paperless-ngx/docker/compose/docker-compose.env

###############################################################################
# IntelliDocs (Paperless-ngx) settings                                        #
###############################################################################

# See http://docs.paperless-ngx.com/configuration/ for all available options.

# The UID and GID of the user used to run paperless in the container. Set this
# to your UID and GID on the host so that you have write access to the
# consumption directory.
#USERMAP_UID=1000
#USERMAP_GID=1000

# See the documentation linked above for all options. A few commonly adjusted settings
# are provided below.

# This is required if you will be exposing IntelliDocs on a public domain
# (if doing so please consider security measures such as reverse proxy)
#PAPERLESS_URL=https://intellidocs.example.com

# Adjust this key if you plan to make paperless available publicly. It should
# be a very long sequence of random characters. You don't need to remember it.
#PAPERLESS_SECRET_KEY=change-me

# Use this variable to set a timezone for the Docker containers. Defaults to UTC.
#PAPERLESS_TIME_ZONE=America/Los_Angeles

# The default language to use for OCR. Set this to the language most of your
# documents are written in.
#PAPERLESS_OCR_LANGUAGE=eng

# Additional languages to install for text recognition, separated by a whitespace.
# Note that this is different from PAPERLESS_OCR_LANGUAGE (default=eng), which defines
# the language used for OCR.
# The container installs English, German, Italian, Spanish and French by default.
# See https://packages.debian.org/search?keywords=tesseract-ocr-&searchon=names
# for available languages.
#PAPERLESS_OCR_LANGUAGES=tur ces

###############################################################################
# IntelliDocs Advanced ML/OCR Features (NEW)                                  #
###############################################################################

# Enable/disable advanced ML features (BERT classification, NER, semantic search)
# Set to 1 to enable, 0 to disable. Default: 1 (enabled)
#PAPERLESS_ENABLE_ML_FEATURES=1

# Enable/disable advanced OCR features (table extraction, handwriting, forms)
# Set to 1 to enable, 0 to disable. Default: 1 (enabled)
#PAPERLESS_ENABLE_ADVANCED_OCR=1

# ML Model selection for document classification
# Options: distilbert-base-uncased (default, fast), bert-base-uncased (more accurate but slower)
#PAPERLESS_ML_CLASSIFIER_MODEL=distilbert-base-uncased

# Enable GPU acceleration for ML/OCR if available
# Set to 1 to use GPU, 0 to use CPU only. Default: 0 (CPU)
#PAPERLESS_USE_GPU=0

# Confidence threshold for table detection (0.0 to 1.0)
# Higher values = fewer false positives but might miss some tables. Default: 0.7
#PAPERLESS_TABLE_DETECTION_THRESHOLD=0.7

# Enable handwriting recognition for documents
# Set to 1 to enable, 0 to disable. Default: 1 (enabled)
#PAPERLESS_ENABLE_HANDWRITING_OCR=1

# Cache directory for ML models (to persist downloaded models between container restarts)
# Should be mounted as a volume for better performance
#PAPERLESS_ML_MODEL_CACHE=/usr/src/paperless/.cache/huggingface