auto-commit

docker-compose.yaml

@@ -3,6 +3,7 @@ services:
     image: ollama/ollama:latest
     container_name: ollama
     restart: unless-stopped
+    runtime: nvidia
     ports:
       - "11434:11434"
     volumes:
@@ -14,6 +15,7 @@ services:
       - OLLAMA_MAX_LOADED_MODELS=2
       - OLLAMA_KEEP_ALIVE=10m
       - OLLAMA_FLASH_ATTENTION=1
+      - OLLAMA_KV_CACHE_TYPE=q4_0
     deploy:
       resources:
         reservations:
@@ -27,6 +29,27 @@ services:
       timeout: 10s
       retries: 5
 
+  searxng:
+    image: searxng/searxng:latest
+    container_name: searxng
+    restart: unless-stopped
+    ports:
+      - "11436:8080"
+    volumes:
+      - ./searxng:/etc/searxng
+    environment:
+      - BASE_URL=http://localhost:11436/
+      - INSTANCE_NAME=searxng
+      - SEARXNG_BASE_URL=${SEARXNG_BASE_URL}
+      - SEARXNG_SECRET=${SEARXNG_SECRET}
+      - SEARXNG_LIMITER=false
+    healthcheck:
+      test: ["CMD-SHELL", "curl -fsS http://localhost:8080/healthz >/dev/null || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+
   open-webui:
     image: ghcr.io/open-webui/open-webui:main
     container_name: open-webui
@@ -37,5 +60,9 @@ services:
       - ./open-webui_data:/app/backend/data
     environment:
       - OLLAMA_BASE_URL=http://ollama:11434
+      - ENABLE_RAG_WEB_SEARCH=true
+      - RAG_WEB_SEARCH_ENGINE=searxng
+      - SEARXNG_QUERY_URL=http://searxng:8080/search?q=<query>
     depends_on:
       - ollama
+      - searxng