# Nextcloud Instance
NEXTCLOUD_HOST=

# ===== AUTHENTICATION MODE =====
# Choose ONE of the following:

# Option 1: OAuth2/OIDC (RECOMMENDED - More Secure)
# - Requires Nextcloud OIDC app installed and configured
# - Admin must enable "Dynamic Client Registration" in OIDC app settings
# - Leave NEXTCLOUD_USERNAME and NEXTCLOUD_PASSWORD empty to use OAuth mode
# - Optional: Pre-register client and provide credentials (otherwise auto-registers)
NEXTCLOUD_OIDC_CLIENT_ID=
NEXTCLOUD_OIDC_CLIENT_SECRET=
NEXTCLOUD_OIDC_CLIENT_STORAGE=.nextcloud_oauth_client.json
NEXTCLOUD_MCP_SERVER_URL=http://localhost:8000

# Option 2: Basic Authentication (LEGACY - Less Secure)
# - Requires username and password
# - Credentials stored in environment variables
# - Use only for backward compatibility or if OAuth unavailable
# - If these are set, OAuth mode is disabled
NEXTCLOUD_USERNAME=
NEXTCLOUD_PASSWORD=

# ============================================
# Document Processing Configuration
# ============================================
# Enable document processing (PDF, DOCX, images, etc.)
# Set to false to disable all document processing
ENABLE_DOCUMENT_PROCESSING=false

# Default processor to use when multiple are available
# Options: unstructured, tesseract, custom
DOCUMENT_PROCESSOR=unstructured

# ============================================
# Unstructured.io Processor
# ============================================
# Enable Unstructured processor (requires unstructured service in docker-compose)
# This is a cloud-based/API processor supporting many document types
ENABLE_UNSTRUCTURED=false

# Unstructured API endpoint
UNSTRUCTURED_API_URL=http://unstructured:8000

# Request timeout in seconds (default: 120)
# OCR operations can take 30-120 seconds for large documents
UNSTRUCTURED_TIMEOUT=120

# Parsing strategy: auto, fast, hi_res
# - auto: Automatically choose based on document type
# - fast: Fast parsing without OCR
# - hi_res: High-resolution with OCR (slowest, most accurate)
UNSTRUCTURED_STRATEGY=auto

# OCR languages (comma-separated ISO 639-3 codes)
# Common: eng=English, deu=German, fra=French, spa=Spanish
UNSTRUCTURED_LANGUAGES=eng,deu

# Progress reporting interval in seconds (default: 10)
# During long-running OCR operations, progress notifications are sent to the MCP client
# at this interval to prevent timeouts and provide status updates
PROGRESS_INTERVAL=10

# ============================================
# Tesseract Processor (Local OCR)
# ============================================
# Enable Tesseract processor (requires tesseract binary installed)
# This is a local, lightweight OCR solution for images only
ENABLE_TESSERACT=false

# Path to tesseract executable (optional, auto-detected if in PATH)
#TESSERACT_CMD=/usr/bin/tesseract

# OCR language (e.g., eng, deu, eng+deu for multiple)
TESSERACT_LANG=eng

# ============================================
# Custom Processor (Your own API)
# ============================================
# Enable custom document processor via HTTP API
ENABLE_CUSTOM_PROCESSOR=false

# Unique name for your processor
#CUSTOM_PROCESSOR_NAME=my_ocr

# Your custom processor API endpoint
#CUSTOM_PROCESSOR_URL=http://localhost:9000/process

# Optional API key for authentication
#CUSTOM_PROCESSOR_API_KEY=your-api-key-here

# Request timeout in seconds
#CUSTOM_PROCESSOR_TIMEOUT=60

# Comma-separated MIME types your processor supports
#CUSTOM_PROCESSOR_TYPES=application/pdf,image/jpeg,image/png