paperless-ngx/paperless.conf.example

# Sample paperless.conf
# Copy this file to /etc/paperless.conf and modify it to suit your needs.
# As this file contains passwords it should only be readable by the user
# running paperless.

###############################################################################
####                           Message Broker                              ####
###############################################################################

# This is required for processing scheduled tasks such as email fetching, index
# optimization and for training the automatic document matcher.
# Defaults to localhost:6379.
#PAPERLESS_REDIS="redis://localhost:6379"


###############################################################################
####                        Database Settings                              ####
###############################################################################

# By default, sqlite is used as the database backend. This can be changed here.
# The docker-compose service definition uses a postgresql server. The
# configuration for this is already done inside the docker-compose.env file.

#Set PAPERLESS_DBHOST and postgresql will be used instead of mysql.
#PAPERLESS_DBHOST="localhost"

#Adjust port if necessary
#PAPERLESS_DBPORT=

#name, user and pass all default to "paperless"
#PAPERLESS_DBNAME="paperless"
#PAPERLESS_DBUSER="paperless"
#PAPERLESS_DBPASS="paperless"


###############################################################################
####                         Paths & Folders                               ####
###############################################################################

# This where your documents should go to be consumed.  Make sure that it exists
# and that the user running the paperless service can read/write its contents
# before you start Paperless.
PAPERLESS_CONSUMPTION_DIR="../consume"

# This is where paperless stores all its data (search index, sqlite database,
# classification model, etc).
#PAPERLESS_DATA_DIR="../data"

# This is where your documents and thumbnails are stored.
#PAPERLESS_MEDIA_ROOT="../media"

# Override the default STATIC_ROOT here.  This is where all static files
# created using "collectstatic" manager command are stored.
#PAPERLESS_STATICDIR="../static"


# Override the STATIC_URL here.  Unless you're hosting Paperless off a
# subdomain like /paperless/, you probably don't need to change this.
#PAPERLESS_STATIC_URL="/static/"


# Specify a filename format for the document (directories are supported)
# Use the following placeholders:
# * {correspondent}
# * {title}
# * {created}
# * {added}
# * {tags[KEY]} If your tags conform to key_value or key-value
# * {tags[INDEX]} If your tags are strings, select the tag by index
# Uniqueness of filenames is ensured, as an incrementing counter is attached
# to each filename.
#PAPERLESS_FILENAME_FORMAT=""

###############################################################################
####                              Security                                 ####
###############################################################################

# Controls whether django's debug mode is enabled. Disable this on production
# systems. Debug mode is disabled by default.
#PAPERLESS_DEBUG="false"

# GnuPG encryption is deprecated and will be removed in future versions.
#
# Paperless can be instructed to attempt to encrypt your PDF files with GPG
# using the PAPERLESS_PASSPHRASE specified below.  If however you're not
# concerned about encrypting these files (for example if you have disk
# encryption locally) then you don't need this and can safely leave this value
# un-set.
#
# One final note about the passphrase.  Once you've consumed a document with
# one passphrase, DON'T CHANGE IT.  Paperless assumes this to be a constant and
# can't properly export documents that were encrypted with an old passphrase if
# you've since changed it to a new one.
#
# The default is to not use encryption at all.
#PAPERLESS_PASSPHRASE="secret"


# The secret key has a default that should be fine so long as you're hosting
# Paperless on a closed network.  However, if you're putting this anywhere
# public, you should change the key to something unique and verbose.
#PAPERLESS_SECRET_KEY="change-me"


# If you're planning on putting Paperless on the open internet, then you
# really should set this value to the domain name you're using.  Failing to do
# so leaves you open to HTTP host header attacks:
# https://docs.djangoproject.com/en/1.10/topics/security/#host-headers-virtual-hosting
#
# Just remember that this is a comma-separated list, so "example.com" is fine,
# as is "example.com,www.example.com", but NOT " example.com" or "example.com,"
#PAPERLESS_ALLOWED_HOSTS="example.com,www.example.com"

# If you decide to use the Paperless API in an ajax call, you need to add your
# servers to the list of allowed hosts that can do CORS calls. By default
# Paperless allows calls from localhost:8080, but you'd like to change that,
# you can set this value to a comma-separated list.
#PAPERLESS_CORS_ALLOWED_HOSTS="localhost:8080,example.com,localhost:8000"

# To host paperless under a subpath url like example.com/paperless you set
# this value to /paperless. No trailing slash!
#
# https://docs.djangoproject.com/en/1.11/ref/settings/#force-script-name
#PAPERLESS_FORCE_SCRIPT_NAME=""

###############################################################################
####                          Software Tweaks                              ####
###############################################################################

# Paperless does multiple things in the background: Maintain the search index,
# maintain the automatic matching algorithm, check emails, consume documents,
# etc. This variable specifies how many things it will do in parallel.
#PAPERLESS_TASK_WORKERS=1

# Furthermore, paperless uses multiple threads when consuming documents to
# speed up OCR. This variable specifies how many pages paperless will process
# in parallel on a single document.
#PAPERLESS_THREADS_PER_WORKER=1

# Ensure that the product
#   PAPERLESS_TASK_WORKERS * PAPERLESS_THREADS_PER_WORKER
# does not exceed your CPU core count or else paperless will be extremely slow.
# If you want paperless to process many documents in parallel, choose a high
# worker count. If you want paperless to process very large documents faster,
# use a higher thread per worker count.
# The default is a balance between the two, according to your CPU core count,
# with a slight favor towards threads per worker, and using as much cores as
# possible.
# If you only specify PAPERLESS_TASK_WORKERS, paperless will adjust
# PAPERLESS_THREADS_PER_WORKER automatically.

# If paperless won't find documents added to your consume folder, it might
# not be able to automatically detect filesystem changes. In that case,
# specify a polling interval in seconds below, which will then cause paperless
# to periodically check your consumption directory for changes.
#PAPERLESS_CONSUMER_POLLING=10


# When the consumer detects a duplicate document, it will not touch the
# original document. This default behavior can be changed here.
#PAPERLESS_CONSUMER_DELETE_DUPLICATES="false"

# After a document is consumed, Paperless can trigger an arbitrary script if
# you like.  This script will be passed a number of arguments for you to work
# with.  The default is blank, which means nothing will be executed.  For more
# information, take a look at the docs:
# http://paperless.readthedocs.org/en/latest/consumption.html#hooking-into-the-consumption-process
#PAPERLESS_POST_CONSUME_SCRIPT="/path/to/an/arbitrary/script.sh"

# By default, paperless will check the document text for document date information.
# Uncomment the line below to enable checking the document filename for date
# information. The date order can be set to any option as specified in
# https://dateparser.readthedocs.io/en/latest/#settings. The filename will be
# checked first, and if nothing is found, the document text will be checked
# as normal.
#PAPERLESS_FILENAME_DATE_ORDER="YMD"

# Sometimes devices won't create filenames which can be parsed properly
# by the filename parser (see
# https://paperless.readthedocs.io/en/latest/guesswork.html).
#
# This setting allows to specify a list of transformations
# in regular expression syntax, which are passed in order to re.sub.
# Transformation stops after the first match, so at most one transformation
# is applied.
#
# Syntax is a JSON array of dictionaries containing "pattern" and "repl"
# as keys.
#
# The example below transforms filenames created by a Brother ADS-2400N
# document scanner in its standard configuration `Name_Date_Count', so that
# count is used as title, name as tag and date can be parsed by paperless.
#PAPERLESS_FILENAME_PARSE_TRANSFORMS=[{"pattern":"^([a-z]+)_(\\d{8})_(\\d{6})_([0-9]+)\\.", "repl":"\\2\\3Z - \\4 - \\1."}]

#
# The following values use sensible defaults for modern systems, but if you're
# running Paperless on a low-resource device (like a Raspberry Pi), modifying
# some of these values may be necessary.
#


# Customize the default language that tesseract will attempt to use when
# parsing documents. The default language is used whenever
#  - No language could be detected on a document
#  - No tesseract data files are available for the detected language
# It should be a 3-letter language code consistent with ISO
# 639: https://www.loc.gov/standards/iso639-2/php/code_list.php
#PAPERLESS_OCR_LANGUAGE=eng


# On smaller systems, or even in the case of Very Large Documents, the consumer
# may explode, complaining about how it's "unable to extend pixel cache".  In
# such cases, try setting this to a reasonably low value, like 32000000.  The
# default is to use whatever is necessary to do everything without writing to
# disk, and units are in megabytes.
#
# For more information on how to use this value, you should probably search
# the web for "MAGICK_MEMORY_LIMIT".
#PAPERLESS_CONVERT_MEMORY_LIMIT=0


# Similar to the memory limit, if you've got a small system and your OS mounts
# /tmp as tmpfs, you should set this to a path that's on a physical disk, like
# /home/your_user/tmp or something.  ImageMagick will use this as scratch space
# when crunching through very large documents.
#
# For more information on how to use this value, you should probably search
# the web for "MAGICK_TMPDIR".
#PAPERLESS_CONVERT_TMPDIR=/var/tmp/paperless


# By default the conversion density setting for documents is 300DPI, in some
# cases it has proven useful to configure a lesser value.
# This setting has a high impact on the physical size of tmp page files,
# the speed of document conversion, and can affect the accuracy of OCR
# results. Individual results can vary and this setting should be tested
# thoroughly against the documents you are importing to see if it has any
# impacts either negative or positive.
# Testing on limited document sets has shown a setting of 200 can cut the
# size of tmp files by 1/3, and speed up conversion by up to 4x
# with little impact to OCR accuracy.
#PAPERLESS_CONVERT_DENSITY=300

# By default Paperless does not OCR a document if the text can be retrieved from
# the document directly. Set to true to always OCR documents.
#PAPERLESS_OCR_ALWAYS="false"


###############################################################################
####                            Interface                                  ####
###############################################################################

# Override the default UTC time zone here.
# See https://docs.djangoproject.com/en/1.10/ref/settings/#std:setting-TIME_ZONE
# for details on how to set it.
#PAPERLESS_TIME_ZONE=UTC


###############################################################################
####                     Third-Party Binaries                              ####
###############################################################################

# There are a few external software packages that Paperless expects to find on
# your system when it starts up.  Unless you've done something creative with
# their installation, you probably won't need to edit any of these.  However,
# if you've installed these programs somewhere where simply typing the name of
# the program doesn't automatically execute it (ie. the program isn't in your
# $PATH), then you'll need to specify the literal path for that program here.

# Convert (part of the ImageMagick suite)
#PAPERLESS_CONVERT_BINARY=/usr/bin/convert

# Ghostscript
#PAPERLESS_GS_BINARY = /usr/bin/gs

# Unpaper
#PAPERLESS_UNPAPER_BINARY=/usr/bin/unpaper

# Optipng (for optimising thumbnail sizes)
#PAPERLESS_OPTIPNG_BINARY=/usr/bin/optipng