mentioned}
-    f --> |ChatCommand| v[ChatHandler]
-
-    A2[SlashCommandReceivedHandler] -->|Message| C{Send to correct command by 
             looking at commandName}
 
     C -->|JoinCommand| D[JoinHandler]
@@ -17,33 +12,9 @@ flowchart TD
     C -->|HelloCommand| F[HelloHandler]
     C -->|GoodbyeCommand| G[GoodbyeHandler]
 ```
+
 Program registers an event listener ```DiscordEventListener``` which publish a message :
 
 ```c#
 await Mediator.Publish(new MessageReceivedNotification(arg), _cancellationToken);
 ```
-
-|Name| Description |
-|--|--|
-| SlashCommandReceivedHandler | Handles commands using ``/`` from any Discord Guild/Server. |
-| MessageReceivedHandler| Listens to **all** messages. |
-
-## Handler integrations
-```mermaid
-flowchart TD
-    D[JoinHandler] --> Disc[Discord Api]
-    E[PlayHandler] --> Disc[Discord Api]
-    F[HelloHandler] --> Disc[Discord Api]
-    G[GoodbyeHandler] --> Disc[Discord Api]
-    v[ChatHandler] --> Disc[Discord Api]
-    v --> o[Ollama Server]
-    o --> v
-    E --> Lava[Lavalink]
-```
-|Name| Description |
-|--|--|
-| JoinHandler| Handles the logic for **just** joining a voice channel. |
-| PlayHandler| Handles the logic for joining and playing music in a voice channel. |
-| HelloHandler| Responds with Hello. (Dummy handler, will be removed)|
-| GoodbyeHandler| Responds with Goodbye. (Dummy handler, will be removed)|
-| ChatHandler| Handles the logic for LLM chat with user. |

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

@@ -25,3 +25,7 @@ Lunaris2 is a Discord bot designed to play music in your server's voice channels
 ## Contributing
 
 Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
+
+## License
+
+[MIT](https://choosealicense.com/licenses/mit/)

docker-compose.yml

@@ -24,40 +24,6 @@ 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: