reflector/docker-compose.selfhosted.yml

# Self-hosted production Docker Compose — single file for everything.
#
# Usage: ./scripts/setup-selfhosted.sh <--gpu|--cpu|--hosted> [--ollama-gpu|--ollama-cpu] [--garage] [--caddy]
#   or:  docker compose -f docker-compose.selfhosted.yml [--profile gpu] [--profile ollama-gpu] [--profile garage] [--profile caddy] up -d
#
# ML processing modes (pick ONE — required):
#   --gpu                  NVIDIA GPU container for transcription/diarization/translation (profile: gpu)
#   --cpu                  In-process CPU processing on server/worker (no ML container needed)
#   --hosted               Remote GPU service URL (no ML container needed)
#
# Local LLM (optional — for summarization/topics):
#   --profile ollama-gpu   Local Ollama with NVIDIA GPU
#   --profile ollama-cpu   Local Ollama on CPU only
#
# Daily.co multitrack processing (auto-detected from server/.env):
#   --profile dailyco      Hatchet workflow engine + CPU/LLM workers
#
# Other optional services:
#   --profile garage       Local S3-compatible storage (Garage)
#   --profile caddy        Reverse proxy with auto-SSL
#
# Prerequisites:
#   1. Run ./scripts/setup-selfhosted.sh to generate env files and secrets
#   2. Or manually create server/.env and www/.env from the .selfhosted.example templates

services:
  # ===========================================================
  # Always-on core services (no profile required)
  # ===========================================================

  server:
    build:
      context: ./server
      dockerfile: Dockerfile
    image: monadicalsas/reflector-backend:latest
    restart: unless-stopped
    ports:
      - "127.0.0.1:1250:1250"
      - "40000-40100:40000-40100/udp"
    env_file:
      - ./server/.env
    environment:
      ENTRYPOINT: server
      # Docker-internal overrides (always correct inside compose network)
      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
      REDIS_HOST: redis
      CELERY_BROKER_URL: redis://redis:6379/1
      CELERY_RESULT_BACKEND: redis://redis:6379/1
      # ML backend config comes from env_file (server/.env), set per-mode by setup script
      # HF_TOKEN needed for in-process pyannote diarization (--cpu mode)
      HF_TOKEN: ${HF_TOKEN:-}
      # WebRTC: fixed UDP port range for ICE candidates (mapped above)
      WEBRTC_PORT_RANGE: "40000-40100"
      # Hatchet workflow engine (always-on for processing pipelines)
      HATCHET_CLIENT_SERVER_URL: ${HATCHET_CLIENT_SERVER_URL:-http://hatchet:8888}
      HATCHET_CLIENT_HOST_PORT: ${HATCHET_CLIENT_HOST_PORT:-hatchet:7077}
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_started
    volumes:
      - server_data:/app/data

  worker:
    build:
      context: ./server
      dockerfile: Dockerfile
    image: monadicalsas/reflector-backend:latest
    restart: unless-stopped
    env_file:
      - ./server/.env
    environment:
      ENTRYPOINT: worker
      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
      REDIS_HOST: redis
      CELERY_BROKER_URL: redis://redis:6379/1
      CELERY_RESULT_BACKEND: redis://redis:6379/1
      # ML backend config comes from env_file (server/.env), set per-mode by setup script
      HF_TOKEN: ${HF_TOKEN:-}
      # Hatchet workflow engine (always-on for processing pipelines)
      HATCHET_CLIENT_SERVER_URL: ${HATCHET_CLIENT_SERVER_URL:-http://hatchet:8888}
      HATCHET_CLIENT_HOST_PORT: ${HATCHET_CLIENT_HOST_PORT:-hatchet:7077}
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_started
    volumes:
      - server_data:/app/data

  beat:
    build:
      context: ./server
      dockerfile: Dockerfile
    image: monadicalsas/reflector-backend:latest
    restart: unless-stopped
    env_file:
      - ./server/.env
    environment:
      ENTRYPOINT: beat
      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
      REDIS_HOST: redis
      CELERY_BROKER_URL: redis://redis:6379/1
      CELERY_RESULT_BACKEND: redis://redis:6379/1
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_started

  web:
    build:
      context: ./www
      dockerfile: Dockerfile
    image: monadicalsas/reflector-frontend:latest
    restart: unless-stopped
    ports:
      - "127.0.0.1:3000:3000"
    env_file:
      - ./www/.env
    environment:
      NODE_ENV: production
      NODE_TLS_REJECT_UNAUTHORIZED: "0"
      SERVER_API_URL: http://server:1250
      KV_URL: redis://redis:6379
      KV_USE_TLS: "false"
      NEXTAUTH_URL_INTERNAL: http://localhost:3000
    depends_on:
      - redis

  redis:
    image: redis:7.2-alpine
    restart: unless-stopped
    ports:
      - "6379:6379"
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 30s
      timeout: 3s
      retries: 3
    volumes:
      - redis_data:/data

  postgres:
    image: postgres:17-alpine
    restart: unless-stopped
    command: ["postgres", "-c", "max_connections=200"]
    environment:
      POSTGRES_USER: reflector
      POSTGRES_PASSWORD: reflector
      POSTGRES_DB: reflector
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./server/docker/init-hatchet-db.sql:/docker-entrypoint-initdb.d/init-hatchet-db.sql:ro
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U reflector"]
      interval: 30s
      timeout: 3s
      retries: 3

  # ===========================================================
  # Specialized model containers (transcription, diarization, translation)
  # Only the gpu profile is activated by the setup script (--gpu mode).
  # The cpu service definition is kept for manual/standalone use but is
  # NOT activated by --cpu mode (which uses in-process local backends).
  # Both services get alias "transcription" so server config never changes.
  # ===========================================================

  gpu:
    build:
      context: ./gpu/self_hosted
      dockerfile: Dockerfile
    profiles: [gpu]
    restart: unless-stopped
    ports:
      - "127.0.0.1:8000:8000"
    environment:
      HF_TOKEN: ${HF_TOKEN:-}
    volumes:
      - gpu_cache:/root/.cache
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
      interval: 15s
      timeout: 5s
      retries: 10
      start_period: 120s
    networks:
      default:
        aliases:
          - transcription

  cpu:
    build:
      context: ./gpu/self_hosted
      dockerfile: Dockerfile.cpu
    profiles: [cpu]
    restart: unless-stopped
    ports:
      - "127.0.0.1:8000:8000"
    environment:
      HF_TOKEN: ${HF_TOKEN:-}
    volumes:
      - gpu_cache:/root/.cache
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
      interval: 15s
      timeout: 5s
      retries: 10
      start_period: 120s
    networks:
      default:
        aliases:
          - transcription

  # ===========================================================
  # Ollama — local LLM for summarization & topic detection
  # Only started with --ollama-gpu or --ollama-cpu modes.
  # ===========================================================

  ollama:
    image: ollama/ollama:latest
    profiles: [ollama-gpu]
    restart: unless-stopped
    ports:
      - "127.0.0.1:11435:11435"
    volumes:
      - ollama_data:/root/.ollama
    environment:
      OLLAMA_HOST: "0.0.0.0:11435"
      OLLAMA_KEEP_ALIVE: "24h"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11435/api/tags"]
      interval: 10s
      timeout: 5s
      retries: 5

  ollama-cpu:
    image: ollama/ollama:latest
    profiles: [ollama-cpu]
    restart: unless-stopped
    ports:
      - "127.0.0.1:11435:11435"
    volumes:
      - ollama_data:/root/.ollama
    environment:
      OLLAMA_HOST: "0.0.0.0:11435"
      OLLAMA_KEEP_ALIVE: "24h"         # keep model loaded to avoid reload delays
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11435/api/tags"]
      interval: 10s
      timeout: 5s
      retries: 5

  # ===========================================================
  # Garage — local S3-compatible object storage (optional)
  # ===========================================================

  garage:
    image: dxflrs/garage:v1.1.0
    profiles: [garage]
    restart: unless-stopped
    ports:
      - "3900:3900"   # S3 API
      - "3903:3903"   # Admin API
    volumes:
      - garage_data:/var/lib/garage/data
      - garage_meta:/var/lib/garage/meta
      - ./data/garage.toml:/etc/garage.toml:ro
    healthcheck:
      test: ["CMD", "/garage", "stats"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 5s

  # ===========================================================
  # Caddy — reverse proxy with automatic SSL (optional)
  # Maps 80:80 and 443:443 — only exposed ports in the stack.
  # ===========================================================

  caddy:
    image: caddy:2-alpine
    profiles: [caddy]
    restart: unless-stopped
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./Caddyfile:/etc/caddy/Caddyfile:ro
      - caddy_data:/data
      - caddy_config:/config
    depends_on:
      - web
      - server

  # ===========================================================
  # Hatchet workflow engine + workers
  # Required for all processing pipelines (file, live, Daily.co multitrack).
  # Always-on — every selfhosted deployment needs Hatchet.
  # ===========================================================

  hatchet:
    image: ghcr.io/hatchet-dev/hatchet/hatchet-lite:latest
    restart: on-failure
    depends_on:
      postgres:
        condition: service_healthy
    ports:
      - "127.0.0.1:8888:8888"
      - "127.0.0.1:7078:7077"
    env_file:
      - ./.env.hatchet
    environment:
      DATABASE_URL: "postgresql://reflector:reflector@postgres:5432/hatchet?sslmode=disable&connect_timeout=30"
      SERVER_AUTH_COOKIE_INSECURE: "t"
      SERVER_GRPC_BIND_ADDRESS: "0.0.0.0"
      SERVER_GRPC_INSECURE: "t"
      SERVER_GRPC_BROADCAST_ADDRESS: hatchet:7077
      SERVER_GRPC_PORT: "7077"
      SERVER_AUTH_SET_EMAIL_VERIFIED: "t"
      SERVER_INTERNAL_CLIENT_INTERNAL_GRPC_BROADCAST_ADDRESS: hatchet:7077
    volumes:
      - hatchet_config:/config
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8888/api/live"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s

  hatchet-worker-cpu:
    build:
      context: ./server
      dockerfile: Dockerfile
    image: monadicalsas/reflector-backend:latest
    profiles: [dailyco]
    restart: unless-stopped
    env_file:
      - ./server/.env
    environment:
      ENTRYPOINT: hatchet-worker-cpu
      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
      REDIS_HOST: redis
      CELERY_BROKER_URL: redis://redis:6379/1
      CELERY_RESULT_BACKEND: redis://redis:6379/1
      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
      HATCHET_CLIENT_HOST_PORT: hatchet:7077
    depends_on:
      hatchet:
        condition: service_healthy
    volumes:
      - server_data:/app/data

  hatchet-worker-llm:
    build:
      context: ./server
      dockerfile: Dockerfile
    image: monadicalsas/reflector-backend:latest
    restart: unless-stopped
    env_file:
      - ./server/.env
    environment:
      ENTRYPOINT: hatchet-worker-llm
      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
      REDIS_HOST: redis
      CELERY_BROKER_URL: redis://redis:6379/1
      CELERY_RESULT_BACKEND: redis://redis:6379/1
      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
      HATCHET_CLIENT_HOST_PORT: hatchet:7077
    depends_on:
      hatchet:
        condition: service_healthy
    volumes:
      - server_data:/app/data

volumes:
  postgres_data:
  redis_data:
  server_data:
  gpu_cache:
  garage_data:
  garage_meta:
  ollama_data:
  caddy_data:
  caddy_config:
  hatchet_config:

networks:
  default:
    attachable: true