compose/ai/compose.yml

services:

  webui:
    image: ghcr.io/open-webui/open-webui:main
    volumes:
      - /mnt/HoardingCow_docker_data/Ollama/open-webui:/app/backend/data
    environment:
      - OLLAMA_API_BASE_URL=http://ollama:11434/api
    networks:
      - traefik-net
    labels:
      - "traefik.enable=true"

      # Router for HTTP + redirection to HTTPS
      - "traefik.http.routers.webui-http.rule=Host(`ai.lazyworkhorse.net`)"
      - "traefik.http.routers.webui-http.entrypoints=web"
      - "traefik.http.routers.webui-http.middlewares=redirect-to-https"

      # Router for HTTPS with TLS
      - "traefik.http.routers.webui-https.rule=Host(`ai.lazyworkhorse.net`)"
      - "traefik.http.routers.webui-https.entrypoints=websecure"
      - "traefik.http.routers.webui-https.tls=true"
      - "traefik.http.routers.webui-https.tls.certresolver=njalla"

  # llama_cpp_devstral:
  #   image: ghcr.io/ggml-org/llama.cpp:server-rocm
  #   container_name: llama_cpp_devstral
  #   restart: unless-stopped
  #   ports:
  #     - "8300:8080"
  #   ipc: host
  #   devices:
  #     - "/dev/kfd:/dev/kfd"
  #     - "/dev/dri:/dev/dri"
  #   group_add:
  #     - "303" # video
  #     - "26"  # render
  #   environment:
  #     HSA_OVERRIDE_GFX_VERSION: 9.0.6
  #     HIP_VISIBLE_DEVICES: 0,1
  #     LLAMA_CACHE: /models
  #   volumes:
  #     - /mnt/HoardingCow_docker_data/Llama_cpp/models:/models
  #     - /mnt/HoardingCow_docker_data/Llama_cpp/devstral-agent.jinja:/template.jinja
  #   command: >
  #     -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Devstral-Small-2-24B-Instruct-2512-Q8_0.gguf
  #     -a devstral-2-small-llama_cpp
  #     --chat-template-file /template.jinja
  #     --host 0.0.0.0
  #     --port 8080
  #     --n-gpu-layers 99
  #     --ctx-size 163840
  #     --batch-size 4096
  #     --ubatch-size 4096
  #     --cache-type-k f16
  #     --cache-type-v f16
  #     --cache-reuse 256
  #     --flash-attn on
  #     --context-shift
  #     --split-mode layer
  #     --no-mmap
  #     --n-predict -1
  #     --parallel 2

  # vllm:
  #   image: nalanzeyu/vllm-gfx906:v0.9.0-rocm6.3
  #   container_name: vllm
  #   # Required for multi-GPU communication (NCCL)
  #   ipc: host 
  #   init: true
  #   shm_size: '2g' 
  #   networks:
  #     - traefik-net
  #   ports:
  #     - "8300:8000"
  #   devices:
  #     - "/dev/kfd:/dev/kfd"
  #     - "/dev/dri:/dev/dri"
  #   group_add:
  #     - "303"
  #     - "26"
  #   environment:
  #     HSA_OVERRIDE_GFX_VERSION: 9.0.6
  #     HSA_ENABLE_SDMA: 0
  #     HIP_VISIBLE_DEVICES: 0,1
  #     NCCL_P2P_DISABLE: 1
  #     VLLM_WORKER_MULTIPROC_METHOD: spawn
  #     VLLM_USE_TRITON_FLASH_ATTN: 0
  #     VLLM_USE_ROCM_CUSTOM_PAGED_ATTN: 0
  #     VLLM_ATTENTION_BACKEND: ROPE_NAIVE
  #     VLLM_SKIP_WARMUP: 1
  #     VLLM_USE_V1: 0
  #     HF_TOKEN: ${HF_TOKEN}
  #   command: >
  #     vllm serve "mistralai/Devstral-Small-2-24B-Instruct-2512" 
  #     --tensor-parallel-size 2
  #     --max-model-len 8192
  #     --gpu-memory-utilization 0.90
  #     --tokenizer_mode mistral
  #     --config_format auto
  #     --load-format auto
  #     --enforce-eager
  #     --disable-custom-all-reduce
  #     --trust-remote-code
  #     --task generate
  #     --block-size 16
  #   volumes:
  #     - /mnt/HoardingCow_docker_data/vllm/models:/root/.cache/huggingface
  #   restart: unless-stopped

  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    privileged: true
    tty: true
    restart: unless-stopped
    ports:
      - "127.0.0.1:11434:11434"
    networks:
      - traefik-net
    volumes:
      - /mnt/HoardingCow_docker_data/Ollama/ollama:/root/.ollama
    environment:
      - OLLAMA_VULKAN=0
      - HSA_OVERRIDE_GFX_VERSION=9.0.6
      - HCC_AMDGPU_TARGET=gfx906
      - HIP_VISIBLE_DEVICES=0,1
      - ROCR_VISIBLE_DEVICES=0,1
      - HSA_ENABLE_SDMA=0 
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_DEBUG=1
      - OLLAMA_FLASH_ATTENTION=0
      - OLLAMA_NUM_PARALLEL=2
    devices:
      # Map the render nodes and KFD for ROCm to work inside the container
      - /dev/kfd:/dev/kfd
      - /dev/dri:/dev/dri
    group_add:
      - "303"
      - "26"

  n8n:
    image: n8nio/n8n:latest
    container_name: n8n
    restart: unless-stopped
    networks:
      - traefik-net
    environment:
      - N8N_HOST=n8n.lazyworkhorse.net
      - N8N_PORT=5678
      - N8N_PROTOCOL=https
      - NODE_ENV=production
      - N8N_ENCRYPTION_KEY=${N8N_ENCRYPTION_KEY}
      - WEBHOOK_URL=https://n8n.lazyworkhorse.net/
      - GENERIC_TIMEZONE=America/New_York # Adjust to your timezone
      - N8N_BLOCK_EXTERNAL_STORAGE_ACCESS=false
      - N8N_NODES_PYTHON_CAN_IMPORT_MODULES=true 
      - N8N_NATIVE_PYTHON_RUNNER=true
      - N8N_PYTHON_ALLOW_STDLIB=uuid,re,os,json
      - N8N_PYTHON_ALLOW_EXTERNAL=requests,pandas
      - NODE_FUNCTION_ALLOW_EXTERNAL=uuid,requests
    volumes:
      - /mnt/HoardingCow_docker_data/n8n:/home/node/.n8n
    labels:
      - "traefik.enable=true"

      # Router for HTTP + redirection to HTTPS
      - "traefik.http.routers.n8n-http.rule=Host(`n8n.lazyworkhorse.net`)"
      - "traefik.http.routers.n8n-http.entrypoints=web"
      - "traefik.http.routers.n8n-http.middlewares=redirect-to-https"

      # Router for HTTPS with TLS
      - "traefik.http.routers.n8n-https.rule=Host(`n8n.lazyworkhorse.net`)"
      - "traefik.http.routers.n8n-https.entrypoints=websecure"
      - "traefik.http.routers.n8n-https.tls=true"
      - "traefik.http.routers.n8n-https.tls.certresolver=njalla"

      # Service Loadbalancer (n8n default port)
      - "traefik.http.services.n8n.loadbalancer.server.port=5678"

networks:
  traefik-net:
    external: true