paperless-ngx is an excellent document organization tool

README.md

paperless

github
https://github.com/paperless-ngx/paperless-ngx
docs
https://paperless-ngx.readthedocs.io/en/latest/

# Initial user setup

docker-compose run --rm webserver createsuperuser

docker-compose.env

# 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

# 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&suite=buster
# for available languages.
#PAPERLESS_OCR_LANGUAGES=tur ces

###############################################################################
# Paperless-specific settings                                                 #
###############################################################################

# All settings defined in the paperless.conf.example can be used here. The
# Docker setup does not use the configuration file.
# A few commonly adjusted settings are provided below.

# This is required if you will be exposing Paperless-ngx on a public domain
# (if doing so please consider security measures such as reverse proxy)
#PAPERLESS_URL=https://paperless.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 Paperless Docker containers. If not specified, 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

docker-compose.yml

# docker-compose file for running paperless from the Docker Hub.
# This file contains everything paperless needs to run.
# Paperless supports amd64, arm and arm64 hardware.
#
# All compose files of paperless configure paperless in the following way:
#
# - Paperless is (re)started on system boot, if it was running before shutdown.
# - Docker volumes for storing data are managed by Docker.
# - Folders for importing and exporting files are created in the same directory
#   as this file and mounted to the correct folders inside the container.
# - Paperless listens on port 8000.
#
# In addition to that, this docker-compose file adds the following optional
# configurations:
#
# - Instead of SQLite (default), PostgreSQL is used as the database server.
#
# To install and update paperless with this file, do the following:
#
# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
#   and '.env' into a folder.
# - Run 'docker-compose pull'.
# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
# - Run 'docker-compose up -d'.
#
# For more extensive installation and update instructions, refer to the
# documentation.

#version: "3.4"

networks:
  svc1:
    name: svc1
    external: true

services:
  broker:
    image: docker.io/library/redis:6.0
    restart: unless-stopped
    volumes:
      - /srv/paperlessngx/redis-data:/data
    labels:
      # - traefik.http.routers.paperless.rule=Host(`paperless.lan`)
      # - traefik.http.services.paperless.loadbalancer.server.port=8000
      - tsdproxy.enable=true
      - tsdproxy.name=paperless

  db:
    image: docker.io/library/postgres:13
    restart: unless-stopped
    volumes:
      - /srv/paperlessngx/postgresql-data:/var/lib/postgresql/data
    environment:
      POSTGRES_DB: paperless
      POSTGRES_USER: paperless
      POSTGRES_PASSWORD: changeme

  webserver:
    image: ghcr.io/paperless-ngx/paperless-ngx:latest
    restart: unless-stopped
    depends_on:
      - db
      - broker
    ports:
      - 8000:8000
    healthcheck:
      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
      interval: 30s
      timeout: 10s
      retries: 5
    volumes:
      - /srv/paperlessngx/paperless-data:/usr/src/paperless/data
      - /srv/paperlessngx/paperless-media:/usr/src/paperless/media
      - /srv/paperlessngx/export:/usr/src/paperless/export
      - /srv/paperlessngx/consume:/usr/src/paperless/consume
    env_file: docker-compose.env
    environment:
      PAPERLESS_REDIS: redis://broker:6379
      PAPERLESS_DBHOST: db

mkdirs.sh

#!/usr/bin/env bash
#
# grep /srv docker-compose.yml  |awk -F'[ :]+' '{print $3}'
sudo mkdir -pv /srv/paperlessngx/redis-data
sudo mkdir -pv /srv/paperlessngx/postgresql-data
sudo mkdir -pv /srv/paperlessngx/paperless-data
sudo mkdir -pv /srv/paperlessngx/paperless-media
sudo mkdir -pv /srv/paperlessngx/export
sudo mkdir -pv /srv/paperlessngx/consume

sudo chown 1000 /srv/paperlessngx/export
sudo chown 1000 /srv/paperlessngx/consume