env.sample•7.36 kB
# 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
# - OAuth client credentials are stored encrypted in SQLite (TOKEN_STORAGE_DB)
# - Optional: Pre-register client and provide credentials (otherwise auto-registers)
NEXTCLOUD_OIDC_CLIENT_ID=
NEXTCLOUD_OIDC_CLIENT_SECRET=
NEXTCLOUD_MCP_SERVER_URL=http://localhost:8000
# OAuth Storage Configuration (SQLite storage for OAuth clients and refresh tokens)
# TOKEN_ENCRYPTION_KEY: Required for encrypting OAuth client secrets and refresh tokens
# Generate with: python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"
#TOKEN_ENCRYPTION_KEY=
# TOKEN_STORAGE_DB: Path to SQLite database (default: /app/data/tokens.db)
#TOKEN_STORAGE_DB=/app/data/tokens.db
# ===== ADR-004 PROGRESSIVE CONSENT CONFIGURATION =====
# Enable Progressive Consent mode (dual OAuth flows)
# When enabled: Flow 1 for client auth, Flow 2 for Nextcloud resource access
# When disabled: Uses existing hybrid flow (backward compatible)
# MCP Server OAuth Client Configuration
# The MCP server's own OAuth client credentials for Flow 2
# If not set, will use dynamic client registration
#MCP_SERVER_CLIENT_ID=
#MCP_SERVER_CLIENT_SECRET=
# Allowed MCP Client IDs (comma-separated list)
# Client IDs that are allowed to authenticate in Flow 1
# Examples: claude-desktop,continue-dev,zed-editor
#ALLOWED_MCP_CLIENTS=claude-desktop,continue-dev,zed-editor
# Token cache configuration for Token Broker Service
# Cache TTL in seconds (default: 300 = 5 minutes)
#TOKEN_CACHE_TTL=300
# Early refresh threshold in seconds (default: 30)
#TOKEN_CACHE_EARLY_REFRESH=30
# 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
# ============================================
# Semantic Search & Vector Sync Configuration
# ============================================
# EXPERIMENTAL: Semantic search for Notes app (multi-app support planned)
# Requires: Qdrant vector database + Ollama embedding service
# Disabled by default
# Enable background vector indexing
VECTOR_SYNC_ENABLED=false
# Document scan interval in seconds (default: 300 = 5 minutes)
# How often to check for new/updated documents
#VECTOR_SYNC_SCAN_INTERVAL=300
# Concurrent indexing workers (default: 3)
# Number of parallel workers for embedding generation
#VECTOR_SYNC_PROCESSOR_WORKERS=3
# Max queued documents (default: 10000)
# Maximum documents waiting to be processed
#VECTOR_SYNC_QUEUE_MAX_SIZE=10000
# ============================================
# Qdrant Vector Database Configuration
# ============================================
# Choose ONE of three modes:
# 1. In-memory mode (default): Set neither QDRANT_URL nor QDRANT_LOCATION
# 2. Persistent local: Set QDRANT_LOCATION=/path/to/data
# 3. Network mode: Set QDRANT_URL=http://qdrant:6333
# Network mode: URL to Qdrant service
#QDRANT_URL=http://qdrant:6333
# Local mode: Path to store vectors (use :memory: for in-memory)
#QDRANT_LOCATION=:memory:
# API key for network mode (optional)
#QDRANT_API_KEY=
# Collection name (optional - auto-generated if not set)
# Auto-generation format: {deployment-id}-{model-name}
# Allows safe model switching and multi-server deployments
#QDRANT_COLLECTION=nextcloud_content
# ============================================
# Ollama Embedding Service Configuration
# ============================================
# Ollama endpoint for embeddings (if not set, uses SimpleEmbeddingProvider fallback)
#OLLAMA_BASE_URL=http://ollama:11434
# Embedding model to use (default: nomic-embed-text, 768 dimensions)
# Changing this creates a new collection (requires re-embedding all documents)
#OLLAMA_EMBEDDING_MODEL=nomic-embed-text
# Verify SSL certificates (default: true)
#OLLAMA_VERIFY_SSL=true
# ============================================
# Document Chunking Configuration
# ============================================
# Configure how documents are split before embedding
# Words per chunk (default: 512)
# Smaller chunks (256-384): More precise, less context, more storage
# Larger chunks (768-1024): More context, less precise, less storage
#DOCUMENT_CHUNK_SIZE=512
# Overlapping words between chunks (default: 50)
# Recommended: 10-20% of chunk size
# Preserves context across chunk boundaries
#DOCUMENT_CHUNK_OVERLAP=50