vision/docker-compose.yml

services:
  gateway:
    build:
      context: .
      dockerfile: gateway/Dockerfile
    ports:
      - "8003:8000"
    env_file:
      - .env
    environment:
      - CLIP_URL=http://clip:8000
      - BLIP_URL=http://blip:8000
      - YOLO_URL=http://yolo:8000
      - QDRANT_SVC_URL=http://qdrant-svc:8000
      - CARD_RENDERER_URL=http://card-renderer:8000
      - MATURITY_URL=http://maturity:8000
      - LLM_URL=${LLM_URL:-http://llm:8080}
      - LLM_ENABLED=${LLM_ENABLED:-false}
      - LLM_TIMEOUT=${LLM_TIMEOUT:-120}
      - LLM_DEFAULT_MODEL=${LLM_DEFAULT_MODEL:-qwen3-1.7b-instruct-q4_k_m}
      - LLM_MAX_TOKENS_DEFAULT=${LLM_MAX_TOKENS_DEFAULT:-256}
      - LLM_MAX_TOKENS_HARD_LIMIT=${LLM_MAX_TOKENS_HARD_LIMIT:-1024}
      - LLM_MAX_REQUEST_BYTES=${LLM_MAX_REQUEST_BYTES:-65536}
      - MATURITY_ENABLED=true
      - API_KEY=${API_KEY}
      - VISION_TIMEOUT=300
      - MAX_IMAGE_BYTES=52428800
    depends_on:
      clip:
        condition: service_healthy
      blip:
        condition: service_healthy
      yolo:
        condition: service_healthy
      qdrant-svc:
        condition: service_healthy
      card-renderer:
        condition: service_healthy
      maturity:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).read()"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s

  card-renderer:
    build:
      context: .
      dockerfile: card-renderer/Dockerfile
    environment:
      - CARD_DEFAULT_FONT=/app/assets/fonts/Inter-Regular.ttf
      - CARD_BOLD_FONT=/app/assets/fonts/Inter-Bold.ttf
      - CARD_LOGO_PATH=/app/assets/logo.png
      - CARD_MAX_IMAGE_BYTES=52428800
      - CARD_DEFAULT_OUTPUT=webp
      - CARD_DEFAULT_QUALITY=90
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).read()"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s

  qdrant:
    image: qdrant/qdrant:latest
    ports:
      - "6333:6333"
    volumes:
        - ./data/qdrant:/qdrant/storage
    environment:
      - QDRANT__SERVICE__GRPC_PORT=6334
    healthcheck:
      test: ["CMD-SHELL", "bash -c ':> /dev/tcp/127.0.0.1/6333' || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 15s

  qdrant-svc:
    build:
      context: .
      dockerfile: qdrant/Dockerfile
    environment:
      - QDRANT_HOST=qdrant
      - QDRANT_PORT=6333
      - CLIP_URL=http://clip:8000
      - COLLECTION_NAME=images
      - VECTOR_DIM=512
      - SEARCH_HNSW_EF=128
    depends_on:
      qdrant:
        condition: service_healthy
      clip:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).read()"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s

  clip:
    build:
      context: .
      dockerfile: clip/Dockerfile
    environment:
      - MODEL_NAME=ViT-B-32
      - MODEL_PRETRAINED=openai
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).read()"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s

  blip:
    build:
      context: .
      dockerfile: blip/Dockerfile
    environment:
      - BLIP_MODEL=Salesforce/blip-image-captioning-base
      #- BLIP_MODEL=Salesforce/blip-image-captioning-small
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).read()"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 90s

  yolo:
    build:
      context: .
      dockerfile: yolo/Dockerfile
    environment:
      - YOLO_MODEL=yolov8n.pt
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).read()"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s

  maturity:
    build:
      context: .
      dockerfile: maturity/Dockerfile
    environment:
      - MATURITY_MODEL=${MATURITY_MODEL:-Falconsai/nsfw_image_detection}
      - MATURITY_THRESHOLD_MATURE=${MATURITY_THRESHOLD_MATURE:-0.80}
      - MATURITY_THRESHOLD_REVIEW=${MATURITY_THRESHOLD_REVIEW:-0.60}
      - MAX_IMAGE_BYTES=52428800
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).read()"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 90s

  llm:
    build:
      context: .
      dockerfile: llm/Dockerfile
    environment:
      - MODEL_PATH=${MODEL_PATH:-/models/Qwen3-1.7B-Instruct-Q4_K_M.gguf}
      - LLM_MODEL_NAME=${LLM_DEFAULT_MODEL:-qwen3-1.7b-instruct-q4_k_m}
      - LLM_CONTEXT_SIZE=${LLM_CONTEXT_SIZE:-4096}
      - LLM_THREADS=${LLM_THREADS:-4}
      - LLM_GPU_LAYERS=${LLM_GPU_LAYERS:-0}
      - LLM_PORT=8080
      - LLM_EXTRA_ARGS=${LLM_EXTRA_ARGS:-}
    volumes:
      - ./models/qwen3:/models:ro
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 120s
    profiles:
      - llm