KohakuHub/docker-compose.example.yml

# docker-compose.yml - Example configuration for KohakuHub
# Copy this to docker-compose.yml and customize for your deployment

services:
  hub-ui:
    image: nginx:alpine
    container_name: hub-ui
    restart: always
    ports:
      - "28080:80" # Public web interface
    volumes:
      - ./src/kohaku-hub-ui/dist:/usr/share/nginx/html
      - ./src/kohaku-hub-admin/dist:/usr/share/nginx/html-admin
      - ./docker/nginx/default.conf:/etc/nginx/conf.d/default.conf
    depends_on:
      - hub-api

  hub-api:
    build: .
    container_name: hub-api
    restart: always
    ports:
      - "48888:48888" # Internal API port (optional, for debugging)
    depends_on:
      - postgres
      - lakefs
      - minio
    environment:
      ## ===== CRITICAL: Endpoint Configuration (MUST CHANGE) =====
      ## These determine how users access your KohakuHub instance
      - KOHAKU_HUB_BASE_URL=http://127.0.0.1:28080 # Change to your public URL (e.g., https://hub.example.com)
      - KOHAKU_HUB_S3_PUBLIC_ENDPOINT=http://127.0.0.1:29001 # Change to your S3 public URL

      ## ===== CRITICAL: Security Configuration (MUST CHANGE) =====
      - KOHAKU_HUB_SESSION_SECRET=change-this-to-random-string-in-production
      - KOHAKU_HUB_ADMIN_SECRET_TOKEN=change-this-to-random-admin-token-in-production
      - KOHAKU_HUB_DATABASE_KEY=change-this-to-random-encryption-key-in-production # For external tokens (generate with: openssl rand -hex 32)

      ## ===== Performance Configuration =====  
      - KOHAKU_HUB_WORKERS=4 # Number of worker processes (1-8, recommend: CPU cores)

      ## ===== Database Configuration =====
      - KOHAKU_HUB_DB_BACKEND=postgres
      - KOHAKU_HUB_DATABASE_URL=postgresql://hub:hubpass@postgres:5432/kohakuhub
      - KOHAKU_HUB_AUTO_MIGRATE=true # Auto-confirm database migrations (required for Docker)

      ## ===== S3 Storage Configuration =====
      - KOHAKU_HUB_S3_ENDPOINT=http://minio:9000
      - KOHAKU_HUB_S3_ACCESS_KEY=minioadmin
      - KOHAKU_HUB_S3_SECRET_KEY=minioadmin
      - KOHAKU_HUB_S3_BUCKET=hub-storage
      - KOHAKU_HUB_S3_REGION=us-east-1  # S3 region (us-east-1 for MinIO, auto for R2, or specific AWS region)
      # - KOHAKU_HUB_S3_SIGNATURE_VERSION=s3v4  # Uncomment for R2/AWS S3 (leave commented for MinIO default)

      ## ===== LakeFS Configuration =====
      - KOHAKU_HUB_LAKEFS_ENDPOINT=http://lakefs:28000
      - KOHAKU_HUB_LAKEFS_REPO_NAMESPACE=hf
      # LakeFS credentials auto-generated on first start

      ## ===== Application Configuration =====
      - KOHAKU_HUB_SITE_NAME=KohakuHub
      - KOHAKU_HUB_LFS_THRESHOLD_BYTES=1000000
      - KOHAKU_HUB_LFS_MULTIPART_THRESHOLD_BYTES=100_000_000 # 100MB - use multipart for files larger than this
      - KOHAKU_HUB_LFS_MULTIPART_CHUNK_SIZE_BYTES=50_000_000 # 50MB - size of each part (min 5MB except last)
      - KOHAKU_HUB_LFS_KEEP_VERSIONS=5
      - KOHAKU_HUB_LFS_AUTO_GC=true

      ## ===== Auth & SMTP Configuration =====
      - KOHAKU_HUB_REQUIRE_EMAIL_VERIFICATION=false
      - KOHAKU_HUB_INVITATION_ONLY=false # Set to true to require invitation for registration
      - KOHAKU_HUB_SESSION_EXPIRE_HOURS=168
      - KOHAKU_HUB_TOKEN_EXPIRE_DAYS=365
      - KOHAKU_HUB_ADMIN_ENABLED=true
      # SMTP (Optional - for email verification)
      - KOHAKU_HUB_SMTP_ENABLED=false
      - KOHAKU_HUB_SMTP_HOST=smtp.gmail.com
      - KOHAKU_HUB_SMTP_PORT=587
      - KOHAKU_HUB_SMTP_USERNAME=
      - KOHAKU_HUB_SMTP_PASSWORD=
      - KOHAKU_HUB_SMTP_FROM=noreply@kohakuhub.local
      - KOHAKU_HUB_SMTP_TLS=true

      ## ===== Storage Quota Configuration (Optional) =====
      - KOHAKU_HUB_DEFAULT_USER_PRIVATE_QUOTA_BYTES=10_000_000
      - KOHAKU_HUB_DEFAULT_USER_PUBLIC_QUOTA_BYTES=100_000_000
      - KOHAKU_HUB_DEFAULT_ORG_PRIVATE_QUOTA_BYTES=10_000_000
      - KOHAKU_HUB_DEFAULT_ORG_PUBLIC_QUOTA_BYTES=100_000_000

      ## ===== Fallback Configuration (Optional) =====
      # - KOHAKU_HUB_FALLBACK_ENABLED=true
      # - KOHAKU_HUB_FALLBACK_REQUIRE_AUTH=false # Set true to require authentication for fallback access
      # - KOHAKU_HUB_FALLBACK_SOURCES=[{"url":"https://huggingface.co","name":"HuggingFace","source_type":"huggingface","priority":1}]
    volumes:
      - ./hub-meta/hub-api:/hub-api-creds

  minio:
    image: quay.io/minio/minio:latest
    container_name: minio
    command: server /data --console-address ":29000"
    environment:
      - MINIO_ROOT_USER=minioadmin
      - MINIO_ROOT_PASSWORD=minioadmin
    ports:
      - "29001:9000"    # S3 API
      - "29000:29000"   # Web Console
    volumes:
      - ./hub-storage/minio-data:/data
      - ./hub-meta/minio-data:/root/.minio

  lakefs:
    image: treeverse/lakefs:latest
    container_name: lakefs
    environment:
      - LAKEFS_DATABASE_TYPE=local
      - LAKEFS_DATABASE_LOCAL_PATH=/var/lakefs/data/metadata.db
      - LAKEFS_BLOCKSTORE_TYPE=s3
      - LAKEFS_BLOCKSTORE_S3_ENDPOINT=http://minio:9000
      - LAKEFS_BLOCKSTORE_S3_FORCE_PATH_STYLE=true
      - LAKEFS_BLOCKSTORE_S3_CREDENTIALS_ACCESS_KEY_ID=minioadmin
      - LAKEFS_BLOCKSTORE_S3_CREDENTIALS_SECRET_ACCESS_KEY=minioadmin
      - LAKEFS_BLOCKSTORE_S3_REGION=us-east-1  # S3 region (us-east-1 for MinIO, auto for R2, or specific AWS region)
      - LAKEFS_AUTH_ENCRYPT_SECRET_KEY=change-me-in-production
      - LAKEFS_LOGGING_FORMAT=text
      - LAKEFS_LISTEN_ADDRESS=0.0.0.0:28000
    ports:
      - "28000:28000"   # LakeFS admin UI (optional)
    user: "${UID}:${GID}"
    depends_on:
      - minio
    volumes:
      - ./hub-meta/lakefs-data:/var/lakefs/data
      - ./hub-meta/lakefs-cache:/lakefs/data/cache

  postgres:
    image: postgres:15
    container_name: postgres
    restart: always
    environment:
      - POSTGRES_USER=hub
      - POSTGRES_PASSWORD=hubpass
      - POSTGRES_DB=kohakuhub
    ports:
      - "25432:5432" # Optional: for external access
    volumes:
      - ./hub-meta/postgres-data:/var/lib/postgresql/data

networks:
  default:
    name: hub-net