ollama/docker-compose.yaml

services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    runtime: nvidia
    ports:
      - "11434:11434"
    volumes:
      - ./ollama_data:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_ORIGINS=*
      - OLLAMA_NUM_PARALLEL=4
      - OLLAMA_MAX_LOADED_MODELS=2
      - OLLAMA_KEEP_ALIVE=10m
      - OLLAMA_FLASH_ATTENTION=1
      - OLLAMA_KV_CACHE_TYPE=q4_0
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "ollama", "list"]
      interval: 30s
      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
    restart: unless-stopped
    ports:
      - "11435:8080"
    volumes:
      - ./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