refactor: split ai/ into hermes/ and ollama/ directories

- Rename ai/ to hermes/ (Hermes agent service) - Move ai/ollama/ to ollama/ (top-level, Ollama ROCm/gfx906 service) - Add ollama/compose.yml for standalone ollama deployment - Update hermes/compose.yml: remove ollama service (now in ollama/) - Update Makefile SERVICES list: ai -> hermes, add ollama - Bump ollama version from v0.13.5 to v0.23.2
2026-05-09 21:44:46 -04:00
8 changed files with 92 additions and 312 deletions
--- a/2
+++ b/2
@@ -2,7 +2,7 @@
 COMPOSE_PATH=~/Projects/AltNet/docker-compose

 # List of services (folder names)
-SERVICES=monitoring ai cloudstorage crm_tp crm_cf mediacenter homeautomation network backup homepage passwordmanager
+SERVICES=monitoring hermes ollama cloudstorage crm_tp crm_cf mediacenter homeautomation network backup homepage passwordmanager

 # Bring up all services
 all_up:
--- a/ai/compose.yml
+++ b/ai/compose.yml
@@ -1,303 +0,0 @@
-version: "3.8"
-services:
-
-  # webui:
-  #   image: ghcr.io/open-webui/open-webui:main
-  #   volumes:
-  #     - /mnt/HoardingCow_docker_data/Ollama/open-webui:/app/backend/data
-  #   restart: always
-  #   environment:
-  #     - OLLAMA_API_BASE_URL=http://ollama:11434/api
-  #   networks:
-  #     - ai_net
-  #     - ai_backend
-  #   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"
-
-  hermes:
-    build: ./
-    container_name: hermes
-    restart: always
-    # Gateway run enables the internal API server on port 8642
-    command: gateway run
-    environment:
-      - OLLAMA_HOST=http://ollama:11434
-      - API_SERVER_ENABLED=true
-      - API_SERVER_PORT=8642
-      - API_SERVER_HOST=0.0.0.0
-      - API_SERVER_KEY=hermes_local_key
-      - GATEWAY_ALLOW_ALL_USERS=true
-      - OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
-      # ROCm for GPU-accelerated faster-whisper STT
-      - 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
-      - TZ=America/Montreal
-    volumes:
-      - /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
-    devices:
-      - /dev/kfd:/dev/kfd
-      - /dev/dri:/dev/dri
-    group_add:
-      - "303"
-      - "26"
-    networks:
-      - ai_backend
-
-  ollama:
-    build:
-      context: ./ollama
-      dockerfile: Dockerfile
-    image: ollama/ollama:rocm-gfx906
-    container_name: ollama
-    privileged: true
-    tty: true
-    restart: always 
-    ports:
-      - "127.0.0.1:11434:11434"
-    networks:
-      - ai_backend
-    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"
-
-networks:
-  ai_net:
-    external: true
-    name: ai_net
-  ai_backend:
-    driver: bridge
-    name: ai_backend
-    
-  # llama_cpp_devstral:
-  #   image: ghcr.io/ggml-org/llama.cpp:server-rocm
-  #   container_name: llama_cpp_devstral
-  #   restart: unless-stopped
-  #   networks:
-  #     - ai_backend
-  #   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:
-  #     - ai_backend
-  #   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: ${HF_TOKEN}
-  #   command: >
-  #     vllm serve "mistralai/Devstral-Small-2-24B-Instruct-2512" 
-  #     --tensor-parallel-size 2
-  #     --max-model-len 8192
-  #     --gpu-memory-utilization 0.90
-  #     --tokenizer_mode mistral
-  #     --config_format auto
-  #     --load-format auto
-  #     --enforce-eager
-  #     --disable-custom-all-reduce
-  #     --trust-remote-code
-  #     --task generate
-  #     --block-size 16
-  #   volumes:
-  #     - /mnt/HoardingCow_docker_data/vllm/models:/root/.cache/huggingface
-  #   restart: unless-stopped
-
-  # n8n:
-  #   image: n8nio/n8n:latest
-  #   container_name: n8n
-  #   restart: unless-stopped
-  #   networks:
-  #     - ai_net
-  #   environment:
-  #     - N8N_HOST=n8n.lazyworkhorse.net
-  #     - N8N_PORT=5678
-  #     - N8N_PROTOCOL=https
-  #     - NODE_ENV=production
-  #     - N8N_ENCRYPTION_KEY=${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"
-
-  # openclaw:
-  #   image: coollabsio/openclaw:latest
-  #   container_name: openclaw
-  #   restart: unless-stopped
-  #   expose:
-  #     - "8080"  # WebUI
-  #     - "18789" # Gateway/WebSocket
-  #     - "8788"  # Nextcloud Webhook
-  #   networks:
-  #     - ai_net
-  #     - ai_backend
-  #   volumes:
-  #     - /mnt/HoardingCow_docker_data/openclaw/data:/data
-  #     - /home/gortium/infra:/data/workspace/infra
-  #   environment:
-  #     - TZ=America/Toronto
-  #     - OPENCLAW_GATEWAY_TOKEN=${OPENCLAW_GATEWAY_TOKEN}
-  #     - OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
-  #     # Point to the sidecar browser
-  #     - BROWSER_CDP_URL=http://openclaw-browser:9222
-  #     - BROWSER_EVALUATE_ENABLED=true
-  #     - OPENCLAW_GATEWAY_HOST=0.0.0.0
-  #     - OPENCLAW_ALLOWED_ORIGINS=https://claw.lazyworkhorse.net
-  #   labels:
-  #     - "traefik.enable=true"
-
-  #     - "traefik.http.routers.openclaw-http.rule=Host(`claw.lazyworkhorse.net`)"
-  #     - "traefik.http.routers.openclaw-http.entrypoints=web"
-  #     - "traefik.http.routers.openclaw-http.middlewares=redirect-to-https"
-
-  #     - "traefik.http.routers.openclaw-https.rule=Host(`claw.lazyworkhorse.net`)"
-  #     - "traefik.http.routers.openclaw-https.priority=50"
-  #     - "traefik.http.routers.openclaw-https.entrypoints=websecure"
-  #     - "traefik.http.routers.openclaw-https.tls=true"
-  #     - "traefik.http.routers.openclaw-https.tls.certresolver=njalla"
-  #     - "traefik.http.services.openclaw.loadbalancer.server.port=8080"
-  #   depends_on:
-  #     - openclaw-browser
-
-  # openclaw-browser:
-  #   image: ghcr.io/browserless/chromium:latest
-  #   restart: always
-  #   expose:
-  #     - "3000"
-  #   environment:
-  #     - MAX_CONCURRENT_SESSIONS=10
-  #     - CONNECTION_TIMEOUT=300000
-  #     - PREBOOT_CHROME=true
-  #     - DEMO_MODE=false
-  #   networks:
-  #     ai_backend:
-  #       aliases:
-  #         - browser
-
-  # openclaw-ssh:
-  #   image: linuxserver/openssh-server:latest
-  #   container_name: openclaw-ssh
-  #   environment:
-  #     - PUID=1000
-  #     - PGID=1000
-  #     - PUBLIC_KEY_FILE=/config/ssh/authorized_keys
-  #     - SUDO_ACCESS=false
-  #     - PASSWORD_ACCESS=false
-  #   volumes:
-  #     - /mnt/HoardingCow_docker_data/openclaw/ssh-config:/config
-  #     - /home/gortium/infra:/data/workspace/infra:ro
-  #   restart: unless-stopped
-  #   networks:
-  #     - ai_backend
-  #   labels:
-  #     - "traefik.enable=true"
-  #     - "traefik.tcp.routers.openclaw-ssh.rule=HostSNI(*)"
-  #     - "traefik.tcp.routers.openclaw-ssh.entrypoints=sshnode"
-  #     - "traefik.tcp.routers.openclaw-ssh.tls.passthrough=false"
-  #     - "traefik.tcp.services.openclaw-ssh.loadbalancer.server.port=2222"
--- a/hermes/Dockerfile
+++ b/hermes/Dockerfile
--- a/hermes/compose.yml
+++ b/hermes/compose.yml
@@ -0,0 +1,38 @@
+version: "3.8"
+services:
+
+  hermes:
+    build: ./
+    container_name: hermes
+    restart: always
+    # Gateway run enables the internal API server on port 8642
+    command: gateway run
+    environment:
+      - OLLAMA_HOST=http://ollama:11434
+      - API_SERVER_ENABLED=true
+      - API_SERVER_PORT=8642
+      - API_SERVER_HOST=0.0.0.0
+      - API_SERVER_KEY=hermes_local_key
+      - GATEWAY_ALLOW_ALL_USERS=true
+      - OPENROUTER_API_KEY=${OPEN...KEY}
+      # ROCm for GPU-accelerated faster-whisper STT
+      - 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
+    volumes:
+      - /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    group_add:
+      - "303"
+      - "26"
+    networks:
+      - ai_backend
+
+networks:
+  ai_backend:
+    external: true
+    name: ai_backend
--- a/hermes/fix-permissions.sh
+++ b/hermes/fix-permissions.sh
--- a/hermes/patch_tts_tool.py
+++ b/hermes/patch_tts_tool.py
--- a/ai/ollama/Dockerfile
+++ b/ai/ollama/Dockerfile
@@ -1,18 +1,19 @@
-# ollama-gfx906/Dockerfile
+# ollama/Dockerfile
 #
-# Custom ollama image with ROCm 6.1 + gfx906 (MI50) support.
-# The default ollama/rocm image ships ROCm 7.2 which dropped gfx906 support.
-# This builds ollama from source targeting AMDGPU_TARGETS=gfx906.
+# Custom ollama image with ROCm + gfx906 (MI50) support.
+# The default ollama/rocm image ships ROCm 7.2 which drops gfx906 support.
+# This builds ollama and its llama.cpp runner from source, targeting gfx906.
 #
-# Build: docker build -t ollama/ollama:rocm-gfx906 .
+# Build:
+#   docker build -t ollama/ollama:rocm-gfx906 ./ollama

 FROM rocm/dev-ubuntu-22.04:6.1.2-complete AS builder

 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
-    git golang cmake build-essential pkg-config \
+    git golang-go cmake build-essential pkg-config \
    && rm -rf /var/lib/apt/lists/*

-ARG OLLAMA_VERSION=v0.13.5
+ARG OLLAMA_VERSION=v0.23.2
 RUN git clone --depth 1 --branch ${OLLAMA_VERSION} https://github.com/ollama/ollama.git /build
 WORKDIR /build

@@ -20,7 +21,7 @@ ENV HIP_PATH=/opt/rocm
 ENV ROCM_PATH=/opt/rocm
 ENV PATH=/opt/rocm/bin:/opt/rocm/hip/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
 RUN cd llama.cpp && \
-    mkdir build && cd build && \
+    mkdir -p build && cd build && \
    cmake .. \
      -DLLAMA_HIPBLAS=ON \
      -DCMAKE_C_COMPILER=clang \
@@ -52,6 +53,9 @@ RUN ldconfig

 ENV LD_LIBRARY_PATH=/opt/rocm/lib:/usr/lib/ollama
 ENV HSA_OVERRIDE_GFX_VERSION=9.0.6
+ENV HCC_AMDGPU_TARGET=gfx906
+ENV HSA_ENABLE_SDMA=0

 EXPOSE 11434
+ENTRYPOINT ["/bin/ollama"]
 CMD ["serve"]
--- a/ollama/compose.yml
+++ b/ollama/compose.yml
@@ -0,0 +1,41 @@
+version: "3.8"
+
+services:
+  ollama:
+    build:
+      context: ./
+      dockerfile: Dockerfile
+    image: ollama/ollama:rocm-gfx906
+    container_name: ollama
+    privileged: true
+    tty: true
+    restart: always
+    ports:
+      - "127.0.0.1:11434:11434"
+    networks:
+      - ai_backend
+    volumes:
+      - /mnt/HoardingCow_docker_data/Ollama/ollama:/root/.ollama
+    environment:
+      - OLLAMA_VULKAN=0
+      - OLLAMA_HOST=0.0.0.0
+      - OLLAMA_DEBUG=1
+      - OLLAMA_FLASH_ATTENTION=0
+      - OLLAMA_NUM_PARALLEL=2
+      # ROCm / gfx906 configuration
+      - 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
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    group_add:
+      - "303"
+      - "26"
+
+networks:
+  ai_backend:
+    external: true
+    name: ai_backend