From 015e546e7a9e92914515aab7ad6dc6e2169f6c55 Mon Sep 17 00:00:00 2001
From: adrien <adrien.bouvais.pro@gmail.com>
Date: Fri, 20 Jun 2025 18:29:27 +0000
Subject: [PATCH] Added openwebui + ollama for selfhosted LLM chatbot

---
 apps.yml                         |  1 +
 config/prometheus/prometheus.yml |  4 ++--
 docker-compose.yml               |  1 +
 llm.yml                          | 28 ++++++++++++++++++++++++++++
 monitoring.yml                   | 19 ++++++++++++++++++-
 5 files changed, 50 insertions(+), 3 deletions(-)
 create mode 100644 llm.yml

diff --git a/apps.yml b/apps.yml
index 50eda9d..0e7bffb 100644
--- a/apps.yml
+++ b/apps.yml
@@ -89,6 +89,7 @@ services:
 
   siyuan:
     image: b3log/siyuan
+    container_name: siyuan
     command: ['--workspace=/siyuan/workspace/']
     volumes:
       - /siyuan/workspace:/siyuan/workspace
diff --git a/config/prometheus/prometheus.yml b/config/prometheus/prometheus.yml
index d852f2c..bb14310 100644
--- a/config/prometheus/prometheus.yml
+++ b/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']
diff --git a/docker-compose.yml b/docker-compose.yml
index cbf2d48..39d2af4 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,6 +1,7 @@
 include:
   - apps.yml
   - gitea.yml
+  - llm.yml
   - monitoring.yml
 
 services:
diff --git a/llm.yml b/llm.yml
new file mode 100644
index 0000000..c39171a
--- /dev/null
+++ b/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
diff --git a/monitoring.yml b/monitoring.yml
index 4b45975..fc6da38 100644
--- a/monitoring.yml
+++ b/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