Files
gh-christianlouis-docuelevate/.env.demo
T
copilot-swe-agent[bot] eea99eb01d feat(pdfa): add PDF/A archival conversion using ocrmypdf
- Add ENABLE_PDFA_CONVERSION, PDFA_FORMAT, PDFA_UPLOAD_TO_PROVIDERS config settings
- Add original_pdfa_path and processed_pdfa_path columns to FileRecord model
- Create Alembic migration 011_add_pdfa_paths
- Create app/tasks/convert_to_pdfa.py Celery task using ocrmypdf + Ghostscript
- Integrate PDF/A conversion into finalize_document_storage pipeline
- Add comprehensive unit tests (15 tests)
- Update .env.demo and docs/ConfigurationGuide.md

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
2026-03-02 13:35:13 +00:00

362 lines
16 KiB
Bash
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# **Core Settings**
WORKDIR=/workdir
DATABASE_URL=sqlite:///./app/database.db
REDIS_URL=redis://redis:6379/0
EXTERNAL_HOSTNAME=docuelevate.example.com
GOTENBERG_URL=http://gotenberg:3000
ALLOW_FILE_DELETE=true # Allow deletion of file records
# **UI / Appearance**
# Default colour scheme: system (follow OS), light, or dark
# Individual users can always override with the navbar dark-mode toggle.
# UI_DEFAULT_COLOR_SCHEME=system
# **Batch Processing Settings**
# Control throttling behavior for the /processall endpoint to prevent overwhelming downstream APIs
PROCESSALL_THROTTLE_THRESHOLD=20 # Number of files above which throttling is applied (default: 20)
PROCESSALL_THROTTLE_DELAY=3 # Delay in seconds between each task submission when throttling (default: 3)
# **Task Retry Settings**
# Failed tasks are automatically retried with exponential backoff and jitter.
# TASK_RETRY_MAX_RETRIES=3 # Max retry attempts per task (default: 3)
# TASK_RETRY_DELAYS=60,300,900 # Countdown (seconds) before each retry; 1 min, 5 min, 15 min
# TASK_RETRY_JITTER=true # Add ±20% random jitter to prevent thundering-herd (default: true)
# **Client-Side Upload Throttling**
# Controls pacing when the browser uploads files (especially large directory drops).
# The browser auto-detects rate-limit (HTTP 429) responses and backs off accordingly.
UPLOAD_CONCURRENCY=3 # Max simultaneous uploads from the browser (default: 3)
UPLOAD_QUEUE_DELAY_MS=500 # Delay (ms) between starting each upload slot (default: 500)
# **File Upload Size Limits** (Security - see SECURITY_AUDIT.md)
# Maximum file upload size in bytes. Default: 1GB (1073741824 bytes)
# Prevents resource exhaustion attacks. Adjust based on your server capacity.
MAX_UPLOAD_SIZE=1073741824
# Maximum size for a single file chunk in bytes (optional)
# If set and a file exceeds this size, it will be split into smaller chunks for processing
# Default: None (no splitting). Example: 104857600 for 100MB chunks
# MAX_SINGLE_FILE_SIZE=104857600
# **Request Body Size Limit** (Security - see SECURITY_AUDIT.md)
# Maximum request body size in bytes for non-file-upload requests (JSON, form data, etc.).
# Default: 1MB (1048576 bytes). File uploads are governed by MAX_UPLOAD_SIZE above.
# Prevents memory exhaustion from oversized JSON/form payloads.
# MAX_REQUEST_BODY_SIZE=1048576
# **Security Headers** (see SECURITY_AUDIT.md and docs/DeploymentGuide.md)
# Disabled by default since most deployments use a reverse proxy (Traefik, Nginx, etc.)
# that already adds these headers. Set to true only if deploying directly without a reverse proxy.
# SECURITY_HEADERS_ENABLED=false
# If you enable security headers, you can also configure individual headers:
# Strict-Transport-Security (HSTS) - Forces HTTPS connections
# Only effective when served over HTTPS. Disable if not using HTTPS or if proxy adds this header
# SECURITY_HEADER_HSTS_ENABLED=true
# SECURITY_HEADER_HSTS_VALUE="max-age=31536000; includeSubDomains"
# Content-Security-Policy (CSP) - Controls resource loading
# Customize based on your application's resource loading needs
# Default allows self-hosted resources, inline scripts/styles, and external images
# SECURITY_HEADER_CSP_ENABLED=true
# SECURITY_HEADER_CSP_VALUE="default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data: https:; font-src 'self' data:;"
# X-Frame-Options - Prevents clickjacking attacks
# Options: DENY (no framing), SAMEORIGIN (same origin framing only), ALLOW-FROM uri
# SECURITY_HEADER_X_FRAME_OPTIONS_ENABLED=true
# SECURITY_HEADER_X_FRAME_OPTIONS_VALUE="DENY"
# X-Content-Type-Options - Prevents MIME sniffing
# Always set to 'nosniff' when enabled
# SECURITY_HEADER_X_CONTENT_TYPE_OPTIONS_ENABLED=true
# **CORS (Cross-Origin Resource Sharing)** (see SECURITY_AUDIT.md Infrastructure Security)
# Disabled by default: most deployments rely on a reverse proxy (Traefik, Nginx, etc.) to inject
# CORS headers. Set CORS_ENABLED=true only if DocuElevate is exposed directly without a proxy,
# or if your proxy does not handle CORS. When enabled, only list the exact origins that need access.
#
# Rationale for reverse-proxy-first approach:
# Traefik/Nginx already set Access-Control-Allow-Origin (and related headers) for every response,
# so adding the middleware here would duplicate headers. When this flag is False the application
# trusts the proxy layer to enforce CORS policy; set it to True for standalone / direct-access
# deployments only.
#
# CORS_ENABLED=false
#
# Comma-separated list of allowed origins (use * to allow all - not recommended with credentials)
# CORS_ALLOWED_ORIGINS=https://app.example.com,https://admin.example.com
#
# Allow cookies / Authorization headers in cross-origin requests
# Must be False when CORS_ALLOWED_ORIGINS=* (browser security requirement)
# CORS_ALLOW_CREDENTIALS=false
#
# Allowed HTTP methods (comma-separated)
# CORS_ALLOWED_METHODS=GET,POST,PUT,DELETE,OPTIONS,PATCH
#
# Allowed request headers (use * to allow all)
# CORS_ALLOWED_HEADERS=*
# **Rate Limiting** (see SECURITY_AUDIT.md and docs/API.md)
# Protects against DoS attacks and API abuse by limiting request rates per IP/user
# Enabled by default - highly recommended for production
RATE_LIMITING_ENABLED=true
# Default rate limit for all API endpoints (format: count/period)
# Periods can be: second, minute, hour, day
# Default: 100 requests per minute per IP/user
RATE_LIMIT_DEFAULT=100/minute
# Rate limit for file upload endpoints
# Allows faster uploads while still preventing abuse
# Default: 600 uploads per minute per IP/user
RATE_LIMIT_UPLOAD=600/minute
# Rate limit for authentication endpoints
# Strict limit to prevent brute force attacks
# Default: 10 attempts per minute per IP
RATE_LIMIT_AUTH=10/minute
# Note: Processing endpoints (OCR, metadata extraction) use built-in queue throttling
# via Celery task queue to control processing rates and prevent upstream API overloads.
# No additional API-level rate limit is needed for processing endpoints.
# **Authentication**
AUTH_ENABLED=true
# Generate a secure random string, for example:
# python -c "import secrets; print(secrets.token_hex(32))"
SESSION_SECRET=b39fd43f68d0491ca942f28a16e484b1e763fe9accf4445ca2669a5f3b179eb4
ADMIN_USERNAME=admin
ADMIN_PASSWORD=your_secure_password
ADMIN_GROUP_NAME=admin
# **OpenID Connect/Authentik Settings**
AUTHENTIK_CLIENT_ID=<yourAuthentikAppClientID>
AUTHENTIK_CLIENT_SECRET=<yourAuthentikClientSecret>
AUTHENTIK_CONFIG_URL=<ConfigUrlOfYourApp, e.g. https://authentik.example.com/application/o/docuelevate/.well-known/openid-configuration>
OAUTH_PROVIDER_NAME="Authentik SSO"
# **AI/ML Services**
# Select your AI provider: openai | azure | anthropic | gemini | ollama | openrouter | portkey | litellm
AI_PROVIDER=openai
# Model override (optional falls back to OPENAI_MODEL when not set)
# AI_MODEL=gpt-4o-mini
# --- OpenAI (AI_PROVIDER=openai) ---
OPENAI_API_KEY="<OPENAI_API_KEY>"
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_MODEL=gpt-4o-mini
# --- Anthropic Claude (AI_PROVIDER=anthropic) ---
# ANTHROPIC_API_KEY=sk-ant-...
# AI_MODEL=claude-3-5-sonnet-20241022
# --- Google Gemini (AI_PROVIDER=gemini) ---
# GEMINI_API_KEY=AIza...
# AI_MODEL=gemini-1.5-pro
# --- Ollama local LLMs (AI_PROVIDER=ollama) ---
# OLLAMA_BASE_URL=http://localhost:11434
# AI_MODEL=llama3.2
# --- OpenRouter (AI_PROVIDER=openrouter) ---
# OPENROUTER_API_KEY=sk-or-...
# AI_MODEL=anthropic/claude-3.5-sonnet
# --- Portkey AI Gateway (AI_PROVIDER=portkey) ---
# PORTKEY_API_KEY=pk-...
# PORTKEY_VIRTUAL_KEY=vk-... # optional routes to provider credentials in Portkey vault
# PORTKEY_CONFIG=pc-... # optional saved Config ID for fallbacks / load balancing
# --- Azure OpenAI (AI_PROVIDER=azure) ---
# OPENAI_API_KEY=<azure-key>
# OPENAI_BASE_URL=https://my-resource.openai.azure.com
# AZURE_OPENAI_API_VERSION=2024-02-01
# AI_MODEL=gpt-4o # deployment name in Azure
# Azure Document Intelligence (OCR separate from AI provider above)
# **Email Settings**
EMAIL_HOST=smtp.example.com
EMAIL_PORT=587
EMAIL_USERNAME=docuelevate@example.com
EMAIL_PASSWORD=your_secure_email_password
EMAIL_USE_TLS=True
EMAIL_SENDER=DocuElevate System <docuelevate@example.com>
EMAIL_DEFAULT_RECIPIENT=recipient@example.com
# **IMAP Settings**
IMAP1_HOST=mail.example.com
IMAP1_PORT=993
IMAP1_USERNAME=<IMAP1_USERNAME>
IMAP1_PASSWORD=<IMAP1_PASSWORD>
IMAP1_SSL=true
IMAP1_POLL_INTERVAL_MINUTES=5
IMAP1_DELETE_AFTER_PROCESS=false
IMAP2_HOST=imap.gmail.com
IMAP2_PORT=993
IMAP2_USERNAME=<IMAP2_USERNAME>
IMAP2_PASSWORD=<IMAP2_PASSWORD>
IMAP2_SSL=true
IMAP2_POLL_INTERVAL_MINUTES=10
IMAP2_DELETE_AFTER_PROCESS=false
# IMAP Readonly Mode (Feature Flag)
# When true, IMAP processing will fetch and process attachments but will NOT modify
# the mailbox state (no starring, labeling, deleting, or flag changes).
# Use for pre-production instances that share a mailbox with production.
IMAP_READONLY_MODE=false
# **Storage/Document Services**
# Amazon S3
AWS_REGION=us-east-1
AWS_ACCESS_KEY_ID=AKIAIOSFODNN7EXAMPLE
AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
S3_BUCKET_NAME=my-document-bucket
S3_FOLDER_PREFIX=documents/uploads/2023/ # Organizes files in this subfolder
S3_STORAGE_CLASS=STANDARD
S3_ACL=private
# NextCloud
NEXTCLOUD_UPLOAD_URL=https://nextcloud.example.com/remote.php/dav/files/<USERNAME>
NEXTCLOUD_FOLDER="<NEXTCLOUD_FOLDER_PATH>"
NEXTCLOUD_USERNAME=<NEXTCLOUD_USERNAME>
NEXTCLOUD_PASSWORD=<NEXTCLOUD_PASSWORD>
# Paperless-ngx
PAPERLESS_HOST=https://paperless.example.com
PAPERLESS_NGX_API_TOKEN=<PAPERLESS_API_TOKEN>
# Optional: Name of the custom field in Paperless-ngx to store the "absender" (sender) value
# If set, the extracted sender information will be automatically set as a custom field in Paperless
# Example: PAPERLESS_CUSTOM_FIELD_ABSENDER=Absender
# PAPERLESS_CUSTOM_FIELD_ABSENDER=
# Optional: JSON mapping of metadata fields to Paperless custom field names
# This allows you to map multiple extracted metadata fields to custom fields in Paperless
# The mapping format is: {"metadata_field_name": "PaperlessCustomFieldName", ...}
# Available metadata fields: absender, empfaenger, correspondent, document_type, language,
# kommunikationsart, kommunikationskategorie, reference_number, etc.
# Example: PAPERLESS_CUSTOM_FIELDS_MAPPING={"absender": "Sender", "empfaenger": "Recipient", "language": "Language", "correspondent": "Correspondent"}
# PAPERLESS_CUSTOM_FIELDS_MAPPING=
# Dropbox
DROPBOX_APP_KEY=<DROPBOX_APP_KEY>
DROPBOX_APP_SECRET=<DROPBOX_APP_SECRET>
DROPBOX_REFRESH_TOKEN=<DROPBOX_REFRESH_TOKEN>
DROPBOX_FOLDER="/Documents/Uploads"
# Google Drive
# Service Account Method:
GOOGLE_DRIVE_CREDENTIALS_JSON={"type":"service_account","project_id":"your-project","private_key_id":"key-id","private_key":"-----BEGIN PRIVATE KEY-----\nYOUR_PRIVATE_KEY\n-----END PRIVATE KEY-----\n","client_email":"service-account@project.iam.gserviceaccount.com","client_id":"client-id","auth_uri":"https://accounts.google.com/o/oauth2/auth","token_uri":"https://oauth2.googleapis.com/token","auth_provider_x509_cert_url":"https://www.googleapis.com/oauth2/v1/certs","client_x509_cert_url":"https://www.googleapis.com/robot/v1/metadata/x509/service-account%40project.iam.gserviceaccount.com"}
GOOGLE_DRIVE_FOLDER_ID=<YOUR_FOLDER_ID>
GOOGLE_DRIVE_DELEGATE_TO=<OPTIONAL_USER_EMAIL>
# OAuth Method (Alternative):
GOOGLE_DRIVE_USE_OAUTH=false # Set to true to use OAuth instead of service account
GOOGLE_DRIVE_CLIENT_ID=your-oauth-client-id # Required for OAuth method
GOOGLE_DRIVE_CLIENT_SECRET=your-oauth-client-secret # Required for OAuth method
GOOGLE_DRIVE_REFRESH_TOKEN=your-oauth-refresh-token # Required for OAuth method
# OneDrive
ONEDRIVE_CLIENT_ID=your-client-id
ONEDRIVE_CLIENT_SECRET=your-client-secret
ONEDRIVE_TENANT_ID=common
ONEDRIVE_REFRESH_TOKEN=your-refresh-token
ONEDRIVE_FOLDER_PATH=Documents/Uploads
# WebDAV
WEBDAV_URL=https://webdav.example.com/path
WEBDAV_USERNAME=webdav_user
WEBDAV_PASSWORD=your_secure_webdav_password
WEBDAV_FOLDER=/Documents/Uploads
WEBDAV_VERIFY_SSL=True
# FTP
# Security Note: FTP_USE_TLS=True is strongly recommended for secure connections
# Set FTP_ALLOW_PLAINTEXT=False in production to prevent unencrypted FTP
FTP_HOST=ftp.example.com
FTP_PORT=21
FTP_USERNAME=ftp_user
FTP_PASSWORD=your_secure_ftp_password
FTP_FOLDER=/Documents/Uploads
FTP_USE_TLS=True
FTP_ALLOW_PLAINTEXT=True
# SFTP
# Security Note: Host key verification is enabled by default (False)
# Only set to True in development/testing environments if needed
# When false, configure SSH known_hosts for proper host key verification
SFTP_HOST=sftp.example.com
SFTP_PORT=22
SFTP_USERNAME=sftp_user
SFTP_PASSWORD=your_secure_sftp_password
# SFTP_PRIVATE_KEY=/path/to/private_key.pem
# SFTP_PRIVATE_KEY_PASSPHRASE=optional_passphrase
SFTP_FOLDER=/Documents/Uploads
SFTP_DISABLE_HOST_KEY_VERIFICATION=False # Default is False (secure); set to True only for testing
# **HTTP Request Settings**
# Timeout for HTTP requests - set higher to handle large PDF files (up to 1GB)
HTTP_REQUEST_TIMEOUT=120 # Timeout in seconds (default: 120 for large file operations)
# **Notification Settings**
# Configure notification services using Apprise URL format
# See https://github.com/caronc/apprise#supported-notifications
# Examples:
# - Discord: discord://webhook_id/webhook_token
# - Telegram: tgram://bot_token/chat_id
# - Email: mailto://user:pass@example.com
# - Pushover: pover://user_key/app_token
# - Slack: slack://tokenA/tokenB/tokenC
# - Matrix: matrix://username:password@domain/#room
# You can specify multiple notification URLs by separating them with commas
NOTIFICATION_URLS=discord://webhook_id/webhook_token,mailto://user:pass@gmail.com,tgram://bot_token/chat_id
# Control when notifications are sent
NOTIFY_ON_TASK_FAILURE=True
NOTIFY_ON_CREDENTIAL_FAILURE=True
NOTIFY_ON_STARTUP=True
NOTIFY_ON_SHUTDOWN=False
NOTIFY_ON_FILE_PROCESSED=True
# Webhooks Notify external systems via HTTP POST on document events.
# Individual webhooks (URL, events, secret) are managed via /api/webhooks/.
WEBHOOK_ENABLED=True
# Uptime Kuma
UPTIME_KUMA_URL=https://status.example.com/api/push/abcdef123456?status=up
UPTIME_KUMA_PING_INTERVAL=5
# **Full-Text Search (Meilisearch)**
# URL for the Meilisearch instance.
# Default is "http://meilisearch:7700" — the Docker Compose / K8s service name —
# so container-to-container networking works without extra configuration.
# Override to "http://localhost:7700" only when running the API process outside Docker.
MEILISEARCH_URL=http://meilisearch:7700
# Optional master/API key for secured Meilisearch instances
# MEILISEARCH_API_KEY=your_master_key_here
MEILISEARCH_INDEX_NAME=documents
ENABLE_SEARCH=True
# **Duplicate Detection**
# Exact duplicate detection (SHA-256) is always on during document processing.
# The settings below control near-duplicate detection (same scanned content,
# different hash) and the visibility of deduplication steps.
ENABLE_DEDUPLICATION=True
SHOW_DEDUPLICATION_STEP=True
# Minimum cosine similarity score (01) for two documents to be flagged as
# near-duplicates. 0.85 means 85 % semantic overlap. Lower = more matches.
NEAR_DUPLICATE_THRESHOLD=0.85
# **PDF/A Archival Conversion**
# When enabled, PDF/A copies of both the original ingested file and the processed
# file are created and saved alongside the standard copies. This may double or
# triple storage but provides better legal coverage with time-stamped archival copies.
# Uses ocrmypdf with Ghostscript for the conversion.
ENABLE_PDFA_CONVERSION=false
# PDF/A format variant: 1 = PDF/A-1b, 2 = PDF/A-2b (default), 3 = PDF/A-3b
PDFA_FORMAT=2
# Also upload the processed PDF/A variant to all configured storage providers
# (files are uploaded with a '-PDFA' suffix in their filename)
PDFA_UPLOAD_TO_PROVIDERS=false