Added openwebui + ollama for selfhosted LLM chatbot

apps.yml

@@ -89,6 +89,7 @@ services:
 
   siyuan:
     image: b3log/siyuan
+    container_name: siyuan
     command: ['--workspace=/siyuan/workspace/']
     volumes:
       - /siyuan/workspace:/siyuan/workspace

config/prometheus/prometheus.yml

@@ -25,6 +25,6 @@ scrape_configs:
     static_configs:
       - targets: ['gitea:3000']
 
-  - job_name: 'affine'
+  - job_name: 'nvidia_gpu_exporter'
     static_configs:
-      - targets: ['affine:3010']
+      - targets: ['nvidia-gpu-exporter:9835']

docker-compose.yml

@@ -1,6 +1,7 @@
 include:
   - apps.yml
   - gitea.yml
+  - llm.yml
   - monitoring.yml
 
 services:

llm.yml

@@ -0,0 +1,28 @@
+services:
+  openwebui:
+    image: ghcr.io/open-webui/open-webui:main
+    container_name: openwebui
+    restart: unless-stopped
+    volumes:
+      - ./hdd0/openwebui:/app/backend/data
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.openwebui.rule=Host(`openwebui.bouvais.lu`)"
+      - "traefik.http.routers.openwebui.entrypoints=websecure"
+      - "traefik.http.routers.openwebui.tls.certresolver=myresolver"
+      - "traefik.http.services.openwebui.loadbalancer.server.port=8080"
+    environment:
+      OLLAMA_BASE_URLS: http://ollama:11434
+
+  ollama:
+    image: ollama/ollama:latest
+    container_name: ollama
+    volumes:
+      - ./hdd0/ollama:/root/.ollama
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              capabilities: ["gpu"]
+              count: all

monitoring.yml

@@ -78,4 +78,21 @@ services:
       - '--path.rootfs=/rootfs'
       - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)'
 
-
+  nvidia-gpu-exporter:
+    image: utkuozdemir/nvidia_gpu_exporter:1.3.1
+    container_name: nvidia-gpu-exporter
+    restart: unless-stopped
+    privileged: true # This might be needed for full access to devices, or try without first
+    devices:
+      - /dev/nvidia0:/dev/nvidia0
+    volumes:
+      - /usr/bin/nvidia-smi:/usr/bin/nvidia-smi:ro
+      - /usr/lib/x86_64-linux-gnu/libnvidia-ml.so:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so:ro
+      - /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:ro
+    command:
+      - --web.listen-address=:9835
+      - --web.telemetry-path=/metrics
+      - --nvidia-smi-command=nvidia-smi
+      - --log.level=info
+      - --query-field-names=AUTO
+      - --log.format=logfmt