The worker restarts every task, so don't log again and again

paperless_text/parsers.py was moved to paperless/parsers/text.py as part of
the Phase 3 parser migration.  Update the signal-based get_parser() factory
to import from the new location and strip the legacy logging_group /
progress_callback kwargs that the new TextDocumentParser no longer accepts.

This shim keeps document consumption functional until Phase 4 replaces the
signal path with the new ParserRegistry.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.codecov.yml

@@ -1,6 +1,7 @@
+# https://docs.codecov.com/docs/codecovyml-reference#codecov
 codecov:
   require_ci_to_pass: true
-  # https://docs.codecov.com/docs/components
+# https://docs.codecov.com/docs/components
 component_management:
   individual_components:
     - component_id: backend
@@ -9,28 +10,76 @@ component_management:
     - component_id: frontend
       paths:
         - src-ui/**
-# https://docs.codecov.com/docs/pull-request-comments
+# https://docs.codecov.com/docs/flags#step-2-flag-management-in-yaml
-# codecov will only comment if coverage changes
+# https://docs.codecov.com/docs/carryforward-flags
+flags:
+  # Backend Python versions
+  backend-python-3.11:
+    paths:
+      - src/**
+    carryforward: true
+  backend-python-3.12:
+    paths:
+      - src/**
+    carryforward: true
+  backend-python-3.13:
+    paths:
+      - src/**
+    carryforward: true
+  backend-python-3.14:
+    paths:
+      - src/**
+    carryforward: true
+  # Frontend (shards merge into single flag)
+  frontend-node-24.x:
+    paths:
+      - src-ui/**
+    carryforward: true
 comment:
   layout: "header, diff, components, flags, files"
-  require_changes: true
-  # https://docs.codecov.com/docs/javascript-bundle-analysis
   require_bundle_changes: true
   bundle_change_threshold: "50Kb"
 coverage:
+  # https://docs.codecov.com/docs/commit-status
   status:
     project:
-      default:
+      backend:
+        flags:
+          - backend-python-3.11
+          - backend-python-3.12
+          - backend-python-3.13
+          - backend-python-3.14
+        paths:
+          - src/**
         # https://docs.codecov.com/docs/commit-status#threshold
         threshold: 1%
+        removed_code_behavior: adjust_base
+      frontend:
+        flags:
+          - frontend-node-24.x
+        paths:
+          - src-ui/**
+        threshold: 1%
+        removed_code_behavior: adjust_base
     patch:
-      default:
+      backend:
-        # For the changed lines only, target 100% covered, but
+        flags:
-        # allow as low as 75%
+          - backend-python-3.11
+          - backend-python-3.12
+          - backend-python-3.13
+          - backend-python-3.14
+        paths:
+          - src/**
+        target: 100%
+        threshold: 25%
+      frontend:
+        flags:
+          - frontend-node-24.x
+        paths:
+          - src-ui/**
         target: 100%
         threshold: 25%
 # https://docs.codecov.com/docs/javascript-bundle-analysis
 bundle_analysis:
-  # Fail if the bundle size increases by more than 1MB
   warning_threshold: "1MB"
   status: true

.codespellrc

@@ -1,3 +0,0 @@
-[codespell]
-write-changes = True
-ignore-words-list = criterias,afterall,valeu,ureue,equest,ure,assertIn

.devcontainer/Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker/dockerfile:1
 
-FROM --platform=$BUILDPLATFORM docker.io/node:20-bookworm-slim as main-app
+FROM --platform=$BUILDPLATFORM docker.io/node:24-trixie-slim as main-app
 
 ARG DEBIAN_FRONTEND=noninteractive
 
@@ -8,16 +8,17 @@ ARG DEBIAN_FRONTEND=noninteractive
 ARG TARGETARCH
 
 # Can be workflow provided, defaults set for manual building
-ARG JBIG2ENC_VERSION=0.29
+ARG JBIG2ENC_VERSION=0.30
-ARG QPDF_VERSION=11.9.0
-ARG GS_VERSION=10.03.1
 
 # Set Python environment variables
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
     # Ignore warning from Whitenoise
     PYTHONWARNINGS="ignore:::django.http.response:517" \
-    PNGX_CONTAINERIZED=1
+    PNGX_CONTAINERIZED=1 \
+    # https://docs.astral.sh/uv/reference/settings/#link-mode
+    UV_LINK_MODE=copy \
+    UV_CACHE_DIR=/cache/uv/
 
 #
 # Begin installation and configuration
@@ -63,8 +64,6 @@ ARG RUNTIME_PACKAGES="\
   libmagic1 \
   media-types \
   zlib1g \
-  # Barcode splitter
-  libzbar0 \
   poppler-utils \
   htop \
   sudo"
@@ -83,36 +82,15 @@ RUN set -eux \
     && apt-get update \
     && apt-get install --yes --quiet ${PYTHON_PACKAGES}
 
-COPY --from=ghcr.io/astral-sh/uv:0.6 /uv /bin/uv
+COPY --from=ghcr.io/astral-sh/uv:0.9.10 /uv /bin/uv
+
 
 RUN set -eux \
   && echo "Installing pre-built updates" \
-    && echo "Installing qpdf ${QPDF_VERSION}" \
-      && curl --fail --silent --show-error --location \
-        --output libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-      && curl --fail --silent --show-error --location \
-        --output qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-      && dpkg --install ./libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-      && dpkg --install ./qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-    && echo "Installing Ghostscript ${GS_VERSION}" \
-      && curl --fail --silent --show-error --location \
-          --output libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-      && curl --fail --silent --show-error --location \
-          --output ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-      && curl --fail --silent --show-error --location \
-          --output libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
-          https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
-        && dpkg --install ./libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
-        && dpkg --install ./libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        && dpkg --install ./ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
     && echo "Installing jbig2enc" \
       && curl --fail --silent --show-error --location \
         --output jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/jbig2enc-${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/jbig2enc-trixie-v${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
       && dpkg --install ./jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb
 
 # setup docker-specific things
@@ -126,9 +104,9 @@ COPY [ \
 
 RUN set -eux \
   && echo "Configuring ImageMagick" \
+    && mkdir -p /etc/ImageMagick-6 \
     && mv paperless-policy.xml /etc/ImageMagick-6/policy.xml
 
-COPY --from=ghcr.io/astral-sh/uv:0.6 /uv /bin/uv
 
 # Packages needed only for building a few quick Python
 # dependencies
@@ -142,7 +120,7 @@ ARG BUILD_PACKAGES="\
   pkg-config"
 
 # hadolint ignore=DL3042
-RUN --mount=type=cache,target=/root/.cache/uv,id=pip-cache \
+RUN --mount=type=cache,target=/cache/uv/,id=uv-cache \
   set -eux \
   && echo "Installing build system packages" \
     && apt-get update \

.devcontainer/README.md

@@ -47,39 +47,19 @@ To start the DevContainer:
 
 1. Open VSCode.
 2. Open the project folder.
-3. Open the command palette:
+3. Open the command palette and choose `Dev Containers: Rebuild and Reopen in Container`.
-   - **Windows/Linux**: `Ctrl+Shift+P`
-   - **Mac**: `Cmd+Shift+P`
-4. Type and select `Dev Containers: Rebuild and Reopen in Container`.
 
 VSCode will build and start the DevContainer environment.
 
 ### Step 2: Initial Setup
 
-Once the DevContainer is up and running, perform the following steps:
+Once the DevContainer is up and running, run the `Project Setup: Run all Init Tasks` task to initialize the project.
 
-1. **Compile Frontend Assets**:
+Alternatively, the Project Setup can be done with individual tasks:
 
-   - Open the command palette:
+1. **Compile Frontend Assets**: `Maintenance: Compile frontend for production`.
-     - **Windows/Linux**: `Ctrl+Shift+P`
+2. **Run Database Migrations**: `Maintenance: manage.py migrate`.
-     - **Mac**: `Cmd+Shift+P`
+3. **Create Superuser**: `Maintenance: manage.py createsuperuser`.
-   - Select `Tasks: Run Task`.
-   - Choose `Frontend Compile`.
-
-2. **Run Database Migrations**:
-
-   - Open the command palette:
-     - **Windows/Linux**: `Ctrl+Shift+P`
-     - **Mac**: `Cmd+Shift+P`
-   - Select `Tasks: Run Task`.
-   - Choose `Migrate Database`.
-
-3. **Create Superuser**:
-   - Open the command palette:
-     - **Windows/Linux**: `Ctrl+Shift+P`
-     - **Mac**: `Cmd+Shift+P`
-   - Select `Tasks: Run Task`.
-   - Choose `Create Superuser`.
 
 ### Debugging and Running Services
 
@@ -95,11 +75,8 @@ You can start and debug backend services either as debugging sessions via `launc
 
 #### Using Tasks
 
-1. Open the command palette:
+1. Open the command palette and select `Tasks: Run Task`.
-   - **Windows/Linux**: `Ctrl+Shift+P`
+2. Choose the desired task:
-   - **Mac**: `Cmd+Shift+P`
-2. Select `Tasks: Run Task`.
-3. Choose the desired task:
    - `Runserver`
    - `Document Consumer`
    - `Celery`
@@ -112,6 +89,18 @@ Additional tasks are available for common maintenance operations:
 - **Migrate Database**: To apply database migrations.
 - **Create Superuser**: To create an admin user for the application.
 
+## Committing from the Host Machine
+
+The DevContainer automatically installs Git pre-commit hooks during setup. However, these hooks are configured for use inside the container.
+
+If you want to commit changes from your host machine (outside the DevContainer), you need to set up prek on your host. This installs it as a standalone tool.
+
+```bash
+uv tool install prek && prek install
+```
+
+After this, you can commit either from inside the DevContainer or from your host machine.
+
 ## Let's Get Started!
 
 Follow the steps above to get your development environment up and running. Happy coding!

.devcontainer/devcontainer.json

@@ -3,26 +3,31 @@
     "dockerComposeFile": "docker-compose.devcontainer.sqlite-tika.yml",
     "service": "paperless-development",
     "workspaceFolder": "/usr/src/paperless/paperless-ngx",
-    "postCreateCommand": "/bin/bash -c 'uv sync --group dev && uv run pre-commit install'",
+    "forwardPorts": [4200, 8000],
+    "containerEnv": {
+        "UV_CACHE_DIR": "/usr/src/paperless/paperless-ngx/.uv-cache"
+    },
+    "postCreateCommand": "/bin/bash -c 'rm -rf .venv/.* && uv sync --group dev && uv run prek install'",
     "customizations": {
         "vscode": {
-          "extensions": [
+            "extensions": [
-            "mhutchie.git-graph",
+                "mhutchie.git-graph",
-            "ms-python.python",
+                "ms-python.python",
-            "ms-vscode.js-debug-nightly",
+                "ms-vscode.js-debug-nightly",
-            "eamodio.gitlens",
+                "eamodio.gitlens",
-            "yzhang.markdown-all-in-one"
+                "yzhang.markdown-all-in-one",
-          ],
+                "pnpm.pnpm"
-          "settings": {
+            ],
-            "python.defaultInterpreterPath": "/usr/src/paperless/paperless-ngx/.venv/bin/python",
+            "settings": {
-            "python.pythonPath": "/usr/src/paperless/paperless-ngx/.venv/bin/python",
+                "python.defaultInterpreterPath": "/usr/src/paperless/paperless-ngx/.venv/bin/python",
-            "python.terminal.activateEnvInCurrentTerminal": true,
+                "python.pythonPath": "/usr/src/paperless/paperless-ngx/.venv/bin/python",
-            "editor.formatOnPaste": false,
+                "python.terminal.activateEnvInCurrentTerminal": true,
-            "editor.formatOnSave": true,
+                "editor.formatOnPaste": false,
-            "editor.formatOnType": true,
+                "editor.formatOnSave": true,
-            "files.trimTrailingWhitespace": true
+                "editor.formatOnType": true,
-          }
+                "files.trimTrailingWhitespace": true
+            }
         }
-      },
+    },
-      "remoteUser": "paperless"
+    "remoteUser": "paperless"
-    }
+}

.devcontainer/docker-compose.devcontainer.sqlite-tika.yml

@@ -20,20 +20,17 @@
 #
 # This file is intended only to be used through VSCOde devcontainers. See README.md
 # in the folder .devcontainer.
-
-
 services:
   broker:
     image: docker.io/library/redis:7
     restart: unless-stopped
     volumes:
       - ./redisdata:/data
-
   # No ports need to be exposed; the VSCode DevContainer plugin manages them.
   paperless-development:
     image: paperless-ngx
     build:
-      context: ../    # Dockerfile cannot access files from parent directories if context is not set.
+      context: ../ # Dockerfile cannot access files from parent directories if context is not set.
       dockerfile: ./.devcontainer/Dockerfile
     restart: unless-stopped
     depends_on:
@@ -52,7 +49,6 @@ services:
       - ./data:/usr/src/paperless/paperless-ngx/data
       - ./media:/usr/src/paperless/paperless-ngx/media
       - ./consume:/usr/src/paperless/paperless-ngx/consume
-      - ~/.gitconfig:/usr/src/paperless/.gitconfig:ro
     environment:
       PAPERLESS_REDIS: redis://broker:6379
       PAPERLESS_TIKA_ENABLED: 1
@@ -60,25 +56,20 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
       PAPERLESS_STATICDIR: ./src/documents/static
       PAPERLESS_DEBUG: true
-
     # Overrides default command so things don't shut down after the process ends.
     command: /bin/sh -c "chown -R paperless:paperless /usr/src/paperless/paperless-ngx/src/documents/static/frontend && chown -R paperless:paperless /usr/src/paperless/paperless-ngx/.ruff_cache && while sleep 1000; do :; done"
-
   gotenberg:
     image: docker.io/gotenberg/gotenberg:8.17
     restart: unless-stopped
-
     # The Gotenberg Chromium route is used to convert .eml files. We do not
     # want to allow external content like tracking pixels or even JavaScript.
     command:
       - "gotenberg"
       - "--chromium-disable-javascript=true"
       - "--chromium-allow-list=file:///tmp/.*"
-
   tika:
     image: docker.io/apache/tika:latest
     restart: unless-stopped
-
 volumes:
   data:
   media:

.devcontainer/vscode/settings.json

@@ -1,11 +1,10 @@
 {
-    "python.testing.pytestArgs": [
+    "python.testing.pytestArgs": [],
-        "src"
-    ],
     "python.testing.unittestEnabled": false,
     "python.testing.pytestEnabled": true,
     "files.watcherExclude": {
         "**/.venv/**": true,
         "**/pytest_cache/**": true
-    }
+    },
+    "python.testing.cwd": "${workspaceFolder}/src"
 }

.devcontainer/vscode/tasks.json

@@ -33,7 +33,7 @@
 			"label": "Start: Frontend Angular",
 			"description": "Start the Frontend Angular Dev Server",
 			"type": "shell",
-			"command": "pnpm start",
+			"command": "pnpm exec ng serve --host 0.0.0.0",
 			"isBackground": true,
 			"options": {
 				"cwd": "${workspaceFolder}/src-ui"
@@ -116,9 +116,9 @@
 		},
 		{
 			"label": "Maintenance: Build Documentation",
-			"description": "Build the documentation with MkDocs",
+			"description": "Build the documentation with Zensical",
 			"type": "shell",
-			"command": "uv run mkdocs build --config-file mkdocs.yml && uv run mkdocs serve",
+			"command": "uv run zensical build && uv run zensical serve",
 			"group": "none",
 			"presentation": {
 				"echo": true,
@@ -156,7 +156,7 @@
 			"label": "Maintenance: recreate .venv",
 			"description": "Recreate the python virtual environment and install python dependencies",
 			"type": "shell",
-			"command": "rm -R -v .venv/* || uv install --dev",
+			"command": "rm -rf .venv && uv venv && uv sync --dev",
 			"group": "none",
 			"presentation": {
 				"echo": true,
@@ -174,12 +174,22 @@
 		{
 			"label": "Maintenance: Install Frontend Dependencies",
 			"description": "Install frontend (pnpm) dependencies",
-			"type": "pnpm",
+			"type": "shell",
-			"script": "install",
+			"command": "pnpm install",
-			"path": "src-ui",
 			"group": "clean",
 			"problemMatcher": [],
-			"detail": "install dependencies from package"
+			"options": {
+				"cwd": "${workspaceFolder}/src-ui"
+			},
+			"presentation": {
+				"echo": true,
+				"reveal": "always",
+				"focus": true,
+				"panel": "shared",
+				"showReuseMessage": false,
+				"clear": true,
+				"revealProblems": "onProblem"
+			}
 		},
 		{
 			"description": "Clean install frontend dependencies and build the frontend for production",

.dockerignore

@@ -28,3 +28,4 @@
 ./resources
 # Other stuff
 **/*.drawio.png
+.mypy_baseline

.editorconfig

@@ -11,6 +11,10 @@ end_of_line = lf
 charset = utf-8
 max_line_length = 79
 
+[*.sh]
+indent_style = tab
+indent_size = 1
+
 [{*.html,*.css,*.js}]
 max_line_length = off
 
@@ -35,3 +39,6 @@ max_line_length = off
 
 [Dockerfile*]
 indent_style = space
+
+[*.toml]
+indent_style = space

.github/DISCUSSION_TEMPLATE/support.yml

@@ -0,0 +1,55 @@
+title: "[Support] "
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: What's your question or issue?
+      description: Provide a clear and concise description of what you're trying to do, and what's going wrong.
+      placeholder: |
+        I'm trying to...
+
+        [Include screenshots if helpful]
+    validations:
+      required: true
+  - type: textarea
+    id: steps
+    attributes:
+      label: What have you tried?
+      description: Describe any steps you've already taken to troubleshoot or solve the issue.
+      placeholder: |
+        - I checked the logs and saw...
+        - I followed the install guide and tried...
+  - type: input
+    id: version
+    attributes:
+      label: Paperless-ngx version
+      placeholder: e.g. 1.14.0
+    validations:
+      required: true
+  - type: input
+    id: host-os
+    attributes:
+      label: Host OS
+      description: Include architecture if relevant.
+      placeholder: e.g. Ubuntu 22.04 / Raspberry Pi arm64
+  - type: dropdown
+    id: install-method
+    attributes:
+      label: Installation method
+      options:
+        - Docker - official image
+        - Docker - linuxserver.io image
+        - Bare metal
+        - Other (please describe above)
+  - type: textarea
+    id: system-status
+    attributes:
+      label: System status
+      description: If available, copy & paste the system status output from Settings > System Status > Copy
+      render: json
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant logs or output
+      description: If you have logs, errors that might help, paste it here. For example other containers or services (database, redis, etc).
+      render: bash

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -6,8 +6,8 @@ body:
   - type: markdown
     attributes:
       value: |
-        ### ⚠️ Please remember: issues are for *bugs*
+        ### ⚠️ Please remember: issues are for *bugs* only! ⚠️
-        That is, something you believe affects every single user of Paperless-ngx, not just you. If you're not sure, start with one of the other options below.
+        That is, something you believe affects every single user of Paperless-ngx (and the demo, for example), not just you. If you are not sure, start with one of the other options below.
 
         Also, note that **Paperless-ngx does not perform OCR or archive file creation itself**, those are handled by other tools. Problems with OCR or archive versions of specific files should likely be raised 'upstream', see https://github.com/ocrmypdf/OCRmyPDF/issues or https://github.com/tesseract-ocr/tesseract/issues
   - type: markdown
@@ -59,6 +59,12 @@ body:
       label: Browser logs
       description: Logs from the web browser related to your issue, if needed
       render: bash
+  - type: textarea
+    id: logs_services
+    attributes:
+      label: Services logs
+      description: Logs from other services (or containers) related to your issue, if needed. For example, the database or redis logs.
+      render: bash
   - type: input
     id: version
     attributes:

.github/PULL_REQUEST_TEMPLATE.md

@@ -35,8 +35,8 @@ NOTE: PRs that do not address the following will not be merged, please do not sk
 
 - [ ] I have read & agree with the [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/main/CONTRIBUTING.md).
 - [ ] If applicable, I have included testing coverage for new code in this PR, for [backend](https://docs.paperless-ngx.com/development/#testing) and / or [front-end](https://docs.paperless-ngx.com/development/#testing-and-code-style) changes.
-- [ ] If applicable, I have tested my code for new features & regressions on both mobile & desktop devices, using the latest version of major browsers.
+- [ ] If applicable, I have tested my code for breaking changes & regressions on both mobile & desktop devices, using the latest version of major browsers.
 - [ ] If applicable, I have checked that all tests pass, see [documentation](https://docs.paperless-ngx.com/development/#back-end-development).
-- [ ] I have run all `pre-commit` hooks, see [documentation](https://docs.paperless-ngx.com/development/#code-formatting-with-pre-commit-hooks).
+- [ ] I have run all Git `pre-commit` hooks, see [documentation](https://docs.paperless-ngx.com/development/#code-formatting-with-pre-commit-hooks).
 - [ ] I have made corresponding changes to the documentation as needed.
-- [ ] I have checked my modifications for any breaking changes.
+- [ ] In the description of the PR above I have disclosed the use of AI tools in the coding of this PR.

.github/dependabot.yml

@@ -1,11 +1,9 @@
 # Please see the documentation for all configuration options:
 # https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
-
 version: 2
 # Required for uv support for now
 enable-beta-ecosystems: true
 updates:
-
   # Enable version updates for pnpm
   - package-ecosystem: "npm"
     target-branch: "dev"
@@ -17,9 +15,6 @@ updates:
     labels:
       - "frontend"
       - "dependencies"
-    # Add reviewers
-    reviewers:
-      - "paperless-ngx/frontend"
     groups:
       frontend-angular-dependencies:
         patterns:
@@ -35,7 +30,6 @@ updates:
         patterns:
           - "@typescript-eslint*"
           - "eslint"
-
   # Enable version updates for Python
   - package-ecosystem: "uv"
     target-branch: "dev"
@@ -46,31 +40,56 @@ updates:
     labels:
       - "backend"
       - "dependencies"
-    # Add reviewers
-    reviewers:
-      - "paperless-ngx/backend"
     groups:
+      # Development & CI/CD Tooling
       development:
         patterns:
           - "*pytest*"
           - "ruff"
-          - "mkdocs-material"
+          - "zensical"
-          - "pre-commit*"
+          - "prek*"
-      django:
+      # Django & DRF Ecosystem
+      django-ecosystem:
         patterns:
           - "*django*"
-      major-versions:
+          - "drf-*"
+          - "djangorestframework"
+          - "whitenoise"
+          - "bleach"
+          - "jinja2"
+      # Async, Task Queuing & Caching
+      async-tasks:
+        patterns:
+          - "celery*"
+          - "channels*"
+          - "flower"
+          - "redis"
+      # Document, PDF, and OCR Processing
+      document-processing:
+        patterns:
+          - "ocrmypdf"
+          - "pdf2image"
+          - "zxing-cpp"
+          - "tika-client"
+          - "gotenberg-client"
+          - "python-magic"
+          - "python-gnupg"
+      # Data, NLP, and Search
+      data-nlp-search:
+        patterns:
+          - "nltk"
+          - "scikit-learn"
+          - "langdetect"
+          - "rapidfuzz"
+          - "whoosh-reloaded"
+      # Utilities (Patch Updates)
+      utilities-patch:
         update-types:
-          - "major"
+          - "patch"
-      small-changes:
+      # Utilities (Minor Updates)
+      utilities-minor:
         update-types:
           - "minor"
-          - "patch"
-      pre-built:
-        patterns:
-          - psycopg*
-          - zxing-cpp
-
   # Enable updates for GitHub Actions
   - package-ecosystem: "github-actions"
     target-branch: "dev"
@@ -81,41 +100,32 @@ updates:
     labels:
       - "ci-cd"
       - "dependencies"
-    # Add reviewers
-    reviewers:
-      - "paperless-ngx/ci-cd"
     groups:
       actions:
         update-types:
           - "major"
           - "minor"
           - "patch"
-
   # Update Dockerfile in root directory
   - package-ecosystem: "docker"
-    directory: "/"
+    directories:
+      - "/"
+      - "/.devcontainer/"
     schedule:
       interval: "weekly"
     open-pull-requests-limit: 5
-    reviewers:
-      - "paperless-ngx/ci-cd"
     labels:
-      - "ci-cd"
       - "dependencies"
     commit-message:
       prefix: "docker"
       include: "scope"
-
   # Update Docker Compose files in docker/compose directory
   - package-ecosystem: "docker-compose"
     directory: "/docker/compose/"
     schedule:
       interval: "weekly"
     open-pull-requests-limit: 5
-    reviewers:
-      - "paperless-ngx/ci-cd"
     labels:
-      - "ci-cd"
       - "dependencies"
     commit-message:
       prefix: "docker-compose"

.github/labeler.yml

@@ -0,0 +1,26 @@
+backend:
+  - changed-files:
+      - any-glob-to-any-file:
+          - 'src/**'
+          - 'pyproject.toml'
+          - 'uv.lock'
+          - 'requirements.txt'
+frontend:
+  - changed-files:
+      - any-glob-to-any-file:
+          - 'src-ui/**'
+documentation:
+  - changed-files:
+      - any-glob-to-any-file:
+          - 'docs/**'
+ci-cd:
+  - changed-files:
+      - any-glob-to-any-file:
+          - '.github/**'
+# pr types
+bug:
+  - head-branch:
+      - ['^fix']
+enhancement:
+  - head-branch:
+      - ['^feature']

.github/release-drafter.yml

@@ -1,15 +1,3 @@
-autolabeler:
-  - label: "bug"
-    branch:
-      - '/^fix/'
-    title:
-      - "/^fix/i"
-      - "/^Bugfix/i"
-  - label: "enhancement"
-    branch:
-      - '/^feature/'
-    title:
-      - "/^feature/i"
 categories:
   - title: 'Breaking Changes'
     labels:
@@ -17,7 +5,7 @@ categories:
   - title: 'Notable Changes'
     labels:
       - 'notable'
-  - title: 'Features'
+  - title: 'Features / Enhancements'
     labels:
       - 'enhancement'
   - title: 'Bug Fixes'
@@ -56,6 +44,7 @@ include-labels:
   - 'notable'
 exclude-labels:
   - 'skip-changelog'
+filter-by-commitish: true
 category-template: '### $TITLE'
 change-template: '- $TITLE @$AUTHOR ([#$NUMBER]($URL))'
 change-title-escapes: '\<*_&#@'

.github/workflows/ci-backend.yml

@@ -0,0 +1,214 @@
+name: Backend Tests
+on:
+  push:
+    branches-ignore:
+      - 'translations**'
+  pull_request:
+    branches-ignore:
+      - 'translations**'
+  workflow_dispatch:
+concurrency:
+  group: backend-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+env:
+  DEFAULT_UV_VERSION: "0.10.x"
+  NLTK_DATA: "/usr/share/nltk_data"
+jobs:
+  changes:
+    name: Detect Backend Changes
+    runs-on: ubuntu-slim
+    outputs:
+      backend_changed: ${{ steps.force.outputs.run_all == 'true' || steps.filter.outputs.backend == 'true' }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+        with:
+          fetch-depth: 0
+      - name: Decide run mode
+        id: force
+        run: |
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            echo "run_all=true" >> "$GITHUB_OUTPUT"
+          elif [[ "${{ github.event_name }}" == "push" && ( "${{ github.ref_name }}" == "main" || "${{ github.ref_name }}" == "dev" ) ]]; then
+            echo "run_all=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "run_all=false" >> "$GITHUB_OUTPUT"
+          fi
+      - name: Set diff range
+        id: range
+        if: steps.force.outputs.run_all != 'true'
+        run: |
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "base=${{ github.event.pull_request.base.sha }}" >> "$GITHUB_OUTPUT"
+          elif [[ "${{ github.event.created }}" == "true" ]]; then
+            echo "base=${{ github.event.repository.default_branch }}" >> "$GITHUB_OUTPUT"
+          else
+            echo "base=${{ github.event.before }}" >> "$GITHUB_OUTPUT"
+          fi
+          echo "ref=${{ github.sha }}" >> "$GITHUB_OUTPUT"
+      - name: Detect changes
+        id: filter
+        if: steps.force.outputs.run_all != 'true'
+        uses: dorny/paths-filter@v3.0.2
+        with:
+          base: ${{ steps.range.outputs.base }}
+          ref: ${{ steps.range.outputs.ref }}
+          filters: |
+            backend:
+              - 'src/**'
+              - 'pyproject.toml'
+              - 'uv.lock'
+              - 'docker/compose/docker-compose.ci-test.yml'
+              - '.github/workflows/ci-backend.yml'
+  test:
+    needs: changes
+    if: needs.changes.outputs.backend_changed == 'true'
+    name: "Python ${{ matrix.python-version }}"
+    runs-on: ubuntu-24.04
+    strategy:
+      matrix:
+        python-version: ['3.11', '3.12', '3.13', '3.14']
+      fail-fast: false
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Start containers
+        run: |
+          docker compose --file docker/compose/docker-compose.ci-test.yml pull --quiet
+          docker compose --file docker/compose/docker-compose.ci-test.yml up --detach
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6.2.0
+        with:
+          python-version: "${{ matrix.python-version }}"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7.3.1
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ steps.setup-python.outputs.python-version }}
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends \
+            unpaper tesseract-ocr imagemagick ghostscript poppler-utils
+      - name: Configure ImageMagick
+        run: |
+          sudo cp docker/rootfs/etc/ImageMagick-6/paperless-policy.xml /etc/ImageMagick-6/policy.xml
+      - name: Install Python dependencies
+        run: |
+          uv sync \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --group testing \
+            --frozen
+      - name: List installed Python dependencies
+        run: |
+          uv pip list
+      - name: Install NLTK data
+        run: |
+          uv run python -m nltk.downloader punkt punkt_tab snowball_data stopwords -d ${{ env.NLTK_DATA }}
+      - name: Run tests
+        env:
+          NLTK_DATA: ${{ env.NLTK_DATA }}
+          PAPERLESS_CI_TEST: 1
+        run: |
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            --frozen \
+            pytest
+      - name: Upload test results to Codecov
+        if: always()
+        uses: codecov/codecov-action@v5.5.2
+        with:
+          flags: backend-python-${{ matrix.python-version }}
+          files: junit.xml
+          report_type: test_results
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5.5.2
+        with:
+          flags: backend-python-${{ matrix.python-version }}
+          files: coverage.xml
+          report_type: coverage
+      - name: Stop containers
+        if: always()
+        run: |
+          docker compose --file docker/compose/docker-compose.ci-test.yml logs
+          docker compose --file docker/compose/docker-compose.ci-test.yml down
+  typing:
+    needs: changes
+    if: needs.changes.outputs.backend_changed == 'true'
+    name: Check project typing
+    runs-on: ubuntu-24.04
+    env:
+      DEFAULT_PYTHON: "3.12"
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6.2.0
+        with:
+          python-version: "${{ env.DEFAULT_PYTHON }}"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7.3.1
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ steps.setup-python.outputs.python-version }}
+      - name: Install Python dependencies
+        run: |
+          uv sync \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --group testing \
+            --group typing \
+            --frozen
+      - name: List installed Python dependencies
+        run: |
+          uv pip list
+      - name: Check typing (pyrefly)
+        continue-on-error: true
+        run: |
+          uv run pyrefly \
+            check \
+            src/
+      - name: Cache Mypy
+        uses: actions/cache@v5.0.3
+        with:
+          path: .mypy_cache
+          # Keyed by OS, Python version, and dependency hashes
+          key: ${{ runner.os }}-mypy-py${{ env.DEFAULT_PYTHON }}-${{ hashFiles('pyproject.toml', 'uv.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-mypy-py${{ env.DEFAULT_PYTHON }}-
+            ${{ runner.os }}-mypy-
+      - name: Check typing (mypy)
+        continue-on-error: true
+        run: |
+          uv run mypy \
+            --show-error-codes \
+            --warn-unused-configs \
+            src/ | uv run mypy-baseline filter
+  gate:
+    name: Backend CI Gate
+    needs: [changes, test, typing]
+    if: always()
+    runs-on: ubuntu-slim
+    steps:
+      - name: Check gate
+        run: |
+          if [[ "${{ needs.changes.outputs.backend_changed }}" != "true" ]]; then
+            echo "No backend-relevant changes detected."
+            exit 0
+          fi
+
+          if [[ "${{ needs.test.result }}" != "success" ]]; then
+            echo "::error::Backend test job result: ${{ needs.test.result }}"
+            exit 1
+          fi
+
+          if [[ "${{ needs.typing.result }}" != "success" ]]; then
+            echo "::error::Backend typing job result: ${{ needs.typing.result }}"
+            exit 1
+          fi
+
+          echo "Backend checks passed."

.github/workflows/ci-docker.yml

@@ -0,0 +1,254 @@
+name: Docker Build
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+      - 'v[0-9]+.[0-9]+.[0-9]+-beta.rc[0-9]+'
+    branches:
+      - dev
+      - beta
+  pull_request:
+    branches:
+      - dev
+      - main
+  workflow_dispatch:
+concurrency:
+  group: docker-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+env:
+  REGISTRY: ghcr.io
+jobs:
+  build-arch:
+    name: Build ${{ matrix.arch }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: ubuntu-24.04
+            arch: amd64
+            platform: linux/amd64
+          - runner: ubuntu-24.04-arm
+            arch: arm64
+            platform: linux/arm64
+    runs-on: ${{ matrix.runner }}
+    permissions:
+      contents: read
+      packages: write
+    outputs:
+      should-push: ${{ steps.check-push.outputs.should-push }}
+      push-external: ${{ steps.check-push.outputs.push-external }}
+      repository: ${{ steps.repo.outputs.name }}
+      ref-name: ${{ steps.ref.outputs.name }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Determine ref name
+        id: ref
+        run: |
+          ref_name="${GITHUB_HEAD_REF:-$GITHUB_REF_NAME}"
+          # Sanitize by replacing / with - for use in tags and cache keys
+          sanitized_ref="${ref_name//\//-}"
+
+          echo "ref_name=${ref_name}"
+          echo "sanitized_ref=${sanitized_ref}"
+
+          echo "name=${sanitized_ref}" >> $GITHUB_OUTPUT
+      - name: Check push permissions
+        id: check-push
+        env:
+          REF_NAME: ${{ steps.ref.outputs.name }}
+        run: |
+          # should-push: Should we push to GHCR?
+          # True for:
+          #   1. Pushes (tags/dev/beta) - filtered via the workflow triggers
+          #   2. Manual dispatch - always push to GHCR
+          #   3. Internal PRs where the branch name starts with 'feature-' or 'fix-'
+
+          should_push="false"
+          if [[ "${{ github.event_name }}" == "push" ]]; then
+            should_push="true"
+          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            should_push="true"
+          elif [[ "${{ github.event_name }}" == "pull_request" && "${{ github.event.pull_request.head.repo.full_name }}" == "${{ github.repository }}" ]]; then
+            if [[ "${REF_NAME}" == feature-* || "${REF_NAME}" == fix-* ]]; then
+              should_push="true"
+            fi
+          fi
+
+          echo "should-push=${should_push}"
+          echo "should-push=${should_push}" >> $GITHUB_OUTPUT
+
+          # push-external: Should we also push to Docker Hub and Quay.io?
+          # Only for main repo on dev/beta branches or version tags
+          push_external="false"
+          if [[ "${should_push}" == "true" && "${{ github.repository_owner }}" == "paperless-ngx" ]]; then
+            case "${REF_NAME}" in
+              dev|beta)
+                push_external="true"
+                ;;
+            esac
+            case "${{ github.ref }}" in
+              refs/tags/v*|*beta.rc*)
+                push_external="true"
+                ;;
+            esac
+          fi
+          echo "push-external=${push_external}"
+          echo "push-external=${push_external}" >> $GITHUB_OUTPUT
+      - name: Set repository name
+        id: repo
+        run: |
+          repo_name="${{ github.repository }}"
+          repo_name="${repo_name,,}"
+
+          echo "repository=${repo_name}"
+          echo "name=${repo_name}" >> $GITHUB_OUTPUT
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3.12.0
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3.7.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Maximize space
+        run: |
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /opt/ghc
+          sudo rm -rf /usr/local/share/boost
+          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+      - name: Docker metadata
+        id: docker-meta
+        uses: docker/metadata-action@v5.10.0
+        with:
+          images: |
+            ${{ env.REGISTRY }}/${{ steps.repo.outputs.name }}
+          tags: |
+            type=ref,event=branch
+            type=raw,value=${{ steps.ref.outputs.name }},enable=${{ github.event_name == 'pull_request' }}
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+      - name: Build and push by digest
+        id: build
+        uses: docker/build-push-action@v6.19.2
+        with:
+          context: .
+          file: ./Dockerfile
+          platforms: ${{ matrix.platform }}
+          labels: ${{ steps.docker-meta.outputs.labels }}
+          build-args: |
+            PNGX_TAG_VERSION=${{ steps.docker-meta.outputs.version }}
+          outputs: type=image,name=${{ env.REGISTRY }}/${{ steps.repo.outputs.name }},push-by-digest=true,name-canonical=true,push=${{ steps.check-push.outputs.should-push }}
+          cache-from: |
+            type=registry,ref=${{ env.REGISTRY }}/${{ steps.repo.outputs.name }}/cache/app:${{ steps.ref.outputs.name }}-${{ matrix.arch }}
+            type=registry,ref=${{ env.REGISTRY }}/${{ steps.repo.outputs.name }}/cache/app:dev-${{ matrix.arch }}
+          cache-to: ${{ steps.check-push.outputs.should-push == 'true' && format('type=registry,mode=max,ref={0}/{1}/cache/app:{2}-{3}', env.REGISTRY, steps.repo.outputs.name, steps.ref.outputs.name, matrix.arch) || '' }}
+      - name: Export digest
+        if: steps.check-push.outputs.should-push == 'true'
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          echo "digest=${digest}"
+          echo "${digest}" > "/tmp/digests/digest-${{ matrix.arch }}.txt"
+      - name: Upload digest
+        if: steps.check-push.outputs.should-push == 'true'
+        uses: actions/upload-artifact@v7.0.0
+        with:
+          name: digests-${{ matrix.arch }}
+          path: /tmp/digests/digest-${{ matrix.arch }}.txt
+          if-no-files-found: error
+          retention-days: 1
+          archive: false
+  merge-and-push:
+    name: Merge and Push Manifest
+    runs-on: ubuntu-24.04
+    needs: build-arch
+    if: needs.build-arch.outputs.should-push == 'true'
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v8.0.0
+        with:
+          path: /tmp/digests
+          pattern: digest-*.txt
+          merge-multiple: true
+      - name: List digests
+        run: |
+          echo "Downloaded digests:"
+          ls -la /tmp/digests/
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3.12.0
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3.7.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Login to Docker Hub
+        if: needs.build-arch.outputs.push-external == 'true'
+        uses: docker/login-action@v3.7.0
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Login to Quay.io
+        if: needs.build-arch.outputs.push-external == 'true'
+        uses: docker/login-action@v3.7.0
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_USERNAME }}
+          password: ${{ secrets.QUAY_ROBOT_TOKEN }}
+      - name: Docker metadata
+        id: docker-meta
+        uses: docker/metadata-action@v5.10.0
+        with:
+          images: |
+            ${{ env.REGISTRY }}/${{ needs.build-arch.outputs.repository }}
+          tags: |
+            type=ref,event=branch
+            type=raw,value=${{ needs.build-arch.outputs.ref-name }},enable=${{ github.event_name == 'pull_request' }}
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        env:
+          REPOSITORY: ${{ needs.build-arch.outputs.repository }}
+        run: |
+          tags=$(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "${DOCKER_METADATA_OUTPUT_JSON}")
+
+          digests=""
+          for digest_file in digest-*.txt; do
+            digest=$(cat "${digest_file}")
+            digests+="${{ env.REGISTRY }}/${REPOSITORY}@${digest} "
+          done
+
+          echo "Creating manifest with tags: ${tags}"
+          echo "From digests: ${digests}"
+
+          docker buildx imagetools create ${tags} ${digests}
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
+      - name: Copy to Docker Hub
+        if: needs.build-arch.outputs.push-external == 'true'
+        env:
+          TAGS: ${{ steps.docker-meta.outputs.tags }}
+          GHCR_REPO: ${{ env.REGISTRY }}/${{ needs.build-arch.outputs.repository }}
+        run: |
+          for tag in ${TAGS}; do
+            dockerhub_tag="${tag/${GHCR_REPO}/docker.io/paperlessngx/paperless-ngx}"
+            echo "Copying ${tag} to ${dockerhub_tag}"
+            skopeo copy --all "docker://${tag}" "docker://${dockerhub_tag}"
+          done
+      - name: Copy to Quay.io
+        if: needs.build-arch.outputs.push-external == 'true'
+        env:
+          TAGS: ${{ steps.docker-meta.outputs.tags }}
+          GHCR_REPO: ${{ env.REGISTRY }}/${{ needs.build-arch.outputs.repository }}
+        run: |
+          for tag in ${TAGS}; do
+            quay_tag="${tag/${GHCR_REPO}/quay.io/paperlessngx/paperless-ngx}"
+            echo "Copying ${tag} to ${quay_tag}"
+            skopeo copy --all "docker://${tag}" "docker://${quay_tag}"
+          done

.github/workflows/ci-docs.yml

@@ -0,0 +1,132 @@
+name: Documentation
+on:
+  push:
+    branches-ignore:
+      - 'translations**'
+  pull_request:
+  workflow_dispatch:
+concurrency:
+  group: docs-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+env:
+  DEFAULT_UV_VERSION: "0.10.x"
+  DEFAULT_PYTHON_VERSION: "3.12"
+jobs:
+  changes:
+    name: Detect Docs Changes
+    runs-on: ubuntu-slim
+    outputs:
+      docs_changed: ${{ steps.force.outputs.run_all == 'true' || steps.filter.outputs.docs == 'true' }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+        with:
+          fetch-depth: 0
+      - name: Decide run mode
+        id: force
+        run: |
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            echo "run_all=true" >> "$GITHUB_OUTPUT"
+          elif [[ "${{ github.event_name }}" == "push" && ( "${{ github.ref_name }}" == "main" || "${{ github.ref_name }}" == "dev" ) ]]; then
+            echo "run_all=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "run_all=false" >> "$GITHUB_OUTPUT"
+          fi
+      - name: Set diff range
+        id: range
+        if: steps.force.outputs.run_all != 'true'
+        run: |
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "base=${{ github.event.pull_request.base.sha }}" >> "$GITHUB_OUTPUT"
+          elif [[ "${{ github.event.created }}" == "true" ]]; then
+            echo "base=${{ github.event.repository.default_branch }}" >> "$GITHUB_OUTPUT"
+          else
+            echo "base=${{ github.event.before }}" >> "$GITHUB_OUTPUT"
+          fi
+          echo "ref=${{ github.sha }}" >> "$GITHUB_OUTPUT"
+      - name: Detect changes
+        id: filter
+        if: steps.force.outputs.run_all != 'true'
+        uses: dorny/paths-filter@v3.0.2
+        with:
+          base: ${{ steps.range.outputs.base }}
+          ref: ${{ steps.range.outputs.ref }}
+          filters: |
+            docs:
+              - 'docs/**'
+              - 'zensical.toml'
+              - 'pyproject.toml'
+              - 'uv.lock'
+              - '.github/workflows/ci-docs.yml'
+  build:
+    needs: changes
+    if: needs.changes.outputs.docs_changed == 'true'
+    name: Build Documentation
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/configure-pages@v5.0.0
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6.2.0
+        with:
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7.3.1
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install Python dependencies
+        run: |
+          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
+      - name: Build documentation
+        run: |
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            --frozen \
+            zensical build --clean
+      - name: Upload GitHub Pages artifact
+        uses: actions/upload-pages-artifact@v4.0.0
+        with:
+          path: site
+          name: github-pages-${{ github.run_id }}-${{ github.run_attempt }}
+  deploy:
+    name: Deploy Documentation
+    needs: [changes, build]
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main' && needs.changes.outputs.docs_changed == 'true'
+    runs-on: ubuntu-24.04
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy GitHub Pages
+        uses: actions/deploy-pages@v4.0.5
+        id: deployment
+        with:
+          artifact_name: github-pages-${{ github.run_id }}-${{ github.run_attempt }}
+  gate:
+    name: Docs CI Gate
+    needs: [changes, build]
+    if: always()
+    runs-on: ubuntu-slim
+    steps:
+      - name: Check gate
+        run: |
+          if [[ "${{ needs.changes.outputs.docs_changed }}" != "true" ]]; then
+            echo "No docs-relevant changes detected."
+            exit 0
+          fi
+
+          if [[ "${{ needs.build.result }}" != "success" ]]; then
+            echo "::error::Docs build job result: ${{ needs.build.result }}"
+            exit 1
+          fi
+
+          echo "Docs checks passed."

.github/workflows/ci-frontend.yml

@@ -0,0 +1,273 @@
+name: Frontend Tests
+on:
+  push:
+    branches-ignore:
+      - 'translations**'
+  pull_request:
+    branches-ignore:
+      - 'translations**'
+  workflow_dispatch:
+concurrency:
+  group: frontend-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+jobs:
+  changes:
+    name: Detect Frontend Changes
+    runs-on: ubuntu-slim
+    outputs:
+      frontend_changed: ${{ steps.force.outputs.run_all == 'true' || steps.filter.outputs.frontend == 'true' }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+        with:
+          fetch-depth: 0
+      - name: Decide run mode
+        id: force
+        run: |
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            echo "run_all=true" >> "$GITHUB_OUTPUT"
+          elif [[ "${{ github.event_name }}" == "push" && ( "${{ github.ref_name }}" == "main" || "${{ github.ref_name }}" == "dev" ) ]]; then
+            echo "run_all=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "run_all=false" >> "$GITHUB_OUTPUT"
+          fi
+      - name: Set diff range
+        id: range
+        if: steps.force.outputs.run_all != 'true'
+        run: |
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "base=${{ github.event.pull_request.base.sha }}" >> "$GITHUB_OUTPUT"
+          elif [[ "${{ github.event.created }}" == "true" ]]; then
+            echo "base=${{ github.event.repository.default_branch }}" >> "$GITHUB_OUTPUT"
+          else
+            echo "base=${{ github.event.before }}" >> "$GITHUB_OUTPUT"
+          fi
+          echo "ref=${{ github.sha }}" >> "$GITHUB_OUTPUT"
+      - name: Detect changes
+        id: filter
+        if: steps.force.outputs.run_all != 'true'
+        uses: dorny/paths-filter@v3.0.2
+        with:
+          base: ${{ steps.range.outputs.base }}
+          ref: ${{ steps.range.outputs.ref }}
+          filters: |
+            frontend:
+              - 'src-ui/**'
+              - '.github/workflows/ci-frontend.yml'
+  install-dependencies:
+    needs: changes
+    if: needs.changes.outputs.frontend_changed == 'true'
+    name: Install Dependencies
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4.2.0
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6.2.0
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        id: cache-frontend-deps
+        uses: actions/cache@v5.0.3
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Install dependencies
+        run: cd src-ui && pnpm install
+  lint:
+    name: Lint
+    needs: [changes, install-dependencies]
+    if: needs.changes.outputs.frontend_changed == 'true'
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4.2.0
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6.2.0
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        uses: actions/cache@v5.0.3
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Re-link Angular CLI
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Run lint
+        run: cd src-ui && pnpm run lint
+  unit-tests:
+    name: "Unit Tests (${{ matrix.shard-index }}/${{ matrix.shard-count }})"
+    needs: [changes, install-dependencies]
+    if: needs.changes.outputs.frontend_changed == 'true'
+    runs-on: ubuntu-24.04
+    strategy:
+      fail-fast: false
+      matrix:
+        node-version: [24.x]
+        shard-index: [1, 2, 3, 4]
+        shard-count: [4]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4.2.0
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6.2.0
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        uses: actions/cache@v5.0.3
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Re-link Angular CLI
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Run Jest unit tests
+        run: cd src-ui && pnpm run test --max-workers=2 --shard=${{ matrix.shard-index }}/${{ matrix.shard-count }}
+      - name: Upload test results to Codecov
+        if: always()
+        uses: codecov/codecov-action@v5.5.2
+        with:
+          flags: frontend-node-${{ matrix.node-version }}
+          directory: src-ui/
+          report_type: test_results
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5.5.2
+        with:
+          flags: frontend-node-${{ matrix.node-version }}
+          directory: src-ui/coverage/
+  e2e-tests:
+    name: "E2E Tests (${{ matrix.shard-index }}/${{ matrix.shard-count }})"
+    needs: [changes, install-dependencies]
+    if: needs.changes.outputs.frontend_changed == 'true'
+    runs-on: ubuntu-24.04
+    container: mcr.microsoft.com/playwright:v1.58.2-noble
+    env:
+      PLAYWRIGHT_BROWSERS_PATH: /ms-playwright
+      PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD: 1
+    strategy:
+      fail-fast: false
+      matrix:
+        node-version: [24.x]
+        shard-index: [1, 2]
+        shard-count: [2]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4.2.0
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6.2.0
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        uses: actions/cache@v5.0.3
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Re-link Angular CLI
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Install dependencies
+        run: cd src-ui && pnpm install --no-frozen-lockfile
+      - name: Run Playwright E2E tests
+        run: cd src-ui && pnpm exec playwright test --shard ${{ matrix.shard-index }}/${{ matrix.shard-count }}
+  bundle-analysis:
+    name: Bundle Analysis
+    needs: [changes, unit-tests, e2e-tests]
+    if: needs.changes.outputs.frontend_changed == 'true'
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+        with:
+          fetch-depth: 2
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4.2.0
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6.2.0
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        uses: actions/cache@v5.0.3
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Re-link Angular CLI
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Build and analyze
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        run: cd src-ui && pnpm run build --configuration=production
+  gate:
+    name: Frontend CI Gate
+    needs: [changes, install-dependencies, lint, unit-tests, e2e-tests, bundle-analysis]
+    if: always()
+    runs-on: ubuntu-slim
+    steps:
+      - name: Check gate
+        run: |
+          if [[ "${{ needs.changes.outputs.frontend_changed }}" != "true" ]]; then
+            echo "No frontend-relevant changes detected."
+            exit 0
+          fi
+
+          if [[ "${{ needs['install-dependencies'].result }}" != "success" ]]; then
+            echo "::error::Frontend install job result: ${{ needs['install-dependencies'].result }}"
+            exit 1
+          fi
+
+          if [[ "${{ needs.lint.result }}" != "success" ]]; then
+            echo "::error::Frontend lint job result: ${{ needs.lint.result }}"
+            exit 1
+          fi
+
+          if [[ "${{ needs['unit-tests'].result }}" != "success" ]]; then
+            echo "::error::Frontend unit-tests job result: ${{ needs['unit-tests'].result }}"
+            exit 1
+          fi
+
+          if [[ "${{ needs['e2e-tests'].result }}" != "success" ]]; then
+            echo "::error::Frontend e2e-tests job result: ${{ needs['e2e-tests'].result }}"
+            exit 1
+          fi
+
+          if [[ "${{ needs['bundle-analysis'].result }}" != "success" ]]; then
+            echo "::error::Frontend bundle-analysis job result: ${{ needs['bundle-analysis'].result }}"
+            exit 1
+          fi
+
+          echo "Frontend checks passed."

.github/workflows/ci-lint.yml

@@ -0,0 +1,24 @@
+name: Lint
+on:
+  push:
+    branches-ignore:
+      - 'translations**'
+  pull_request:
+    branches-ignore:
+      - 'translations**'
+concurrency:
+  group: lint-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+jobs:
+  lint:
+    name: Linting via prek
+    runs-on: ubuntu-slim
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      - name: Install Python
+        uses: actions/setup-python@v6.2.0
+        with:
+          python-version: "3.14"
+      - name: Run prek
+        uses: j178/prek-action@v1.1.1

.github/workflows/ci-release.yml

@@ -0,0 +1,238 @@
+name: Release
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+      - 'v[0-9]+.[0-9]+.[0-9]+-beta.rc[0-9]+'
+concurrency:
+  group: release-${{ github.ref }}
+  cancel-in-progress: false
+env:
+  DEFAULT_UV_VERSION: "0.10.x"
+  DEFAULT_PYTHON_VERSION: "3.12"
+jobs:
+  wait-for-docker:
+    name: Wait for Docker Build
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Wait for Docker build
+        uses: lewagon/wait-on-check-action@v1.5.0
+        with:
+          ref: ${{ github.sha }}
+          check-name: 'Build Docker Image'
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          wait-interval: 60
+  build-release:
+    name: Build Release
+    needs: wait-for-docker
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+      # ---- Frontend Build ----
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4.2.0
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6.2.0
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Install frontend dependencies
+        run: cd src-ui && pnpm install
+      - name: Build frontend
+        run: cd src-ui && pnpm run build --configuration production
+      # ---- Backend Setup ----
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6.2.0
+        with:
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7.3.1
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ steps.setup-python.outputs.python-version }}
+      - name: Install Python dependencies
+        run: |
+          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends gettext liblept5
+      # ---- Build Documentation ----
+      - name: Build documentation
+        run: |
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            --frozen \
+            zensical build --clean
+      # ---- Prepare Release ----
+      - name: Generate requirements file
+        run: |
+          uv export --quiet --no-dev --all-extras --format requirements-txt --output-file requirements.txt
+      - name: Compile messages
+        run: |
+          cd src/
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            manage.py compilemessages
+      - name: Collect static files
+        run: |
+          cd src/
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            manage.py collectstatic --no-input --clear
+      - name: Assemble release package
+        run: |
+          mkdir -p dist/paperless-ngx/scripts
+
+          for file_name in .dockerignore \
+                          .env \
+                          Dockerfile \
+                          pyproject.toml \
+                          uv.lock \
+                          requirements.txt \
+                          LICENSE \
+                          README.md \
+                          paperless.conf.example
+          do
+            cp --verbose ${file_name} dist/paperless-ngx/
+          done
+          mv dist/paperless-ngx/paperless.conf.example dist/paperless-ngx/paperless.conf
+
+          cp --recursive docker/ dist/paperless-ngx/docker
+          cp scripts/*.service scripts/*.sh scripts/*.socket dist/paperless-ngx/scripts/
+          cp --recursive src/ dist/paperless-ngx/src
+          cp --recursive site/ dist/paperless-ngx/docs
+          mv static dist/paperless-ngx/
+
+          find dist/paperless-ngx -name "__pycache__" -type d -exec rm -rf {} +
+      - name: Create release archive
+        run: |
+          cd dist
+          sudo chown -R 1000:1000 paperless-ngx/
+          tar -cJf paperless-ngx.tar.xz paperless-ngx/
+      - name: Upload release artifact
+        uses: actions/upload-artifact@v7.0.0
+        with:
+          name: release
+          path: dist/paperless-ngx.tar.xz
+          retention-days: 7
+  publish-release:
+    name: Publish Release
+    needs: build-release
+    runs-on: ubuntu-24.04
+    outputs:
+      prerelease: ${{ steps.get-version.outputs.prerelease }}
+      changelog: ${{ steps.create-release.outputs.body }}
+      version: ${{ steps.get-version.outputs.version }}
+    steps:
+      - name: Download release artifact
+        uses: actions/download-artifact@v8.0.0
+        with:
+          name: release
+          path: ./
+      - name: Get version info
+        id: get-version
+        run: |
+          echo "version=${{ github.ref_name }}" >> $GITHUB_OUTPUT
+          if [[ "${{ github.ref_name }}" == *"-beta.rc"* ]]; then
+            echo "prerelease=true" >> $GITHUB_OUTPUT
+          else
+            echo "prerelease=false" >> $GITHUB_OUTPUT
+          fi
+      - name: Create release and changelog
+        id: create-release
+        uses: release-drafter/release-drafter@v6.2.0
+        with:
+          name: Paperless-ngx ${{ steps.get-version.outputs.version }}
+          tag: ${{ steps.get-version.outputs.version }}
+          version: ${{ steps.get-version.outputs.version }}
+          prerelease: ${{ steps.get-version.outputs.prerelease }}
+          publish: true
+          commitish: main
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Upload release archive
+        uses: shogo82148/actions-upload-release-asset@v1.9.2
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: ./paperless-ngx.tar.xz
+          asset_name: paperless-ngx-${{ steps.get-version.outputs.version }}.tar.xz
+          asset_content_type: application/x-xz
+  # ---------------------------------------------------------------------------
+  # Append changelog to docs (only on non-prerelease)
+  # ---------------------------------------------------------------------------
+  append-changelog:
+    name: Append Changelog
+    needs: publish-release
+    if: needs.publish-release.outputs.prerelease == 'false'
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.2
+        with:
+          ref: main
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6.2.0
+        with:
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7.3.1
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Update changelog
+        working-directory: docs
+        run: |
+          git branch ${{ needs.publish-release.outputs.version }}-changelog
+          git checkout ${{ needs.publish-release.outputs.version }}-changelog
+
+          echo -e "# Changelog\n\n${{ needs.publish-release.outputs.changelog }}\n" > changelog-new.md
+
+          echo "Manually linking usernames"
+          sed -i -r 's|@([a-zA-Z0-9_]+) \(\[#|[@\1](https://github.com/\1) ([#|g' changelog-new.md
+
+          echo "Removing unneeded comment tags"
+          sed -i -r 's|@<!---->|@|g' changelog-new.md
+
+          CURRENT_CHANGELOG=$(tail --lines +2 changelog.md)
+          echo -e "$CURRENT_CHANGELOG" >> changelog-new.md
+          mv changelog-new.md changelog.md
+
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            prek run --files changelog.md || true
+
+          git config --global user.name "github-actions"
+          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git commit -am "Changelog ${{ needs.publish-release.outputs.version }} - GHA"
+          git push origin ${{ needs.publish-release.outputs.version }}-changelog
+      - name: Create pull request
+        uses: actions/github-script@v8.0.0
+        with:
+          script: |
+            const { repo, owner } = context.repo;
+            const result = await github.rest.pulls.create({
+              title: 'Documentation: Add ${{ needs.publish-release.outputs.version }} changelog',
+              owner,
+              repo,
+              head: '${{ needs.publish-release.outputs.version }}-changelog',
+              base: 'main',
+              body: 'This PR is auto-generated by CI.'
+            });
+            github.rest.issues.addLabels({
+              owner,
+              repo,
+              issue_number: result.data.number,
+              labels: ['documentation', 'skip-changelog']
+            });

.github/workflows/ci.yml

@@ -1,674 +0,0 @@
-name: ci
-
-on:
-  push:
-    tags:
-      # https://semver.org/#spec-item-2
-      - 'v[0-9]+.[0-9]+.[0-9]+'
-      # https://semver.org/#spec-item-9
-      - 'v[0-9]+.[0-9]+.[0-9]+-beta.rc[0-9]+'
-    branches-ignore:
-      - 'translations**'
-  pull_request:
-    branches-ignore:
-      - 'translations**'
-
-env:
-  DEFAULT_UV_VERSION: "0.6.x"
-  # This is the default version of Python to use in most steps which aren't specific
-  DEFAULT_PYTHON_VERSION: "3.11"
-
-jobs:
-  pre-commit:
-    # We want to run on external PRs, but not on our own internal PRs as they'll be run
-    # by the push to the branch. Without this if check, checks are duplicated since
-    # internal PRs match both the push and pull_request events.
-    if:
-      github.event_name == 'push' || github.event.pull_request.head.repo.full_name !=
-      github.repository
-
-    name: Linting Checks
-    runs-on: ubuntu-24.04
-    steps:
-      -
-        name: Checkout repository
-        uses: actions/checkout@v4
-      -
-        name: Install python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      -
-        name: Check files
-        uses: pre-commit/action@v3.0.1
-
-  documentation:
-    name: "Build & Deploy Documentation"
-    runs-on: ubuntu-24.04
-    needs:
-      - pre-commit
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v4
-      -
-        name: Set up Python
-        id: setup-python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      -
-        name: Install uv
-        uses: astral-sh/setup-uv@v5
-        with:
-          version: ${{ env.DEFAULT_UV_VERSION }}
-          enable-cache: true
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      -
-        name: Install Python dependencies
-        run: |
-          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
-      -
-        name: Make documentation
-        run: |
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --dev \
-            --frozen \
-            mkdocs build --config-file ./mkdocs.yml
-      -
-        name: Deploy documentation
-        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        run: |
-          echo "docs.paperless-ngx.com" > "${{ github.workspace }}/docs/CNAME"
-          git config --global user.name "${{ github.actor }}"
-          git config --global user.email "${{ github.actor }}@users.noreply.github.com"
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --dev \
-            --frozen \
-            mkdocs gh-deploy --force --no-history
-      -
-        name: Upload artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: documentation
-          path: site/
-          retention-days: 7
-
-  tests-backend:
-    name: "Backend Tests (Python ${{ matrix.python-version }})"
-    runs-on: ubuntu-24.04
-    needs:
-      - pre-commit
-    strategy:
-      matrix:
-        python-version: ['3.10', '3.11', '3.12']
-      fail-fast: false
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v4
-      -
-        name: Start containers
-        run: |
-          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml pull --quiet
-          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml up --detach
-      -
-        name: Set up Python
-        id: setup-python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "${{ matrix.python-version }}"
-      -
-        name: Install uv
-        uses: astral-sh/setup-uv@v5
-        with:
-          version: ${{ env.DEFAULT_UV_VERSION }}
-          enable-cache: true
-          python-version: ${{ steps.setup-python.outputs.python-version }}
-      -
-        name: Install system dependencies
-        run: |
-          sudo apt-get update -qq
-          sudo apt-get install -qq --no-install-recommends unpaper tesseract-ocr imagemagick ghostscript libzbar0 poppler-utils
-      -
-        name: Configure ImageMagick
-        run: |
-          sudo cp docker/rootfs/etc/ImageMagick-6/paperless-policy.xml /etc/ImageMagick-6/policy.xml
-      -
-        name: Install Python dependencies
-        run: |
-          uv sync \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --group testing \
-            --frozen
-      -
-        name: List installed Python dependencies
-        run: |
-          uv pip list
-      -
-        name: Tests
-        env:
-          PAPERLESS_CI_TEST: 1
-          # Enable paperless_mail testing against real server
-          PAPERLESS_MAIL_TEST_HOST: ${{ secrets.TEST_MAIL_HOST }}
-          PAPERLESS_MAIL_TEST_USER: ${{ secrets.TEST_MAIL_USER }}
-          PAPERLESS_MAIL_TEST_PASSWD: ${{ secrets.TEST_MAIL_PASSWD }}
-        run: |
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --dev \
-            --frozen \
-            pytest
-      -
-        name: Upload backend test results to Codecov
-        if: always()
-        uses: codecov/test-results-action@v1
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: backend-python-${{ matrix.python-version }}
-          files: junit.xml
-      -
-        name: Upload backend coverage to Codecov
-        uses: codecov/codecov-action@v5
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: backend-python-${{ matrix.python-version }}
-          files: coverage.xml
-      -
-        name: Stop containers
-        if: always()
-        run: |
-          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml logs
-          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml down
-
-  install-frontend-dependencies:
-    name: "Install Frontend Dependencies"
-    runs-on: ubuntu-24.04
-    needs:
-      - pre-commit
-    steps:
-      - uses: actions/checkout@v4
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 10
-      -
-        name: Use Node.js 20
-        uses: actions/setup-node@v4
-        with:
-          node-version: 20.x
-          cache: 'pnpm'
-          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
-      - name: Cache frontend dependencies
-        id: cache-frontend-deps
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.pnpm-store
-            ~/.cache
-          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
-      -
-        name: Install dependencies
-        if: steps.cache-frontend-deps.outputs.cache-hit != 'true'
-        run: cd src-ui && pnpm install
-      -
-        name: Install Playwright
-        if: steps.cache-frontend-deps.outputs.cache-hit != 'true'
-        run: cd src-ui && pnpm playwright install --with-deps
-
-  tests-frontend:
-    name: "Frontend Tests (Node ${{ matrix.node-version }} - ${{ matrix.shard-index }}/${{ matrix.shard-count }})"
-    runs-on: ubuntu-24.04
-    needs:
-      - install-frontend-dependencies
-    strategy:
-      fail-fast: false
-      matrix:
-        node-version: [20.x]
-        shard-index: [1, 2, 3, 4]
-        shard-count: [4]
-    steps:
-      - uses: actions/checkout@v4
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 10
-      -
-        name: Use Node.js 20
-        uses: actions/setup-node@v4
-        with:
-          node-version: 20.x
-          cache: 'pnpm'
-          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
-      - name: Cache frontend dependencies
-        id: cache-frontend-deps
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.pnpm-store
-            ~/.cache
-          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
-      - name: Re-link Angular cli
-        run: cd src-ui && pnpm link @angular/cli
-      -
-        name: Linting checks
-        run: cd src-ui && pnpm run lint
-      -
-        name: Run Jest unit tests
-        run: cd src-ui && pnpm run test --max-workers=2 --shard=${{ matrix.shard-index }}/${{ matrix.shard-count }}
-      -
-        name: Run Playwright e2e tests
-        run: cd src-ui && pnpm exec playwright test --shard ${{ matrix.shard-index }}/${{ matrix.shard-count }}
-      -
-        name: Upload frontend test results to Codecov
-        uses: codecov/test-results-action@v1
-        if: always()
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: frontend-node-${{ matrix.node-version }}
-          directory: src-ui/
-      -
-        name: Upload frontend coverage to Codecov
-        uses: codecov/codecov-action@v5
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: frontend-node-${{ matrix.node-version }}
-          directory: src-ui/coverage/
-
-  frontend-bundle-analysis:
-    name: "Frontend Bundle Analysis"
-    runs-on: ubuntu-24.04
-    needs:
-      - tests-frontend
-    steps:
-      - uses: actions/checkout@v4
-      -
-        name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 10
-      -
-        name: Use Node.js 20
-        uses: actions/setup-node@v4
-        with:
-          node-version: 20.x
-          cache: 'pnpm'
-          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
-      -
-        name: Cache frontend dependencies
-        id: cache-frontend-deps
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.pnpm-store
-            ~/.cache
-          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/package-lock.json') }}
-      -
-        name: Re-link Angular cli
-        run: cd src-ui && pnpm link @angular/cli
-      -
-        name: Build frontend and upload analysis
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-        run: cd src-ui && pnpm run build --configuration=production
-
-  build-docker-image:
-    name: Build Docker image for ${{ github.ref_name }}
-    runs-on: ubuntu-24.04
-    if: github.event_name == 'push' && (startsWith(github.ref, 'refs/heads/feature-') || startsWith(github.ref, 'refs/heads/fix-') || github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/beta' || contains(github.ref, 'beta.rc') || startsWith(github.ref, 'refs/tags/v'))
-    concurrency:
-      group: ${{ github.workflow }}-build-docker-image-${{ github.ref_name }}
-      cancel-in-progress: true
-    needs:
-      - tests-backend
-      - tests-frontend
-    steps:
-      -
-        name: Check pushing to Docker Hub
-        id: push-other-places
-        # Only push to Dockerhub from the main repo AND the ref is either:
-        #  main
-        #  dev
-        #  beta
-        #  a tag
-        # Otherwise forks would require a Docker Hub account and secrets setup
-        run: |
-          if [[ ${{ github.repository_owner }} == "paperless-ngx" && ( ${{ github.ref_name }} == "dev" || ${{ github.ref_name }} == "beta" || ${{ startsWith(github.ref, 'refs/tags/v') }} == "true" ) ]] ; then
-            echo "Enabling DockerHub image push"
-            echo "enable=true" >> $GITHUB_OUTPUT
-          else
-            echo "Not pushing to DockerHub"
-            echo "enable=false" >> $GITHUB_OUTPUT
-          fi
-      -
-        name: Set ghcr repository name
-        id: set-ghcr-repository
-        run: |
-          ghcr_name=$(echo "${{ github.repository }}" | awk '{ print tolower($0) }')
-          echo "Name is ${ghcr_name}"
-          echo "ghcr-repository=${ghcr_name}" >> $GITHUB_OUTPUT
-      -
-        name: Gather Docker metadata
-        id: docker-meta
-        uses: docker/metadata-action@v5
-        with:
-          images: |
-            ghcr.io/${{ steps.set-ghcr-repository.outputs.ghcr-repository }}
-            name=paperlessngx/paperless-ngx,enable=${{ steps.push-other-places.outputs.enable }}
-            name=quay.io/paperlessngx/paperless-ngx,enable=${{ steps.push-other-places.outputs.enable }}
-          tags: |
-            # Tag branches with branch name
-            type=ref,event=branch
-            # Process semver tags
-            # For a tag x.y.z or vX.Y.Z, output an x.y.z and x.y image tag
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-      -
-        name: Checkout
-        uses: actions/checkout@v4
-      # If https://github.com/docker/buildx/issues/1044 is resolved,
-      # the append input with a native arm64 arch could be used to
-      # significantly speed up building
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-        with:
-          platforms: arm64
-      -
-        name: Login to GitHub Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      -
-        name: Login to Docker Hub
-        uses: docker/login-action@v3
-        # Don't attempt to login if not pushing to Docker Hub
-        if: steps.push-other-places.outputs.enable == 'true'
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-      -
-        name: Login to Quay.io
-        uses: docker/login-action@v3
-        # Don't attempt to login if not pushing to Quay.io
-        if: steps.push-other-places.outputs.enable == 'true'
-        with:
-          registry: quay.io
-          username: ${{ secrets.QUAY_USERNAME }}
-          password: ${{ secrets.QUAY_ROBOT_TOKEN }}
-      -
-        name: Build and push
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          file: ./Dockerfile
-          platforms: linux/amd64,linux/arm64
-          push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.docker-meta.outputs.tags }}
-          labels: ${{ steps.docker-meta.outputs.labels }}
-          build-args: |
-            PNGX_TAG_VERSION=${{ steps.docker-meta.outputs.version }}
-          # Get cache layers from this branch, then dev
-          # This allows new branches to get at least some cache benefits, generally from dev
-          cache-from: |
-            type=registry,ref=ghcr.io/${{ steps.set-ghcr-repository.outputs.ghcr-repository }}/builder/cache/app:${{ github.ref_name }}
-            type=registry,ref=ghcr.io/${{ steps.set-ghcr-repository.outputs.ghcr-repository }}/builder/cache/app:dev
-          cache-to: |
-            type=registry,mode=max,ref=ghcr.io/${{ steps.set-ghcr-repository.outputs.ghcr-repository }}/builder/cache/app:${{ github.ref_name }}
-      -
-        name: Inspect image
-        run: |
-          docker buildx imagetools inspect ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
-      -
-        name: Export frontend artifact from docker
-        run: |
-          docker create --name frontend-extract ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
-          docker cp frontend-extract:/usr/src/paperless/src/documents/static/frontend src/documents/static/frontend/
-      -
-        name: Upload frontend artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: frontend-compiled
-          path: src/documents/static/frontend/
-          retention-days: 7
-
-  build-release:
-    name: "Build Release"
-    needs:
-      - build-docker-image
-      - documentation
-    runs-on: ubuntu-24.04
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v4
-      -
-        name: Set up Python
-        id: setup-python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      -
-        name: Install uv
-        uses: astral-sh/setup-uv@v5
-        with:
-          version: ${{ env.DEFAULT_UV_VERSION }}
-          enable-cache: true
-          python-version: ${{ steps.setup-python.outputs.python-version }}
-      -
-        name: Install Python dependencies
-        run: |
-          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
-      -
-        name: Install system dependencies
-        run: |
-          sudo apt-get update -qq
-          sudo apt-get install -qq --no-install-recommends gettext liblept5
-      -
-        name: Download frontend artifact
-        uses: actions/download-artifact@v4
-        with:
-          name: frontend-compiled
-          path: src/documents/static/frontend/
-      -
-        name: Download documentation artifact
-        uses: actions/download-artifact@v4
-        with:
-          name: documentation
-          path: docs/_build/html/
-      -
-        name: Generate requirements file
-        run: |
-           uv export --quiet --no-dev --all-extras --format requirements-txt --output-file requirements.txt
-      -
-        name: Compile messages
-        run: |
-          cd src/
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            manage.py compilemessages
-      -
-        name: Collect static files
-        run: |
-          cd src/
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            manage.py collectstatic --no-input
-      -
-        name: Move files
-        run: |
-          echo "Making dist folders"
-          for directory in dist \
-                          dist/paperless-ngx \
-                          dist/paperless-ngx/scripts;
-          do
-            mkdir --verbose --parents ${directory}
-          done
-
-          echo "Copying basic files"
-          for file_name in .dockerignore \
-                          .env \
-                          Dockerfile \
-                          pyproject.toml \
-                          uv.lock \
-                          requirements.txt \
-                          LICENSE \
-                          README.md \
-                          paperless.conf.example
-          do
-            cp --verbose ${file_name} dist/paperless-ngx/
-          done
-          mv --verbose dist/paperless-ngx/paperless.conf.example dist/paperless-ngx/paperless.conf
-
-          echo "Copying Docker related files"
-          cp --recursive docker/ dist/paperless-ngx/docker
-
-          echo "Copying startup scripts"
-          cp --verbose scripts/*.service scripts/*.sh scripts/*.socket dist/paperless-ngx/scripts/
-
-          echo "Copying source files"
-          cp --recursive src/ dist/paperless-ngx/src
-          echo "Copying documentation"
-          cp --recursive docs/_build/html/ dist/paperless-ngx/docs
-
-          mv --verbose static dist/paperless-ngx
-      -
-        name: Make release package
-        run: |
-          echo "Creating release archive"
-          cd dist
-          sudo chown -R 1000:1000 paperless-ngx/
-          tar -cJf paperless-ngx.tar.xz paperless-ngx/
-      -
-        name: Upload release artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: release
-          path: dist/paperless-ngx.tar.xz
-          retention-days: 7
-
-  publish-release:
-    name: "Publish Release"
-    runs-on: ubuntu-24.04
-    outputs:
-      prerelease: ${{ steps.get_version.outputs.prerelease }}
-      changelog: ${{ steps.create-release.outputs.body }}
-      version: ${{ steps.get_version.outputs.version }}
-    needs:
-      - build-release
-    if: github.ref_type == 'tag' && (startsWith(github.ref_name, 'v') || contains(github.ref_name, '-beta.rc'))
-    steps:
-      -
-        name: Download release artifact
-        uses: actions/download-artifact@v4
-        with:
-          name: release
-          path: ./
-      -
-        name: Get version
-        id: get_version
-        run: |
-          echo "version=${{ github.ref_name }}" >> $GITHUB_OUTPUT
-          if [[ ${{ contains(github.ref_name, '-beta.rc') }} == 'true' ]]; then
-            echo "prerelease=true" >> $GITHUB_OUTPUT
-          else
-            echo "prerelease=false" >> $GITHUB_OUTPUT
-          fi
-      -
-        name: Create Release and Changelog
-        id: create-release
-        uses: release-drafter/release-drafter@v6
-        with:
-          name: Paperless-ngx ${{ steps.get_version.outputs.version }}
-          tag: ${{ steps.get_version.outputs.version }}
-          version: ${{ steps.get_version.outputs.version }}
-          prerelease: ${{ steps.get_version.outputs.prerelease }}
-          publish: true # ensures release is not marked as draft
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      -
-        name: Upload release archive
-        id: upload-release-asset
-        uses: shogo82148/actions-upload-release-asset@v1
-        with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          upload_url: ${{ steps.create-release.outputs.upload_url }}
-          asset_path: ./paperless-ngx.tar.xz
-          asset_name: paperless-ngx-${{ steps.get_version.outputs.version }}.tar.xz
-          asset_content_type: application/x-xz
-
-  append-changelog:
-    name: "Append Changelog"
-    runs-on: ubuntu-24.04
-    needs:
-      - publish-release
-    if: needs.publish-release.outputs.prerelease == 'false'
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: main
-      -
-        name: Set up Python
-        id: setup-python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      -
-        name: Install uv
-        uses: astral-sh/setup-uv@v5
-        with:
-          version: ${{ env.DEFAULT_UV_VERSION }}
-          enable-cache: true
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      -
-        name: Append Changelog to docs
-        id: append-Changelog
-        working-directory: docs
-        run: |
-          git branch ${{ needs.publish-release.outputs.version }}-changelog
-          git checkout ${{ needs.publish-release.outputs.version }}-changelog
-          echo -e "# Changelog\n\n${{ needs.publish-release.outputs.changelog }}\n" > changelog-new.md
-          echo "Manually linking usernames"
-          sed -i -r 's|@([a-zA-Z0-9_]+) \(\[#|[@\1](https://github.com/\1) ([#|g' changelog-new.md
-          echo "Removing unneeded comment tags"
-          sed -i -r 's|@<!---->|@|g' changelog-new.md
-          CURRENT_CHANGELOG=`tail --lines +2 changelog.md`
-          echo -e "$CURRENT_CHANGELOG" >> changelog-new.md
-          mv changelog-new.md changelog.md
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --dev \
-            pre-commit run --files changelog.md || true
-          git config --global user.name "github-actions"
-          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
-          git commit -am "Changelog ${{ needs.publish-release.outputs.version }} - GHA"
-          git push origin ${{ needs.publish-release.outputs.version }}-changelog
-      -
-        name: Create Pull Request
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const { repo, owner } = context.repo;
-            const result = await github.rest.pulls.create({
-              title: 'Documentation: Add ${{ needs.publish-release.outputs.version }} changelog',
-              owner,
-              repo,
-              head: '${{ needs.publish-release.outputs.version }}-changelog',
-              base: 'main',
-              body: 'This PR is auto-generated by CI.'
-            });
-            github.rest.issues.addLabels({
-              owner,
-              repo,
-              issue_number: result.data.number,
-              labels: ['documentation', 'skip-changelog']
-            });

.github/workflows/cleanup-tags.yml

@@ -4,19 +4,14 @@
 # Requires a PAT with the correct scope set in the secrets.
 #
 # This workflow will not trigger runs on forked repos.
-
 name: Cleanup Image Tags
-
 on:
-  delete:
+  workflow_dispatch:
-  push:
+  schedule:
-    paths:
+    - cron: '0 0 * * 0'
-      - ".github/workflows/cleanup-tags.yml"
-
 concurrency:
   group: registry-tags-cleanup
   cancel-in-progress: false
-
 jobs:
   cleanup-images:
     name: Cleanup Image Tags for ${{ matrix.primary-name }}
@@ -30,10 +25,9 @@ jobs:
       # Requires a personal access token with the OAuth scope delete:packages
       TOKEN: ${{ secrets.GHA_CONTAINER_DELETE_TOKEN }}
     steps:
-      -
+      - name: Clean temporary images
-        name: Clean temporary images
         if: "${{ env.TOKEN != '' }}"
-        uses: stumpylog/image-cleaner-action/ephemeral@v0.10.0
+        uses: stumpylog/image-cleaner-action/ephemeral@v0.12.0
         with:
           token: "${{ env.TOKEN }}"
           owner: "${{ github.repository_owner }}"
@@ -43,7 +37,6 @@ jobs:
           repo_name: "paperless-ngx"
           match_regex: "(feature|fix)"
           do_delete: "true"
-
   cleanup-untagged-images:
     name: Cleanup Untagged Images Tags for ${{ matrix.primary-name }}
     if: github.repository_owner == 'paperless-ngx'
@@ -58,10 +51,9 @@ jobs:
       # Requires a personal access token with the OAuth scope delete:packages
       TOKEN: ${{ secrets.GHA_CONTAINER_DELETE_TOKEN }}
     steps:
-      -
+      - name: Clean untagged images
-        name: Clean untagged images
         if: "${{ env.TOKEN != '' }}"
-        uses: stumpylog/image-cleaner-action/untagged@v0.10.0
+        uses: stumpylog/image-cleaner-action/untagged@v0.12.0
         with:
           token: "${{ env.TOKEN }}"
           owner: "${{ github.repository_owner }}"

.github/workflows/codeql-analysis.yml

@@ -10,16 +10,14 @@
 # supported CodeQL languages.
 #
 name: "CodeQL"
-
 on:
   push:
-    branches: [ main, dev ]
+    branches: [main, dev]
   pull_request:
     # The branches below must be a subset of the branches above
-    branches: [ dev ]
+    branches: [dev]
   schedule:
     - cron: '28 13 * * 5'
-
 jobs:
   analyze:
     name: Analyze
@@ -28,27 +26,23 @@ jobs:
       actions: read
       contents: read
       security-events: write
-
     strategy:
       fail-fast: false
       matrix:
-        language: [ 'javascript', 'python' ]
+        language: ['javascript', 'python']
         # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
         # Learn more about CodeQL language support at https://git.io/codeql-language-support
-
     steps:
-    - name: Checkout repository
+      - name: Checkout repository
-      uses: actions/checkout@v4
+        uses: actions/checkout@v6.0.2
-
+      # Initializes the CodeQL tools for scanning.
-    # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
-    - name: Initialize CodeQL
+        uses: github/codeql-action/init@v4.32.5
-      uses: github/codeql-action/init@v3
+        with:
-      with:
+          languages: ${{ matrix.language }}
-        languages: ${{ matrix.language }}
+          # If you wish to specify custom queries, you can do so here or in a config file.
-        # If you wish to specify custom queries, you can do so here or in a config file.
+          # By default, queries listed here will override any specified in a config file.
-        # By default, queries listed here will override any specified in a config file.
+          # Prefix the list here with "+" to use these queries and those in the config file.
-        # Prefix the list here with "+" to use these queries and those in the config file.
+          # queries: ./path/to/local/query, your-org/your-repo/queries@main
-        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+      - name: Perform CodeQL Analysis
-
+        uses: github/codeql-action/analyze@v4.32.5
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3

.github/workflows/crowdin.yml

@@ -1,35 +1,30 @@
 name: Crowdin Action
-
 on:
   workflow_dispatch:
   schedule:
     - cron: '2 */12 * * *'
   push:
-    paths: [
+    paths: ['src/locale/**', 'src-ui/messages.xlf', 'src-ui/src/locale/**']
-      'src/locale/**',
+    branches: [dev]
-      'src-ui/messages.xlf',
-      'src-ui/src/locale/**'
-    ]
-    branches: [ dev ]
-
 jobs:
   synchronize-with-crowdin:
     name: Crowdin Sync
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
-
     steps:
-    - name: Checkout
+      - name: Checkout
-      uses: actions/checkout@v4
+        uses: actions/checkout@v6.0.2
-    - name: crowdin action
+        with:
-      uses: crowdin/github-action@v2
+          token: ${{ secrets.PNGX_BOT_PAT }}
-      with:
+      - name: crowdin action
-        upload_translations: false
+        uses: crowdin/github-action@v2.15.0
-        download_translations: true
+        with:
-        crowdin_branch_name: 'dev'
+          upload_translations: false
-        localization_branch_name: l10n_dev
+          download_translations: true
-        pull_request_labels: 'skip-changelog, translation'
+          crowdin_branch_name: 'dev'
-      env:
+          localization_branch_name: l10n_dev
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          pull_request_labels: 'skip-changelog, translation'
-        CROWDIN_PROJECT_ID: ${{ secrets.CROWDIN_PROJECT_ID }}
+        env:
-        CROWDIN_PERSONAL_TOKEN: ${{ secrets.CROWDIN_PERSONAL_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          CROWDIN_PROJECT_ID: ${{ secrets.CROWDIN_PROJECT_ID }}
+          CROWDIN_PERSONAL_TOKEN: ${{ secrets.CROWDIN_PERSONAL_TOKEN }}

.github/workflows/pr-bot.yml

@@ -0,0 +1,123 @@
+name: PR Bot
+on:
+  pull_request_target:
+    types: [opened]
+jobs:
+  anti-slop:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      issues: read
+      pull-requests: write
+    steps:
+      - uses: peakoss/anti-slop@v0.2.1
+        with:
+          max-failures: 4
+          failure-add-pr-labels: 'ai'
+  pr-bot:
+    name: Automated PR Bot
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+    steps:
+      - name: Label PR by file path or branch name
+        # see .github/labeler.yml for the labeler config
+        uses: actions/labeler@v6.0.1
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+      - name: Label by size
+        uses: Gascon1/pr-size-labeler@v1.3.0
+        with:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          xs_label: 'small-change'
+          xs_diff: '9'
+          s_label: 'non-trivial'
+          s_diff: '99999'
+          fail_if_xl: 'false'
+          excluded_files: /\.lock$/ /\.txt$/ ^src-ui/pnpm-lock\.yaml$ ^src-ui/messages\.xlf$ ^src/locale/en_US/LC_MESSAGES/django\.po$
+      - name: Label by PR title
+        uses: actions/github-script@v8.0.0
+        with:
+          script: |
+            const pr = context.payload.pull_request;
+            const title = pr.title.toLowerCase();
+            const labels = [];
+
+            if (/^(fix|bugfix)/i.test(title)) {
+              labels.push('bug');
+            } else if (/^feature/i.test(title)) {
+              labels.push('enhancement');
+            } else if (!/^(dependabot)/i.test(title) && !/^(chore)/i.test(title)) {
+              labels.push('enhancement'); // Default fallback
+            }
+
+            if (labels.length) {
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: pr.number,
+                labels,
+              });
+              core.info(`Added labels based on title: ${labels.join(', ')}`);
+            }
+      - name: Label bot-generated PRs
+        if: ${{ contains(github.actor, 'dependabot') || contains(github.actor, 'crowdin-bot') }}
+        uses: actions/github-script@v8.0.0
+        with:
+          script: |
+            const pr = context.payload.pull_request;
+            const user = pr.user.login.toLowerCase();
+            const labels = [];
+
+            if (user.includes('dependabot')) {
+              labels.push('dependencies');
+            }
+
+            if (user.includes('crowdin-bot')) {
+              labels.push('translation', 'skip-changelog');
+            }
+
+            if (labels.length) {
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: pr.number,
+                labels,
+              });
+            }
+      - name: Welcome comment
+        if: ${{ !contains(github.actor, 'bot') }}
+        uses: actions/github-script@v8.0.0
+        with:
+          script: |
+            const pr = context.payload.pull_request;
+            const user = pr.user.login;
+
+            const { data: members } = await github.rest.orgs.listMembers({
+              org: 'paperless-ngx',
+            });
+
+            const memberLogins = members.map(m => m.login.toLowerCase());
+            if (memberLogins.includes(user.toLowerCase())) {
+              core.info('Skipping comment: user is org member');
+              return;
+            }
+
+            const body =
+                "Hello @" + user + ",\n\n" +
+                "Thank you very much for submitting this PR to us!\n\n" +
+                "This is what will happen next:\n\n" +
+                "1. CI tests will run against your PR to ensure quality and consistency.\n" +
+                "2. Next, human contributors from paperless-ngx review your changes.\n" +
+                "3. Please address any issues that come up during the review as soon as you are able to.\n" +
+                "4. If accepted, your pull request will be merged into the `dev` branch and changes there will be tested further.\n" +
+                "5. Eventually, changes from you and other contributors will be merged into `main` and a new release will be made.\n\n" +
+                "You'll be hearing from us soon, and thank you again for contributing to our project.";
+
+            await github.rest.issues.createComment({
+              issue_number: pr.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body,
+            });

.github/workflows/project-actions.yml

@@ -1,5 +1,4 @@
 name: Project Automations
-
 on:
   pull_request_target: #_target allows access to secrets
     types:
@@ -8,10 +7,8 @@ on:
     branches:
       - main
       - dev
-
 permissions:
   contents: read
-
 jobs:
   pr_opened_or_reopened:
     name: pr_opened_or_reopened
@@ -22,6 +19,6 @@ jobs:
     if: github.event_name == 'pull_request_target' && (github.event.action == 'opened' || github.event.action == 'reopened') && github.event.pull_request.user.login != 'dependabot'
     steps:
       - name: Label PR with release-drafter
-        uses: release-drafter/release-drafter@v6
+        uses: release-drafter/release-drafter@v6.2.0
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/repo-maintenance.yml

@@ -1,67 +1,63 @@
 name: 'Repository Maintenance'
-
 on:
   schedule:
     - cron: '0 3 * * *'
   workflow_dispatch:
-
 permissions:
   issues: write
   pull-requests: write
   discussions: write
-
 concurrency:
   group: lock
-
 jobs:
   stale:
     name: 'Stale'
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/stale@v9
+      - uses: actions/stale@v10.2.0
         with:
           days-before-stale: 7
           days-before-close: 14
-          any-of-labels: 'stale,cant-reproduce,not a bug'
+          any-of-issue-labels: 'cant-reproduce,not a bug'
           stale-issue-label: stale
-          stale-pr-label: stale
           stale-issue-message: >
-            This issue has been automatically marked as stale because it has not had
+            This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
-            recent activity. It will be closed if no further activity occurs. Thank you
+
-            for your contributions. See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
+          days-before-pr-stale: 14
+          days-before-pr-close: 7
+          stale-pr-message: ""
+          stale-pr-label: stale
+          exempt-pr-labels: 'notable'
+          close-pr-message: >
+            This pull request has been automatically closed because it has not had recent activity. Thank you for your contributions. Please open a new pull request or discussion if you would like to continue working on this change.
+
   lock-threads:
     name: 'Lock Old Threads'
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: dessant/lock-threads@v5
+      - uses: dessant/lock-threads@v6.0.0
         with:
           issue-inactive-days: '30'
           pr-inactive-days: '30'
           discussion-inactive-days: '30'
           log-output: true
           issue-comment: >
-            This issue has been automatically locked since there
+            This issue has been automatically locked since there has not been any recent activity after it was closed. Please open a new discussion or issue for related concerns. See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
-            has not been any recent activity after it was closed.
+
-            Please open a new discussion or issue for related concerns.
-            See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
           pr-comment: >
-            This pull request has been automatically locked since there
+            This pull request has been automatically locked since there has not been any recent activity after it was closed. Please open a new discussion or issue for related concerns. See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
-            has not been any recent activity after it was closed.
+
-            Please open a new discussion or issue for related concerns.
-            See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
           discussion-comment: >
-            This discussion has been automatically locked since there
+            This discussion has been automatically locked since there has not been any recent activity after it was closed. Please open a new discussion for related concerns. See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
-            has not been any recent activity after it was closed.
+
-            Please open a new discussion for related concerns.
-            See our [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/dev/CONTRIBUTING.md#automatic-repository-maintenance) for more details.
   close-answered-discussions:
     name: 'Close Answered Discussions'
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/github-script@v7
+      - uses: actions/github-script@v8.0.0
         with:
           script: |
             function sleep(ms) {
@@ -118,7 +114,7 @@ jobs:
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/github-script@v7
+      - uses: actions/github-script@v8.0.0
         with:
           script: |
             function sleep(ms) {
@@ -210,7 +206,7 @@ jobs:
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/github-script@v7
+      - uses: actions/github-script@v8.0.0
         with:
           script: |
             function sleep(ms) {
@@ -245,6 +241,7 @@ jobs:
                 ) {
                   nodes {
                     id,
+                    createdAt,
                     number,
                     updatedAt,
                     upvoteCount,

.github/workflows/translate-strings.yml

@@ -0,0 +1,71 @@
+name: Generate Translation Strings
+on:
+  push:
+    branches:
+      - dev
+jobs:
+  generate-translate-strings:
+    name: Generate Translation Strings
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v6.0.2
+        env:
+          GH_REF: ${{ github.ref }} # sonar rule:githubactions:S7630 - avoid injection
+        with:
+          token: ${{ secrets.PNGX_BOT_PAT }}
+          ref: ${{ env.GH_REF }}
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6.2.0
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends gettext
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7.3.1
+        with:
+          enable-cache: true
+      - name: Install backend python dependencies
+        run: |
+          uv sync \
+            --group dev \
+            --frozen
+      - name: Generate backend translation strings
+        run: cd src/ && uv run manage.py makemessages -l en_US -i "samples*"
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4.2.0
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6.2.0
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        id: cache-frontend-deps
+        uses: actions/cache@v5.0.3
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Install frontend dependencies
+        if: steps.cache-frontend-deps.outputs.cache-hit != 'true'
+        run: cd src-ui && pnpm install
+      - name: Re-link Angular cli
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Generate frontend translation strings
+        run: |
+          cd src-ui
+          pnpm run ng extract-i18n
+      - name: Commit changes
+        uses: stefanzweifel/git-auto-commit-action@v7.1.0
+        with:
+          file_pattern: 'src-ui/messages.xlf src/locale/en_US/LC_MESSAGES/django.po'
+          commit_message: "Auto translate strings"
+          commit_user_name: "GitHub Actions"
+          commit_author: "GitHub Actions <41898282+github-actions[bot]@users.noreply.github.com>"

.gitignore

@@ -40,6 +40,7 @@ htmlcov/
 .coverage
 .coverage.*
 .cache
+.uv-cache
 nosetests.xml
 coverage.xml
 *,cover
@@ -53,7 +54,7 @@ junit.xml
 # Django stuff:
 *.log
 
-# MkDocs documentation
+# Zensical documentation
 site/
 
 # PyBuilder
@@ -107,3 +108,6 @@ celerybeat-schedule*
 /.devcontainer/data/
 /.devcontainer/media/
 /.devcontainer/redisdata/
+
+# ignore pnpm package store folder created when setting up the devcontainer
+.pnpm-store/

.pre-commit-config.yaml

@@ -1,11 +1,11 @@
 # This file configures pre-commit hooks.
 # See https://pre-commit.com/ for general information
 # See https://pre-commit.com/hooks.html for a listing of possible hooks
-
+# We actually run via https://github.com/j178/prek which is compatible
 repos:
   # General hooks
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: check-docstring-first
       - id: check-json
@@ -19,7 +19,7 @@ repos:
         exclude_types:
           - svg
           - pofile
-        exclude: "(^LICENSE$)"
+        exclude: "(^LICENSE$|^src/documents/static/bootstrap.min.css$)"
       - id: mixed-line-ending
         args:
           - "--fix=lf"
@@ -29,16 +29,16 @@ repos:
       - id: check-case-conflict
       - id: detect-private-key
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.4.0
+    rev: v2.4.1
     hooks:
       - id: codespell
-        exclude: "(^src-ui/src/locale/)|(^src-ui/pnpm-lock.yaml)|(^src-ui/e2e/)|(^src/paperless_mail/tests/samples/)"
+        additional_dependencies: [tomli]
         exclude_types:
           - pofile
           - json
   # See https://github.com/prettier/prettier/issues/15742 for the fork reason
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: 'v3.3.3'
+    rev: 'v3.8.1'
     hooks:
       - id: prettier
         types_or:
@@ -50,29 +50,36 @@ repos:
           - 'prettier-plugin-organize-imports@4.1.0'
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.9
+    rev: v0.15.5
     hooks:
-      - id: ruff
+      - id: ruff-check
       - id: ruff-format
   - repo: https://github.com/tox-dev/pyproject-fmt
-    rev: "v2.5.1"
+    rev: "v2.12.1"
     hooks:
       - id: pyproject-fmt
   # Dockerfile hooks
   - repo: https://github.com/AleksaC/hadolint-py
-    rev: v2.12.0.3
+    rev: v2.14.0
     hooks:
       - id: hadolint
   # Shell script hooks
   - repo: https://github.com/lovesegfault/beautysh
-    rev: v6.2.1
+    rev: v6.4.2
     hooks:
       - id: beautysh
-        additional_dependencies:
+        types: [file]
-          - setuptools
+        files: (\.sh$|/run$|/finish$)
         args:
           - "--tab"
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: "v0.10.0.1"
+    rev: "v0.11.0.1"
     hooks:
       - id: shellcheck
+  - repo: https://github.com/google/yamlfmt
+    rev: v0.21.0
+    hooks:
+      - id: yamlfmt
+        exclude: "^src-ui/pnpm-lock.yaml"
+        types:
+          - yaml

.yamlfmt

@@ -0,0 +1 @@
+line_ending: lf

CONTRIBUTING.md

@@ -2,16 +2,20 @@
 
 If you feel like contributing to the project, please do! Bug fixes and improvements are always welcome.
 
+⚠️ Please note: Pull requests that implement a new feature or enhancement _should almost always target an existing feature request_ with evidence of community interest and discussion. This is in order to balance the work of implementing and maintaining new features / enhancements. Pull requests that are opened without meeting this requirement may not be merged.
+
 If you want to implement something big:
 
-- Please start a discussion about that in the issues! Maybe something similar is already in development and we can make it happen together.
+- As above, please start with a discussion! Maybe something similar is already in development and we can make it happen together.
 - When making additions to the project, consider if the majority of users will benefit from your change. If not, you're probably better of forking the project.
 - Also consider if your change will get in the way of other users. A good change is a change that enhances the experience of some users who want that change and does not affect users who do not care about the change.
 - Please see the [paperless-ngx merge process](#merging-prs) below.
 
 ## Python
 
-Paperless supports python 3.10 - 3.12 at this time. We format Python code with [ruff](https://docs.astral.sh/ruff/formatter/).
+Paperless-ngx currently supports Python 3.11, 3.12, 3.13, and 3.14. As a policy, we aim to support at least the three most recent Python versions, and drop support for versions as they reach end-of-life. Older versions may be supported if dependencies permit, but this is not guaranteed.
+
+We format Python code with [ruff](https://docs.astral.sh/ruff/formatter/).
 
 ## Branches
 
@@ -37,6 +41,8 @@ Before you can run `pytest`, ensure to [properly set up your local environment](
 
 Once you have submitted a **P**ull **R**equest it will be reviewed, approved, and merged by one or more community members of any team. Automated code tests and formatting checks must be passed.
 
+Important: Pull requests that implement a new feature or enhancement _should almost always target an existing feature request_ with evidence of community interest and discussion. This is in order to balance the work of implementing and maintaining new features / enhancements. Instead of opening a PR which does not meet this requirement, please open a feature request instead, to gather feedback from both users and the project maintainers.
+
 ## Non-Trivial Requests
 
 PRs deemed `non-trivial` will go through a stricter review process before being merged into `dev`. This is to ensure code quality and complete functionality (free of side effects).
@@ -81,7 +87,7 @@ Some notes about translation:
 
 If a language has already been added, and you would like to contribute new translations or change existing translations, please read the "Translation" section in the README.md file for further details on that.
 
-If you would like the project to be translated to another language, first head over to https://crwd.in/paperless-ngx to check if that language has already been enabled for translation.
+If you would like the project to be translated to another language, first head over to https://crowdin.com/project/paperless-ngx to check if that language has already been enabled for translation.
 If not, please request the language to be added by creating an issue on GitHub. The issue should contain:
 
 - English name of the language (the localized name can be added on Crowdin).
@@ -109,28 +115,12 @@ Paperless-ngx is a community project. We do our best to delegate permission and
 
 ## Structure
 
-As of writing, there are 21 members in paperless-ngx. 4 of these people have complete administrative privileges to the repo:
+There are currently 2 members in paperless-ngx with complete administrative privileges to the repo:
 
 - [@shamoon](https://github.com/shamoon)
-- [@bauerj](https://github.com/bauerj)
+- [@stumpylog](https://github.com/stumpylog)
-- [@qcasey](https://github.com/qcasey)
-- [@FrankStrieter](https://github.com/FrankStrieter)
 
-There are 5 teams collaborating on specific tasks within paperless-ngx:
+There are other members who occasionally contribute but we are actively seeking more dedicated maintainers of the project. Please reach out if you are interested.
-
-- @paperless-ngx/backend (Python / django)
-- @paperless-ngx/frontend (JavaScript / Typescript)
-- @paperless-ngx/ci-cd (GitHub Actions / Deployment)
-- @paperless-ngx/issues (Issue triage)
-- @paperless-ngx/test (General testing for larger PRs)
-
-## Permissions
-
-All team members are notified when mentioned or assigned to a relevant issue or pull request. Additionally, each team has slightly different access to paperless-ngx:
-
-- The **test** team has no special permissions.
-- The **issues** team has `triage` access. This means they can organize issues and pull requests.
-- The **backend**, **frontend**, and **ci-cd** teams have `write` access. This means they can approve PRs and push code, containers, releases, and more.
 
 ## Joining
 
@@ -141,13 +131,13 @@ The admins occasionally invite contributors directly if we believe having them o
 # Automatic Repository Maintenance
 
 The Paperless-ngx team appreciates all effort and interest from the community in filing bug reports, creating feature requests, sharing ideas and helping other
-community members. That said, in an effort to keep the repository organized and managebale the project uses automatic handling of certain areas:
+community members. That said, in an effort to keep the repository organized and manageable the project uses automatic handling of certain areas:
 
 - Issues that cannot be reproduced will be marked 'stale' after 7 days of inactivity and closed after 14 further days of inactivity.
 - Issues, pull requests and discussions that are closed will be locked after 30 days of inactivity.
 - Discussions with a marked answer will be automatically closed.
 - Discussions in the 'General' or 'Support' categories will be closed after 180 days of inactivity.
-- Feature requests that do not meet the following thresholds will be closed: 180 days of inactivity, < 5 "up-votes" after 180 days, < 20 "up-votes" after 1 year or < 80 "up-votes" at 2 years.
+- Feature requests that do not meet the following thresholds will be closed: 180 days of inactivity with less than 80 "up-votes", < 5 "up-votes" after 180 days, < 20 "up-votes" after 1 year or < 40 "up-votes" at 2 years.
 
 In all cases, threads can be re-opened by project maintainers and, of course, users can always create a new discussion for related concerns.
 Finally, remember that all information remains searchable and 'closed' feature requests can still serve as inspiration for new features.

Dockerfile

@@ -5,14 +5,12 @@
 # Purpose: Compiles the frontend
 # Notes:
 #  - Does PNPM stuff with Typescript and such
-FROM --platform=$BUILDPLATFORM docker.io/node:20-bookworm-slim AS compile-frontend
+FROM --platform=$BUILDPLATFORM docker.io/node:24-trixie-slim AS compile-frontend
 
 COPY ./src-ui /src/src-ui
 
 WORKDIR /src/src-ui
 RUN set -eux \
-  && npm update -g pnpm \
-  && npm install -g corepack@latest \
   && corepack enable \
   && pnpm install
 
@@ -21,7 +19,7 @@ ARG PNGX_TAG_VERSION=
 RUN set -eux && \
 case "${PNGX_TAG_VERSION}" in \
   dev|beta|fix*|feature*) \
-    sed -i -E "s/version: '([0-9\.]+)'/version: '\1 #${PNGX_TAG_VERSION}'/g" /src/src-ui/src/environments/environment.prod.ts \
+    sed -i -E "s/tag: '([a-z\.]+)'/tag: '${PNGX_TAG_VERSION}'/g" /src/src-ui/src/environments/environment.prod.ts \
     ;; \
 esac
 
@@ -32,7 +30,7 @@ RUN set -eux \
 # Purpose: Installs s6-overlay and rootfs
 # Comments:
 #  - Don't leave anything extra in here either
-FROM ghcr.io/astral-sh/uv:0.6.11-python3.12-bookworm-slim AS s6-overlay-base
+FROM ghcr.io/astral-sh/uv:0.10.7-python3.12-trixie-slim AS s6-overlay-base
 
 WORKDIR /usr/src/s6
 
@@ -47,7 +45,7 @@ ENV \
 ARG TARGETARCH
 ARG TARGETVARIANT
 # Lock this version
-ARG S6_OVERLAY_VERSION=3.2.0.2
+ARG S6_OVERLAY_VERSION=3.2.2.0
 
 ARG S6_BUILD_TIME_PKGS="curl \
                         xz-utils"
@@ -102,8 +100,6 @@ ARG TARGETARCH
 
 # Can be workflow provided, defaults set for manual building
 ARG JBIG2ENC_VERSION=0.30
-ARG QPDF_VERSION=11.9.0
-ARG GS_VERSION=10.03.1
 
 # Set Python environment variables
 ENV PYTHONDONTWRITEBYTECODE=1 \
@@ -112,8 +108,7 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONWARNINGS="ignore:::django.http.response:517" \
     PNGX_CONTAINERIZED=1 \
     # https://docs.astral.sh/uv/reference/settings/#link-mode
-    UV_LINK_MODE=copy \
+    UV_LINK_MODE=copy
-    UV_CACHE_DIR=/cache/uv/
 
 #
 # Begin installation and configuration
@@ -159,8 +154,6 @@ ARG RUNTIME_PACKAGES="\
   libmagic1 \
   media-types \
   zlib1g \
-  # Barcode splitter
-  libzbar0 \
   poppler-utils"
 
 # Install basic runtime packages.
@@ -170,20 +163,8 @@ RUN set -eux \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${RUNTIME_PACKAGES} \
     && echo "Installing pre-built updates" \
-      && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all --parallel --parallel-max 4 \
+      && curl --fail --silent --no-progress-meter --show-error --location --remote-name-all \
-        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
+        https://github.com/paperless-ngx/builder/releases/download/jbig2enc-trixie-v${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/qpdf-${QPDF_VERSION}/qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        https://github.com/paperless-ngx/builder/releases/download/ghostscript-${GS_VERSION}/libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
-        https://github.com/paperless-ngx/builder/releases/download/jbig2enc-${JBIG2ENC_VERSION}/jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
-      && echo "Installing qpdf ${QPDF_VERSION}" \
-        && dpkg --install ./libqpdf29_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-        && dpkg --install ./qpdf_${QPDF_VERSION}-1_${TARGETARCH}.deb \
-      && echo "Installing Ghostscript ${GS_VERSION}" \
-        && dpkg --install ./libgs10-common_${GS_VERSION}.dfsg-1_all.deb \
-        && dpkg --install ./libgs10_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
-        && dpkg --install ./ghostscript_${GS_VERSION}.dfsg-1_${TARGETARCH}.deb \
       && echo "Installing jbig2enc" \
         && dpkg --install ./jbig2enc_${JBIG2ENC_VERSION}-1_${TARGETARCH}.deb \
       && echo "Configuring imagemagick" \
@@ -207,14 +188,17 @@ ARG BUILD_PACKAGES="\
   pkg-config"
 
 # hadolint ignore=DL3042
-RUN --mount=type=cache,target=${UV_CACHE_DIR},id=python-cache \
+RUN set -eux \
-  set -eux \
   && echo "Installing build system packages" \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
   && echo "Installing Python requirements" \
     && uv export --quiet --no-dev --all-extras --format requirements-txt --output-file requirements.txt \
-    && uv pip install --system --no-python-downloads --python-preference system --requirements requirements.txt \
+    && uv pip install --no-cache --system --no-python-downloads --python-preference system \
+      --index https://pypi.org/simple \
+      --index https://download.pytorch.org/whl/cpu \
+      --index-strategy unsafe-best-match \
+      --requirements requirements.txt \
   && echo "Installing NLTK data" \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" snowball_data \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" stopwords \
@@ -254,7 +238,8 @@ RUN set -eux \
     && chown --from root:root --changes --recursive paperless:paperless /usr/src/paperless \
   && echo "Collecting static files" \
     && s6-setuidgid paperless python3 manage.py collectstatic --clear --no-input --link \
-    && s6-setuidgid paperless python3 manage.py compilemessages
+    && s6-setuidgid paperless python3 manage.py compilemessages \
+    && /usr/local/bin/deduplicate.py --verbose /usr/src/paperless/static/
 
 VOLUME ["/usr/src/paperless/data", \
         "/usr/src/paperless/media", \
@@ -265,4 +250,4 @@ ENTRYPOINT ["/init"]
 
 EXPOSE 8000
 
-HEALTHCHECK --interval=30s --timeout=10s --retries=5 CMD [ "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000" ]
+HEALTHCHECK --interval=30s --timeout=10s --retries=5 CMD [ "curl", "-fs", "-S", "-L", "--max-time", "2", "http://localhost:8000" ]

README.md

@@ -83,7 +83,7 @@ People interested in continuing the work on paperless-ngx are encouraged to reac
 
 ## Translation
 
-Paperless-ngx is available in many languages that are coordinated on Crowdin. If you want to help out by translating paperless-ngx into your language, please head over to https://crwd.in/paperless-ngx, and thank you! More details can be found in [CONTRIBUTING.md](https://github.com/paperless-ngx/paperless-ngx/blob/main/CONTRIBUTING.md#translating-paperless-ngx).
+Paperless-ngx is available in many languages that are coordinated on Crowdin. If you want to help out by translating paperless-ngx into your language, please head over to https://crowdin.com/project/paperless-ngx, and thank you! More details can be found in [CONTRIBUTING.md](https://github.com/paperless-ngx/paperless-ngx/blob/main/CONTRIBUTING.md#translating-paperless-ngx).
 
 ## Feature Requests
 

docker/compose/docker-compose.ci-test.yml

@@ -1,11 +1,10 @@
-# Docker Compose file for running paperless testing with actual gotenberg
+# Docker Compose file for running paperless testing with actual Gotenberg
 # and Tika containers for a more end to end test of the Tika related functionality
 # Can be used locally or by the CI to start the necessary containers with the
 # correct networking for the tests
-
 services:
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:8.19
+    image: docker.io/gotenberg/gotenberg:8.27
     hostname: gotenberg
     container_name: gotenberg
     network_mode: host
@@ -24,3 +23,24 @@ services:
     container_name: tika
     network_mode: host
     restart: unless-stopped
+  greenmail:
+    image: greenmail/standalone:2.1.8
+    hostname: greenmail
+    container_name: greenmail
+    environment:
+      # Enable only IMAP for now (SMTP available via 3025 if needed later)
+      GREENMAIL_OPTS: >-
+        -Dgreenmail.setup.test.imap -Dgreenmail.users=test@localhost:test -Dgreenmail.users.login=test@localhost -Dgreenmail.verbose
+    ports:
+      - "3143:3143" # IMAP
+    restart: unless-stopped
+  nginx:
+    image: docker.io/nginx:1.29.5-alpine
+    hostname: nginx
+    container_name: nginx
+    ports:
+      - "8080:8080"
+    restart: unless-stopped
+    volumes:
+      - ../../docs/assets:/usr/share/nginx/html/assets:ro
+      - ./test-nginx.conf:/etc/nginx/conf.d/default.conf:ro

docker/compose/docker-compose.env

@@ -32,6 +32,6 @@
 # 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
+# See https://packages.debian.org/search?keywords=tesseract-ocr-&searchon=names
 # for available languages.
 #PAPERLESS_OCR_LANGUAGES=tur ces

docker/compose/docker-compose.mariadb-tika.yml

@@ -16,8 +16,8 @@
 # - Instead of SQLite (default), MariaDB is used as the database server.
 # - Apache Tika and Gotenberg servers are started with paperless and paperless
 #   is configured to use these services. These provide support for consuming
-#   Office documents (Word, Excel, Power Point and their LibreOffice counter-
+#   Office documents (Word, Excel, PowerPoint and their LibreOffice counter-
-#   parts.
+#   parts).
 #
 # To install and update paperless with this file, do the following:
 #
@@ -25,20 +25,17 @@
 #   and '.env' into a folder.
 # - Run 'docker compose pull'.
 # - Run 'docker compose up -d'.
-
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
-
 services:
   broker:
-    image: docker.io/library/redis:7
+    image: docker.io/library/redis:8
     restart: unless-stopped
     volumes:
       - redisdata:/data
-
   db:
-    image: docker.io/library/mariadb:11
+    image: docker.io/library/mariadb:12
     restart: unless-stopped
     volumes:
       - dbdata:/var/lib/mysql
@@ -48,7 +45,6 @@ services:
       MARIADB_USER: paperless
       MARIADB_PASSWORD: paperless
       MARIADB_ROOT_PASSWORD: paperless
-
   webserver:
     image: ghcr.io/paperless-ngx/paperless-ngx:latest
     restart: unless-stopped
@@ -75,9 +71,8 @@ services:
       PAPERLESS_TIKA_ENABLED: 1
       PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
-
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:8.19
+    image: docker.io/gotenberg/gotenberg:8.27
     restart: unless-stopped
     # The gotenberg chromium route is used to convert .eml files. We do not
     # want to allow external content like tracking pixels or even javascript.
@@ -85,11 +80,9 @@ services:
       - "gotenberg"
       - "--chromium-disable-javascript=true"
       - "--chromium-allow-list=file:///tmp/.*"
-
   tika:
     image: docker.io/apache/tika:latest
     restart: unless-stopped
-
 volumes:
   data:
   media:

docker/compose/docker-compose.mariadb.yml

@@ -24,16 +24,14 @@
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
-
 services:
   broker:
-    image: docker.io/library/redis:7
+    image: docker.io/library/redis:8
     restart: unless-stopped
     volumes:
       - redisdata:/data
-
   db:
-    image: docker.io/library/mariadb:11
+    image: docker.io/library/mariadb:12
     restart: unless-stopped
     volumes:
       - dbdata:/var/lib/mysql
@@ -43,7 +41,6 @@ services:
       MARIADB_USER: paperless
       MARIADB_PASSWORD: paperless
       MARIADB_ROOT_PASSWORD: paperless
-
   webserver:
     image: ghcr.io/paperless-ngx/paperless-ngx:latest
     restart: unless-stopped
@@ -65,7 +62,6 @@ services:
       PAPERLESS_DBUSER: paperless # only needed if non-default username
       PAPERLESS_DBPASS: paperless # only needed if non-default password
       PAPERLESS_DBPORT: 3306
-
 volumes:
   data:
   media:

docker/compose/docker-compose.portainer.yml

@@ -25,24 +25,21 @@
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
-
 services:
   broker:
-    image: docker.io/library/redis:7
+    image: docker.io/library/redis:8
     restart: unless-stopped
     volumes:
       - redisdata:/data
-
   db:
-    image: docker.io/library/postgres:17
+    image: docker.io/library/postgres:18
     restart: unless-stopped
     volumes:
-      - pgdata:/var/lib/postgresql/data
+      - pgdata:/var/lib/postgresql
     environment:
       POSTGRES_DB: paperless
       POSTGRES_USER: paperless
       POSTGRES_PASSWORD: paperless
-
   webserver:
     image: ghcr.io/paperless-ngx/paperless-ngx:latest
     restart: unless-stopped
@@ -61,7 +58,6 @@ services:
       PAPERLESS_DBHOST: db
     env_file:
       - stack.env
-
 volumes:
   data:
   media:

docker/compose/docker-compose.postgres-tika.yml

@@ -16,8 +16,8 @@
 # - Instead of SQLite (default), PostgreSQL is used as the database server.
 # - Apache Tika and Gotenberg servers are started with paperless and paperless
 #   is configured to use these services. These provide support for consuming
-#   Office documents (Word, Excel, Power Point and their LibreOffice counter-
+#   Office documents (Word, Excel, PowerPoint and their LibreOffice counter-
-#   parts.
+#   parts).
 #
 # To install and update paperless with this file, do the following:
 #
@@ -28,24 +28,21 @@
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
-
 services:
   broker:
-    image: docker.io/library/redis:7
+    image: docker.io/library/redis:8
     restart: unless-stopped
     volumes:
       - redisdata:/data
-
   db:
-    image: docker.io/library/postgres:17
+    image: docker.io/library/postgres:18
     restart: unless-stopped
     volumes:
-      - pgdata:/var/lib/postgresql/data
+      - pgdata:/var/lib/postgresql
     environment:
       POSTGRES_DB: paperless
       POSTGRES_USER: paperless
       POSTGRES_PASSWORD: paperless
-
   webserver:
     image: ghcr.io/paperless-ngx/paperless-ngx:latest
     restart: unless-stopped
@@ -68,22 +65,18 @@ services:
       PAPERLESS_TIKA_ENABLED: 1
       PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
-
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:8.19
+    image: docker.io/gotenberg/gotenberg:8.27
     restart: unless-stopped
-
     # The gotenberg chromium route is used to convert .eml files. We do not
     # want to allow external content like tracking pixels or even javascript.
     command:
       - "gotenberg"
       - "--chromium-disable-javascript=true"
       - "--chromium-allow-list=file:///tmp/.*"
-
   tika:
     image: docker.io/apache/tika:latest
     restart: unless-stopped
-
 volumes:
   data:
   media:

docker/compose/docker-compose.postgres.yml

@@ -24,24 +24,21 @@
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
-
 services:
   broker:
-    image: docker.io/library/redis:7
+    image: docker.io/library/redis:8
     restart: unless-stopped
     volumes:
       - redisdata:/data
-
   db:
-    image: docker.io/library/postgres:17
+    image: docker.io/library/postgres:18
     restart: unless-stopped
     volumes:
-      - pgdata:/var/lib/postgresql/data
+      - pgdata:/var/lib/postgresql
     environment:
       POSTGRES_DB: paperless
       POSTGRES_USER: paperless
       POSTGRES_PASSWORD: paperless
-
   webserver:
     image: ghcr.io/paperless-ngx/paperless-ngx:latest
     restart: unless-stopped
@@ -59,7 +56,6 @@ services:
     environment:
       PAPERLESS_REDIS: redis://broker:6379
       PAPERLESS_DBHOST: db
-
 volumes:
   data:
   media:

docker/compose/docker-compose.sqlite-tika.yml

@@ -16,8 +16,8 @@
 #
 # - Apache Tika and Gotenberg servers are started with paperless and paperless
 #   is configured to use these services. These provide support for consuming
-#   Office documents (Word, Excel, Power Point and their LibreOffice counter-
+#   Office documents (Word, Excel, PowerPoint and their LibreOffice counter-
-#   parts.
+#   parts).
 #
 # To install and update paperless with this file, do the following:
 #
@@ -28,14 +28,12 @@
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
-
 services:
   broker:
-    image: docker.io/library/redis:7
+    image: docker.io/library/redis:8
     restart: unless-stopped
     volumes:
       - redisdata:/data
-
   webserver:
     image: ghcr.io/paperless-ngx/paperless-ngx:latest
     restart: unless-stopped
@@ -56,22 +54,18 @@ services:
       PAPERLESS_TIKA_ENABLED: 1
       PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
-
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:8.19
+    image: docker.io/gotenberg/gotenberg:8.27
     restart: unless-stopped
-
     # The gotenberg chromium route is used to convert .eml files. We do not
     # want to allow external content like tracking pixels or even javascript.
     command:
       - "gotenberg"
       - "--chromium-disable-javascript=true"
       - "--chromium-allow-list=file:///tmp/.*"
-
   tika:
     image: docker.io/apache/tika:latest
     restart: unless-stopped
-
 volumes:
   data:
   media:

docker/compose/docker-compose.sqlite.yml

@@ -21,14 +21,12 @@
 #
 # For more extensive installation and update instructions, refer to the
 # documentation.
-
 services:
   broker:
-    image: docker.io/library/redis:7
+    image: docker.io/library/redis:8
     restart: unless-stopped
     volumes:
       - redisdata:/data
-
   webserver:
     image: ghcr.io/paperless-ngx/paperless-ngx:latest
     restart: unless-stopped
@@ -44,7 +42,6 @@ services:
     env_file: docker-compose.env
     environment:
       PAPERLESS_REDIS: redis://broker:6379
-
 volumes:
   data:
   media:

docker/compose/test-nginx.conf

@@ -0,0 +1,14 @@
+server {
+    listen 8080;
+    server_name localhost;
+
+    root /usr/share/nginx/html;
+
+    # Enable CORS for test requests
+    add_header 'Access-Control-Allow-Origin' '*' always;
+    add_header 'Access-Control-Allow-Methods' 'GET, HEAD, OPTIONS' always;
+
+    location / {
+        try_files $uri $uri/ =404;
+    }
+}

docker/docker-entrypoint.sh

@@ -1,179 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-# Source: https://github.com/sameersbn/docker-gitlab/
-map_uidgid() {
-	local -r usermap_original_uid=$(id -u paperless)
-	local -r usermap_original_gid=$(id -g paperless)
-	local -r usermap_new_uid=${USERMAP_UID:-$usermap_original_uid}
-	local -r usermap_new_gid=${USERMAP_GID:-${usermap_original_gid:-$usermap_new_uid}}
-	if [[ ${usermap_new_uid} != "${usermap_original_uid}" || ${usermap_new_gid} != "${usermap_original_gid}" ]]; then
-		echo "Mapping UID and GID for paperless:paperless to $usermap_new_uid:$usermap_new_gid"
-		usermod --non-unique --uid "${usermap_new_uid}" paperless
-		groupmod --non-unique --gid "${usermap_new_gid}" paperless
-	fi
-}
-
-map_folders() {
-	# Export these so they can be used in docker-prepare.sh
-	export DATA_DIR="${PAPERLESS_DATA_DIR:-/usr/src/paperless/data}"
-	export MEDIA_ROOT_DIR="${PAPERLESS_MEDIA_ROOT:-/usr/src/paperless/media}"
-	export CONSUME_DIR="${PAPERLESS_CONSUMPTION_DIR:-/usr/src/paperless/consume}"
-}
-
-custom_container_init() {
-	# Mostly borrowed from the LinuxServer.io base image
-	# https://github.com/linuxserver/docker-baseimage-ubuntu/tree/bionic/root/etc/cont-init.d
-	local -r custom_script_dir="/custom-cont-init.d"
-	# Tamper checking.
-	# Don't run files which are owned by anyone except root
-	# Don't run files which are writeable by others
-	if [ -d "${custom_script_dir}" ]; then
-		if [ -n "$(/usr/bin/find "${custom_script_dir}" -maxdepth 1 ! -user root)" ]; then
-			echo "**** Potential tampering with custom scripts detected ****"
-			echo "**** The folder '${custom_script_dir}' must be owned by root ****"
-			return 0
-		fi
-		if [ -n "$(/usr/bin/find "${custom_script_dir}" -maxdepth 1 -perm -o+w)" ]; then
-			echo "**** The folder '${custom_script_dir}' or some of contents have write permissions for others, which is a security risk. ****"
-			echo "**** Please review the permissions and their contents to make sure they are owned by root, and can only be modified by root. ****"
-			return 0
-		fi
-
-		# Make sure custom init directory has files in it
-		if [ -n "$(/bin/ls --almost-all "${custom_script_dir}" 2>/dev/null)" ]; then
-			echo "[custom-init] files found in ${custom_script_dir} executing"
-			# Loop over files in the directory
-			for SCRIPT in "${custom_script_dir}"/*; do
-				NAME="$(basename "${SCRIPT}")"
-				if [ -f "${SCRIPT}" ]; then
-					echo "[custom-init] ${NAME}: executing..."
-					/bin/bash "${SCRIPT}"
-					echo "[custom-init] ${NAME}: exited $?"
-				elif [ ! -f "${SCRIPT}" ]; then
-					echo "[custom-init] ${NAME}: is not a file"
-				fi
-			done
-		else
-			echo "[custom-init] no custom files found exiting..."
-		fi
-
-	fi
-}
-
-initialize() {
-
-	# Setup environment from secrets before anything else
-	# Check for a version of this var with _FILE appended
-	# and convert the contents to the env var value
-	# Source it so export is persistent
-	# shellcheck disable=SC1091
-	source /sbin/env-from-file.sh
-
-	# Change the user and group IDs if needed
-	map_uidgid
-
-	# Check for overrides of certain folders
-	map_folders
-
-	local -r export_dir="/usr/src/paperless/export"
-
-	for dir in \
-		"${export_dir}" \
-		"${DATA_DIR}" "${DATA_DIR}/index" \
-		"${MEDIA_ROOT_DIR}" "${MEDIA_ROOT_DIR}/documents" "${MEDIA_ROOT_DIR}/documents/originals" "${MEDIA_ROOT_DIR}/documents/thumbnails" \
-		"${CONSUME_DIR}"; do
-		if [[ ! -d "${dir}" ]]; then
-			echo "Creating directory ${dir}"
-			mkdir --parents --verbose "${dir}"
-		fi
-	done
-
-	local -r tmp_dir="${PAPERLESS_SCRATCH_DIR:=/tmp/paperless}"
-	echo "Creating directory scratch directory ${tmp_dir}"
-	mkdir --parents --verbose "${tmp_dir}"
-
-	set +e
-	echo "Adjusting permissions of paperless files. This may take a while."
-	chown -R paperless:paperless "${tmp_dir}"
-	for dir in \
-		"${export_dir}" \
-		"${DATA_DIR}" \
-		"${MEDIA_ROOT_DIR}" \
-		"${CONSUME_DIR}"; do
-		find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown --changes paperless:paperless {} +
-	done
-	set -e
-
-	"${gosu_cmd[@]}" /sbin/docker-prepare.sh
-
-	# Leave this last thing
-	custom_container_init
-
-}
-
-install_languages() {
-	echo "Installing languages..."
-
-	read -ra langs <<<"$1"
-
-	# Check that it is not empty
-	if [ ${#langs[@]} -eq 0 ]; then
-		return
-	fi
-
-	# Build list of packages to install
-	to_install=()
-	for lang in "${langs[@]}"; do
-		pkg="tesseract-ocr-$lang"
-
-		if dpkg --status "$pkg" &>/dev/null; then
-			echo "Package $pkg already installed!"
-			continue
-		else
-			to_install+=("$pkg")
-		fi
-	done
-
-	# Use apt only when we install packages
-	if [ ${#to_install[@]} -gt 0 ]; then
-		apt-get update
-
-		for pkg in "${to_install[@]}"; do
-
-			if ! apt-cache show "$pkg" &>/dev/null; then
-				echo "Skipped $pkg: Package not found! :("
-				continue
-			fi
-
-			echo "Installing package $pkg..."
-			if ! apt-get --assume-yes install "$pkg" &>/dev/null; then
-				echo "Could not install $pkg"
-				exit 1
-			fi
-		done
-	fi
-}
-
-echo "Paperless-ngx docker container starting..."
-
-gosu_cmd=(gosu paperless)
-if [ "$(id --user)" == "$(id --user paperless)" ]; then
-	gosu_cmd=()
-fi
-
-# Install additional languages if specified
-if [[ -n "$PAPERLESS_OCR_LANGUAGES" ]]; then
-	install_languages "$PAPERLESS_OCR_LANGUAGES"
-fi
-
-initialize
-
-if [[ "$1" != "/"* ]]; then
-	echo Executing management command "$@"
-	exec "${gosu_cmd[@]}" python3 manage.py "$@"
-else
-	echo Executing "$@"
-	exec "$@"
-fi

docker/install_management_commands.sh

@@ -4,13 +4,13 @@
 
 set -eu
 
-for command in decrypt_documents \
+for command in document_archiver \
-	document_archiver \
 	document_exporter \
 	document_importer \
 	mail_fetcher \
 	document_create_classifier \
 	document_index \
+	document_llmindex \
 	document_renamer \
 	document_retagger \
 	document_thumbnails \

docker/management_script.sh

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py management_command "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py management_command "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py management_command "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-env-file/run

@@ -9,7 +9,7 @@ if find /run/s6/container_environment/*"_FILE" -maxdepth 1 > /dev/null 2>&1; the
 	for FILENAME in /run/s6/container_environment/*; do
 		if [[ "${FILENAME##*/}" == PAPERLESS_*_FILE ]]; then
 			# This should have been named different..
-			if [[ ${FILENAME} == "PAPERLESS_OCR_SKIP_ARCHIVE_FILE" || ${FILENAME} == "PAPERLESS_MODEL_FILE" ]]; then
+			if [[ "${FILENAME##*/}" == "PAPERLESS_OCR_SKIP_ARCHIVE_FILE" || "${FILENAME##*/}" == "PAPERLESS_MODEL_FILE" ]]; then
 				continue
 			fi
 			SECRETFILE=$(cat "${FILENAME}")
@@ -17,6 +17,9 @@ if find /run/s6/container_environment/*"_FILE" -maxdepth 1 > /dev/null 2>&1; the
 			if [[ -f ${SECRETFILE} ]]; then
 				# Trim off trailing _FILE
 				FILESTRIP=${FILENAME//_FILE/}
+				if [[ $(tail -n1 "${SECRETFILE}" | wc -l) != 0 ]]; then
+					echo "${log_prefix} Your secret: ${FILENAME##*/} contains a trailing newline and may not work as expected"
+				fi
 				# Set environment variable
 				cat "${SECRETFILE}" > "${FILESTRIP}"
 				echo "${log_prefix} ${FILESTRIP##*/} set from ${FILENAME##*/}"
@@ -26,5 +29,5 @@ if find /run/s6/container_environment/*"_FILE" -maxdepth 1 > /dev/null 2>&1; the
 		fi
 	done
 else
-		echo "${log_prefix} No *_FILE environment found"
+	echo "${log_prefix} No *_FILE environment found"
 fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-folders/run

@@ -9,25 +9,57 @@ declare -r media_root_dir="${PAPERLESS_MEDIA_ROOT:-/usr/src/paperless/media}"
 declare -r consume_dir="${PAPERLESS_CONSUMPTION_DIR:-/usr/src/paperless/consume}"
 declare -r tmp_dir="${PAPERLESS_SCRATCH_DIR:=/tmp/paperless}"
 
-echo "${log_prefix} Checking for folder existence"
+declare -r main_dirs=(
+	"${export_dir}"
+	"${data_dir}"
+	"${media_root_dir}"
+	"${consume_dir}"
+	"${tmp_dir}"
+)
 
-for dir in \
+declare -r extra_dirs=(
-	"${export_dir}" \
+	"${main_dirs[@]}"
-	"${data_dir}" "${data_dir}/index" \
+	"${data_dir}/index"
-	"${media_root_dir}" "${media_root_dir}/documents" "${media_root_dir}/documents/originals" "${media_root_dir}/documents/thumbnails" \
+	"${media_root_dir}/documents"
-	"${consume_dir}" \
+	"${media_root_dir}/documents/originals"
-	"${tmp_dir}"; do
+	"${media_root_dir}/documents/thumbnails"
-	if [[ ! -d "${dir}" ]]; then
+)
-		mkdir --parents --verbose "${dir}"
-	fi
-done
 
-echo "${log_prefix} Adjusting file and folder permissions"
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
-for dir in \
+	# Non-root mode: Create directories as current user, warn about permission issues
-	"${export_dir}" \
+	echo "${log_prefix} Running in non-root mode, checking directories"
-	"${data_dir}" \
+	current_uid=$(id --user)
-	"${media_root_dir}" \
+	current_gid=$(id --group)
-	"${consume_dir}" \
+
-	"${tmp_dir}"; do
+	for dir in "${extra_dirs[@]}"; do
-	find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown --changes paperless:paperless {} +
+		if [[ ! -d "${dir}" ]]; then
-done
+			mkdir --parents --verbose "${dir}" || echo "${log_prefix} WARNING: Could not create ${dir} - permission denied"
+		fi
+		# Check permissions on existing directories too
+		if [[ -d "${dir}" && ! -w "${dir}" ]]; then
+			echo "${log_prefix} WARNING: No write permission to ${dir}"
+		fi
+	done
+
+	# Warn about ownership issues
+	for dir in "${main_dirs[@]}"; do
+		if [[ -d "${dir}" ]]; then
+			find "${dir}" -not \( -user ${current_uid} -and -group ${current_gid} \) -exec echo "${log_prefix} WARNING: Permission issue on {}: not owned by current user (${current_uid}:${current_gid})" \; 2>/dev/null || echo "${log_prefix} WARNING: Cannot check permissions on ${dir}"
+		fi
+	done
+else
+	# Root mode: Create and fix permissions as needed
+	echo "${log_prefix} Running with root privileges, adjusting directories and permissions"
+
+	# First create directories
+	for dir in "${extra_dirs[@]}"; do
+		if [[ ! -d "${dir}" ]]; then
+			mkdir --parents --verbose "${dir}"
+		fi
+	done
+
+	# Then fix permissions on all directories
+	for dir in "${main_dirs[@]}"; do
+		find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown --changes paperless:paperless {} +
+	done
+fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-migrations/run

@@ -1,20 +1,18 @@
 #!/command/with-contenv /usr/bin/bash
 # shellcheck shell=bash
 declare -r log_prefix="[init-migrations]"
+
 declare -r data_dir="${PAPERLESS_DATA_DIR:-/usr/src/paperless/data}"
 
-(
+echo "${log_prefix} Apply database migrations..."
-	# flock is in place to prevent multiple containers from doing migrations
-	# simultaneously. This also ensures that the db is ready when the command
-	# of the current container starts.
-	flock 200
-	echo "${log_prefix} Apply database migrations..."
-	cd "${PAPERLESS_SRC_DIR}"
 
-	if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+cd "${PAPERLESS_SRC_DIR}"
-		exec python3 manage.py migrate --skip-checks --no-input
-	else
-		exec s6-setuidgid paperless python3 manage.py migrate --skip-checks --no-input
-	fi
 
-) 200>"${data_dir}/migration_lock"
+# The whole migrate, with flock, needs to run as the right user
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	exec s6-setlock -n "${data_dir}/migration_lock" python3 manage.py migrate --skip-checks --no-input
+else
+	exec s6-setuidgid paperless \
+		s6-setlock -n "${data_dir}/migration_lock" \
+		python3 manage.py migrate --skip-checks --no-input
+fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-start/run

@@ -11,9 +11,10 @@ printf "/usr/src/paperless/src" > /var/run/s6/container_environment/PAPERLESS_SR
 echo $(date +%s) > /var/run/s6/container_environment/PAPERLESS_START_TIME_S
 
 # Check if we're starting as a non-root user
-if [ $(id -u) == $(id -u paperless) ]; then
+if [ "$(id --user)" != "0" ]; then
 	printf "true" > /var/run/s6/container_environment/USER_IS_NON_ROOT
-	echo "${log_prefix}  paperless-ngx docker container running under a user"
+	echo "${log_prefix} paperless-ngx docker container running under a user ($(id --user):$(id --group))"
 else
-	echo "${log_prefix}  paperless-ngx docker container starting init as root"
+	printf "/usr/src/paperless" > /var/run/s6/container_environment/HOME
+	echo "${log_prefix} paperless-ngx docker container starting init as root"
 fi

docker/rootfs/etc/s6-overlay/s6-rc.d/init-wait-for-db/run

@@ -1,70 +1,66 @@
 #!/command/with-contenv /usr/bin/bash
 # shellcheck shell=bash
+# vim: set ft=bash ts=4 sw=4 sts=4 et :
 
-declare -r log_prefix="[init-db-wait]"
+set -euo pipefail
+
+declare -r LOG_PREFIX="[init-db-wait]"
+
+declare -ri TIMEOUT=60
+declare -i ATTEMPT=0
+declare -i DELAY=0
+declare -i STARTED_AT=${EPOCHSECONDS:?EPOCHSECONDS var unset}
+
+delay_next_attempt() {
+	local -i elapsed=$(( EPOCHSECONDS - STARTED_AT ))
+	local -ri remaining=$(( TIMEOUT - elapsed ))
+
+	if (( remaining <= 0 )); then
+		echo "${LOG_PREFIX} Unable to connect after $elapsed seconds."
+		exit 1
+	fi
+
+	DELAY+=1
+
+	# clamp to remaining time
+	if (( DELAY > remaining )); then
+		DELAY=$remaining
+	fi
+
+	ATTEMPT+=1
+	echo "${LOG_PREFIX} Attempt $ATTEMPT failed! Trying again in $DELAY seconds..."
+	sleep "$DELAY"
+}
 
 wait_for_postgres() {
-	local attempt_num=1
+	echo "${LOG_PREFIX} Waiting for PostgreSQL to start..."
-	local -r max_attempts=5
-
-	echo "${log_prefix} Waiting for PostgreSQL to start..."
 
 	local -r host="${PAPERLESS_DBHOST:-localhost}"
 	local -r port="${PAPERLESS_DBPORT:-5432}"
 	local -r user="${PAPERLESS_DBUSER:-paperless}"
 
-	# Disable warning, host and port can't have spaces
+	while ! pg_isready -h "${host}" -p "${port}" --username "${user}"; do
-	# shellcheck disable=SC2086
+		delay_next_attempt
-	while [ ! "$(pg_isready -h ${host} -p ${port} --username ${user})" ]; do
-
-		if [ $attempt_num -eq $max_attempts ]; then
-			echo "${log_prefix} Unable to connect to database."
-			exit 1
-		else
-			echo "${log_prefix} Attempt $attempt_num failed! Trying again in 5 seconds..."
-		fi
-
-		attempt_num=$(("$attempt_num" + 1))
-		sleep 5
 	done
-	# Extra in case this is a first start
+	echo "${LOG_PREFIX} Connected to PostgreSQL"
-	sleep 5
-	echo "Connected to PostgreSQL"
 }
 
 wait_for_mariadb() {
-	echo "${log_prefix} Waiting for MariaDB to start..."
+	echo "${LOG_PREFIX} Waiting for MariaDB to start..."
 
-	local -r host="${PAPERLESS_DBHOST:=localhost}"
+	local -r host="${PAPERLESS_DBHOST:-localhost}"
-	local -r port="${PAPERLESS_DBPORT:=3306}"
+	local -r port="${PAPERLESS_DBPORT:-3306}"
 
-	local attempt_num=1
+	while ! mariadb-admin --host="${host}" --port="${port}" --skip-ssl ping --silent >/dev/null 2>&1; do
-	local -r max_attempts=5
+		delay_next_attempt
-
-	# Disable warning, host and port can't have spaces
-	# shellcheck disable=SC2086
-	while ! true > /dev/tcp/$host/$port; do
-
-		if [ $attempt_num -eq $max_attempts ]; then
-			echo "${log_prefix} Unable to connect to database."
-			exit 1
-		else
-			echo "${log_prefix} Attempt $attempt_num failed! Trying again in 5 seconds..."
-
-		fi
-
-		attempt_num=$(("$attempt_num" + 1))
-		sleep 5
 	done
-	echo "Connected to MariaDB"
+	echo "${LOG_PREFIX} Connected to MariaDB"
 }
 
-if [[ "${PAPERLESS_DBENGINE}" == "mariadb" ]]; then
+if [[ "${PAPERLESS_DBENGINE:-}" == "mariadb" ]]; then
-	echo "${log_prefix} Waiting for MariaDB to report ready"
 	wait_for_mariadb
-elif [[ -n "${PAPERLESS_DBHOST}" ]]; then
+elif [[ -n "${PAPERLESS_DBHOST:-}" ]]; then
-	echo "${log_prefix} Waiting for postgresql to report ready"
 	wait_for_postgres
 fi
 
-	echo "${log_prefix} Database is ready"
+echo "${LOG_PREFIX} Database is ready"

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-webserver/run

@@ -10,11 +10,11 @@ export GRANIAN_WORKERS=${GRANIAN_WORKERS:-${PAPERLESS_WEBSERVER_WORKERS:-1}}
 
 # Only set GRANIAN_URL_PATH_PREFIX if PAPERLESS_FORCE_SCRIPT_NAME is set
 if [[ -n "${PAPERLESS_FORCE_SCRIPT_NAME}" ]]; then
-  export GRANIAN_URL_PATH_PREFIX=${PAPERLESS_FORCE_SCRIPT_NAME}
+	export GRANIAN_URL_PATH_PREFIX=${PAPERLESS_FORCE_SCRIPT_NAME}
 fi
 
 if [[ -n "${USER_IS_NON_ROOT}" ]]; then
-  exec granian --interface asginl --ws --loop uvloop "paperless.asgi:application"
+	exec granian --interface asginl --ws --loop uvloop "paperless.asgi:application"
 else
-  exec s6-setuidgid paperless granian --interface asginl --ws --loop uvloop "paperless.asgi:application"
+	exec s6-setuidgid paperless granian --interface asginl --ws --loop uvloop "paperless.asgi:application"
 fi

docker/rootfs/usr/local/bin/convert_mariadb_uuid

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py convert_mariadb_uuid "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py convert_mariadb_uuid "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py convert_mariadb_uuid "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/createsuperuser

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py createsuperuser "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py createsuperuser "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py createsuperuser "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/deduplicate.py

@@ -0,0 +1,167 @@
+#!/usr/bin/env python3
+"""
+File deduplication script that replaces identical files with symlinks.
+Uses SHA256 hashing to identify duplicate files.
+"""
+
+import hashlib
+from collections import defaultdict
+from pathlib import Path
+
+import click
+import humanize
+
+
+def calculate_sha256(filepath: Path) -> str | None:
+    sha256_hash = hashlib.sha256()
+    try:
+        with filepath.open("rb") as f:
+            # Read file in chunks to handle large files efficiently
+            while chunk := f.read(65536):  # 64KB chunks
+                sha256_hash.update(chunk)
+        return sha256_hash.hexdigest()
+    except OSError as e:
+        click.echo(f"Error reading {filepath}: {e}", err=True)
+        return None
+
+
+def find_duplicate_files(directory: Path) -> dict[str, list[Path]]:
+    """
+    Recursively scan directory and group files by their SHA256 hash.
+    Returns a dictionary mapping hash -> list of file paths.
+    """
+    hash_to_files: dict[str, list[Path]] = defaultdict(list)
+
+    for filepath in directory.rglob("*"):
+        # Skip symlinks
+        if filepath.is_symlink():
+            continue
+
+        # Skip if not a regular file
+        if not filepath.is_file():
+            continue
+
+        file_hash = calculate_sha256(filepath)
+        if file_hash:
+            hash_to_files[file_hash].append(filepath)
+
+    # Filter to only return hashes with duplicates
+    return {h: files for h, files in hash_to_files.items() if len(files) > 1}
+
+
+def replace_with_symlinks(
+    duplicate_groups: dict[str, list[Path]],
+    *,
+    dry_run: bool = False,
+) -> tuple[int, int]:
+    """
+    Replace duplicate files with symlinks to the first occurrence.
+    Returns (number_of_files_replaced, space_saved_in_bytes).
+    """
+    total_duplicates = 0
+    space_saved = 0
+
+    for file_hash, file_list in duplicate_groups.items():
+        # Keep the first file as the original, replace others with symlinks
+        original_file = file_list[0]
+        duplicates = file_list[1:]
+
+        click.echo(f"Found {len(duplicates)} duplicate(s) of: {original_file}")
+
+        for duplicate in duplicates:
+            try:
+                # Get file size before deletion
+                file_size = duplicate.stat().st_size
+
+                if dry_run:
+                    click.echo(f"  [DRY RUN] Would replace: {duplicate}")
+                else:
+                    # Remove the duplicate file
+                    duplicate.unlink()
+
+                    # Create relative symlink if possible, otherwise absolute
+                    try:
+                        # Try to create a relative symlink
+                        rel_path = original_file.relative_to(duplicate.parent)
+                        duplicate.symlink_to(rel_path)
+                        click.echo(f"  Replaced: {duplicate} -> {rel_path}")
+                    except ValueError:
+                        # Fall back to absolute path
+                        duplicate.symlink_to(original_file.resolve())
+                        click.echo(f"  Replaced: {duplicate} -> {original_file}")
+
+                    space_saved += file_size
+
+                total_duplicates += 1
+
+            except OSError as e:
+                click.echo(f"  Error replacing {duplicate}: {e}", err=True)
+
+    return total_duplicates, space_saved
+
+
+@click.command()
+@click.argument(
+    "directory",
+    type=click.Path(
+        exists=True,
+        file_okay=False,
+        dir_okay=True,
+        readable=True,
+        path_type=Path,
+    ),
+)
+@click.option(
+    "--dry-run",
+    is_flag=True,
+    help="Show what would be done without making changes",
+)
+@click.option("--verbose", "-v", is_flag=True, help="Show verbose output")
+def deduplicate(directory: Path, *, dry_run: bool, verbose: bool) -> None:
+    """
+    Recursively search DIRECTORY for identical files and replace them with symlinks.
+
+    Uses SHA256 hashing to identify duplicate files. The first occurrence of each
+    unique file is kept, and all duplicates are replaced with symlinks pointing to it.
+    """
+    directory = directory.resolve()
+
+    click.echo(f"Scanning directory: {directory}")
+    if dry_run:
+        click.echo("Running in DRY RUN mode - no changes will be made")
+
+    # Find all duplicate files
+    click.echo("Calculating file hashes...")
+    duplicate_groups = find_duplicate_files(directory)
+
+    if not duplicate_groups:
+        click.echo("No duplicate files found!")
+        return
+
+    total_files = sum(len(files) - 1 for files in duplicate_groups.values())
+    click.echo(
+        f"Found {len(duplicate_groups)} group(s) of duplicates "
+        f"({total_files} files to deduplicate)",
+    )
+
+    if verbose:
+        for file_hash, files in duplicate_groups.items():
+            click.echo(f"Hash: {file_hash}")
+            for f in files:
+                click.echo(f"  - {f}")
+
+    # Replace duplicates with symlinks
+    click.echo("Processing duplicates...")
+    num_replaced, space_saved = replace_with_symlinks(duplicate_groups, dry_run=dry_run)
+
+    # Summary
+    click.echo(
+        f"{'Would replace' if dry_run else 'Replaced'} "
+        f"{num_replaced} duplicate file(s)",
+    )
+    if not dry_run:
+        click.echo(f"Space saved: {humanize.naturalsize(space_saved, binary=True)}")
+
+
+if __name__ == "__main__":
+    deduplicate()

docker/rootfs/usr/local/bin/document_archiver

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_archiver "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_archiver "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_archiver "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_create_classifier

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_create_classifier "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_create_classifier "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_create_classifier "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_exporter

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_exporter "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_exporter "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_exporter "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_fuzzy_match

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_fuzzy_match "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_fuzzy_match "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_fuzzy_match "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_importer

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_importer "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_importer "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_importer "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_index

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_index "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_index "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_index "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_llmindex

@@ -6,9 +6,9 @@ set -e
 cd "${PAPERLESS_SRC_DIR}"
 
 if [[ $(id -u) == 0 ]]; then
-	s6-setuidgid paperless python3 manage.py decrypt_documents "$@"
+	s6-setuidgid paperless python3 manage.py document_llmindex "$@"
 elif [[ $(id -un) == "paperless" ]]; then
-	python3 manage.py decrypt_documents "$@"
+	python3 manage.py document_llmindex "$@"
 else
 	echo "Unknown user."
 fi

docker/rootfs/usr/local/bin/document_renamer

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_renamer "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_renamer "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_renamer "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_retagger

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_retagger "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_retagger "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_retagger "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_sanity_checker

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_sanity_checker "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_sanity_checker "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_sanity_checker "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/document_thumbnails

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py document_thumbnails "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py document_thumbnails "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py document_thumbnails "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/mail_fetcher

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py mail_fetcher "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py mail_fetcher "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py mail_fetcher "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/manage_superuser

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py manage_superuser "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py manage_superuser "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py manage_superuser "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docker/rootfs/usr/local/bin/prune_audit_logs

@@ -5,10 +5,13 @@ set -e
 
 cd "${PAPERLESS_SRC_DIR}"
 
-if [[ $(id -u) == 0 ]]; then
+if [[ -n "${USER_IS_NON_ROOT}" ]]; then
+	python3 manage.py prune_audit_logs "$@"
+elif [[ $(id -u) == 0 ]]; then
 	s6-setuidgid paperless python3 manage.py prune_audit_logs "$@"
 elif [[ $(id -un) == "paperless" ]]; then
 	python3 manage.py prune_audit_logs "$@"
 else
 	echo "Unknown user."
+	exit 1
 fi

docs/administration.md

@@ -62,6 +62,10 @@ copies you created in the steps above.
 
 ## Updating Paperless {#updating}
 
+!!! warning
+
+    Please review the [migration instructions](migration-v3.md) before upgrading Paperless-ngx to v3.0, it includes some breaking changes that require manual intervention before upgrading.
+
 ### Docker Route {#docker-updating}
 
 If a new release of paperless-ngx is available, upgrading depends on how
@@ -179,10 +183,14 @@ following:
 
 ### Database Upgrades
 
-In general, paperless does not require a specific version of PostgreSQL or MariaDB and it is
+Paperless-ngx is compatible with Django-supported versions of PostgreSQL and MariaDB and it is generally
 safe to update them to newer versions. However, you should always take a backup and follow
 the instructions from your database's documentation for how to upgrade between major versions.
 
+!!! note
+
+    As of Paperless-ngx v2.18, the minimum supported version of PostgreSQL is 14.
+
 For PostgreSQL, refer to [Upgrading a PostgreSQL Cluster](https://www.postgresql.org/docs/current/upgrading.html).
 
 For MariaDB, refer to [Upgrading MariaDB](https://mariadb.com/kb/en/upgrading/)
@@ -306,7 +314,7 @@ in dedicated folders according to their nature: `archive`, `originals`,
 If `-sm` or `--split-manifest` is provided, information about document
 will be placed in individual json files, instead of a single JSON file. The main
 manifest.json will still contain application wide information (e.g. tags, correspondent,
-documenttype, etc)
+document type, etc)
 
 If `-z` or `--zip` is provided, the export will be a zip file
 in the target directory, named according to the current local date or the
@@ -333,7 +341,7 @@ must be provided to import. If this value is lost, the export cannot be imported
 The document importer takes the export produced by the [Document
 exporter](#exporter) and imports it into paperless.
 
-The importer works just like the exporter. You point it at a directory,
+The importer works just like the exporter. You point it at a directory or the generated .zip file,
 and the script does the rest of the work:
 
 ```shell
@@ -351,9 +359,6 @@ When you use the provided docker compose script, put the export inside
 the `export` folder in your paperless source directory. Specify
 `../export` as the `source`.
 
-Note that .zip files (as can be generated from the exporter) are not supported. You must unzip them into
-the target directory first.
-
 !!! note
 
     Importing from a previous version of Paperless may work, but for best
@@ -460,6 +465,22 @@ of the index and usually makes queries faster and also ensures that the
 autocompletion works properly. This command is regularly invoked by the
 task scheduler.
 
+### Clearing the database read cache
+
+If the database read cache is enabled, **you must run this command** after making any changes to the database outside the application context.
+This includes operations such as restoring a database backup or executing SQL statements like UPDATE, INSERT, DELETE, ALTER, CREATE, or DROP.
+
+Failing to invalidate the cache after such modifications can lead to stale data being served from the cache, and **may cause data corruption** or inconsistent behavior in the application.
+
+Use the following management command to clear the cache:
+
+```
+python3 manage.py invalidate_cachalot
+```
+
+!!! info
+The database read cache is based on Django-Cachalot. You can refer to their [documentation](https://django-cachalot.readthedocs.io/en/latest/quickstart.html#manage-py-command).
+
 ### Managing filenames {#renamer}
 
 If you use paperless' feature to
@@ -563,39 +584,9 @@ document.
     documents, such as encrypted PDF documents. The archiver will skip over
     these documents each time it sees them.
 
-### Managing encryption {#encryption}
-
-!!! warning
-
-    Encryption was removed in [paperless-ng 0.9](changelog.md#paperless-ng-090)
-    because it did not really provide any additional security, the passphrase
-    was stored in a configuration file on the same system as the documents.
-    Furthermore, the entire text content of the documents is stored plain in
-    the database, even if your documents are encrypted. Filenames are not
-    encrypted as well. Finally, the web server provides transparent access to
-    your encrypted documents.
-
-    Consider running paperless on an encrypted filesystem instead, which
-    will then at least provide security against physical hardware theft.
-
-#### Enabling encryption
-
-Enabling encryption is no longer supported.
-
-#### Disabling encryption
-
-Basic usage to disable encryption of your document store:
-
-(Note: If `PAPERLESS_PASSPHRASE` isn't set already, you need to specify
-it here)
-
-```
-decrypt_documents [--passphrase SECR3TP4SSPHRA$E]
-```
-
 ### Detecting duplicates {#fuzzy_duplicate}
 
-Paperless already catches and prevents upload of exactly matching documents,
+Paperless-ngx already catches and warns of exactly matching documents,
 however a new scan of an existing document may not produce an exact bit for bit
 duplicate. But the content should be exact or close, allowing detection.
 

docs/advanced_usage.md

@@ -179,6 +179,7 @@ variables:
 | ---------------------------- | ---------------------------------------------- |
 | `DOCUMENT_ID`                | Database primary key of the document           |
 | `DOCUMENT_FILE_NAME`         | Formatted filename, not including paths        |
+| `DOCUMENT_TYPE`              | The document type (if any)                     |
 | `DOCUMENT_CREATED`           | Date & time when document created              |
 | `DOCUMENT_MODIFIED`          | Date & time when document was last modified    |
 | `DOCUMENT_ADDED`             | Date & time when document was added            |
@@ -261,6 +262,10 @@ your files differently, you can do that by adjusting the
 or using [storage paths (see below)](#storage-paths). Paperless adds the
 correct file extension e.g. `.pdf`, `.jpg` automatically.
 
+When a document has file versions, each version uses the same naming rules and
+storage path resolution as any other document file, with an added version suffix
+such as `_v1`, `_v2`, etc.
+
 This variable allows you to configure the filename (folders are allowed)
 using placeholders. For example, configuring this to
 
@@ -352,6 +357,8 @@ If paperless detects that two documents share the same filename,
 paperless will automatically append `_01`, `_02`, etc to the filename.
 This happens if all the placeholders in a filename evaluate to the same
 value.
+For versioned files, this counter is appended after the version suffix
+(for example `statement_v2_01.pdf`).
 
 If there are any errors in the placeholders included in `PAPERLESS_FILENAME_FORMAT`,
 paperless will fall back to using the default naming scheme instead.
@@ -430,8 +437,138 @@ This allows for complex logic to be included in the format, including [logical s
 and [filters](https://jinja.palletsprojects.com/en/3.1.x/templates/#id11) to manipulate the [variables](#filename-format-variables)
 provided. The template is provided as a string, potentially multiline, and rendered into a single line.
 
-In addition, the entire Document instance is available to be utilized in a more advanced way, as well as some variables which only make sense to be accessed
+In addition, a limited `document` object is available for advanced templates.
-with more complex logic.
+This object includes common metadata fields such as `id`, `pk`, `title`, `content`, `page_count`, `created`, `added`, `modified`, `mime_type`,
+`checksum`, `archive_checksum`, `archive_serial_number`, `filename`, `archive_filename`, and `original_filename`.
+Related values are available as nested objects with limited fields, for example document.correspondent.name, etc.
+
+#### Custom Jinja2 Filters
+
+##### Custom Field Access
+
+The `get_cf_value` filter retrieves a value from custom field data with optional default fallback.
+
+###### Syntax
+
+```jinja2
+{{ custom_fields | get_cf_value('field_name') }}
+{{ custom_fields | get_cf_value('field_name', 'default_value') }}
+```
+
+###### Parameters
+
+-   `custom_fields`: This _must_ be the provided custom field data
+-   `name` (str): Name of the custom field to retrieve
+-   `default` (str, optional): Default value to return if field is not found or has no value
+
+###### Returns
+
+-   `str | None`: The field value, default value, or `None` if neither exists
+
+###### Examples
+
+```jinja2
+<!-- Basic usage -->
+{{ custom_fields | get_cf_value('department') }}
+
+<!-- With default value -->
+{{ custom_fields | get_cf_value('phone', 'Not provided') }}
+```
+
+##### Datetime Formatting
+
+The `datetime` filter formats a datetime string or datetime object using Python's strftime formatting.
+
+###### Syntax
+
+```jinja2
+{{ datetime_value | datetime('%Y-%m-%d %H:%M:%S') }}
+```
+
+###### Parameters
+
+-   `value` (str | datetime): Date/time value to format (strings will be parsed automatically)
+-   `format` (str): Python strftime format string
+
+###### Returns
+
+-   `str`: Formatted datetime string
+
+###### Examples
+
+```jinja2
+<!-- Format datetime object -->
+{{ created | datetime('%B %d, %Y at %I:%M %p') }}
+<!-- Output: "January 15, 2024 at 02:30 PM" -->
+
+<!-- Custom formatting -->
+{{ custom_fields | get_cf_value('Date Field') | datetime('%A, %B %d, %Y') }}
+<!-- Output: "Monday, January 15, 2024" -->
+```
+
+See the [strftime format code documentation](https://docs.python.org/3.13/library/datetime.html#strftime-and-strptime-format-codes)
+for the possible codes and their meanings.
+
+##### Date Localization {#date-localization}
+
+The `localize_date` filter formats a date or datetime object into a localized string using Babel internationalization.
+This takes into account the provided locale for translation. Since this must be used on a date or datetime object,
+you must access the field directly, i.e. `document.created`.
+An ISO string can also be provided to control the output format.
+
+###### Syntax
+
+```jinja2
+{{ date_value | localize_date('medium', 'en_US') }}
+{{ datetime_value | localize_date('short', 'fr_FR') }}
+```
+
+###### Parameters
+
+-   `value` (date | datetime | str): Date, datetime object or ISO string to format (datetime should be timezone-aware)
+-   `format` (str): Format type - either a Babel preset ('short', 'medium', 'long', 'full') or custom pattern
+-   `locale` (str): Locale code for localization (e.g., 'en_US', 'fr_FR', 'de_DE')
+
+###### Returns
+
+-   `str`: Localized, formatted date string
+
+###### Examples
+
+```jinja2
+<!-- Preset formats -->
+{{ document.created | localize_date('short', 'en_US') }}
+<!-- Output: "1/15/24" -->
+
+{{ document.created | localize_date('medium', 'en_US') }}
+<!-- Output: "Jan 15, 2024" -->
+
+{{ document.created | localize_date('long', 'en_US') }}
+<!-- Output: "January 15, 2024" -->
+
+{{ document.created | localize_date('full', 'en_US') }}
+<!-- Output: "Monday, January 15, 2024" -->
+
+<!-- Different locales -->
+{{ document.created | localize_date('medium', 'fr_FR') }}
+<!-- Output: "15 janv. 2024" -->
+
+{{ document.created | localize_date('medium', 'de_DE') }}
+<!-- Output: "15.01.2024" -->
+
+<!-- Custom patterns -->
+{{ document.created | localize_date('dd/MM/yyyy', 'en_GB') }}
+<!-- Output: "15/01/2024" -->
+```
+
+See the [supported format codes](https://unicode.org/reports/tr35/tr35-dates.html#Date_Format_Patterns) for more options.
+
+### Format Presets
+
+-   **short**: Abbreviated format (e.g., "1/15/24")
+-   **medium**: Medium-length format (e.g., "Jan 15, 2024")
+-   **long**: Long format with full month name (e.g., "January 15, 2024")
+-   **full**: Full format including day of week (e.g., "Monday, January 15, 2024")
 
 #### Additional Variables
 
@@ -645,7 +782,6 @@ At this time, the library utilized for detection of barcodes supports the follow
 -   QR Code
 -   SQ Code
 
-You may check for updates on the [zbar library homepage](https://github.com/mchehab/zbar).
 For usage in Paperless, the type of barcode does not matter, only the contents of it.
 
 For how to enable barcode usage, see [the configuration](configuration.md#barcodes).
@@ -654,9 +790,17 @@ below.
 
 ### Document Splitting {#document-splitting}
 
-When enabled, Paperless will look for a barcode with the configured value and create a new document
+If document splitting is enabled, Paperless splits _after_ a separator barcode by default.
-starting from the next page. The page with the barcode on it will _not_ be retained. It
+This means:
-is expected to be a page existing only for triggering the split.
+
+-   any page containing the configured separator barcode starts a new document, starting with the **next** page
+-   pages containing the separator barcode are discarded
+
+This is intended for dedicated separator sheets such as PATCH-T pages.
+
+If [`PAPERLESS_CONSUMER_BARCODE_RETAIN_SPLIT_PAGES`](configuration.md#PAPERLESS_CONSUMER_BARCODE_RETAIN_SPLIT_PAGES)
+is enabled, the page containing the separator barcode is retained instead. In this mode,
+each page containing the separator barcode becomes the **first** page of a new document.
 
 ### Archive Serial Number Assignment
 
@@ -665,8 +809,9 @@ archive serial number, allowing quick reference back to the original, paper docu
 
 If document splitting via barcode is also enabled, documents will be split when an ASN
 barcode is located. However, differing from the splitting, the page with the
-barcode _will_ be retained. This allows application of a barcode to any page, including
+barcode _will_ be retained. Each detected ASN barcode starts a new document _starting with
-one which holds data to keep in the document.
+that page_. This allows placing ASN barcodes on content pages that should remain part of
+the document.
 
 ### Tag Assignment
 
@@ -676,6 +821,27 @@ See the relevant settings [`PAPERLESS_CONSUMER_ENABLE_TAG_BARCODE`](configuratio
 and [`PAPERLESS_CONSUMER_TAG_BARCODE_MAPPING`](configuration.md#PAPERLESS_CONSUMER_TAG_BARCODE_MAPPING)
 for more information.
 
+#### Splitting on Tag Barcodes
+
+By default, tag barcodes only assign tags to documents without splitting them. However,
+you can enable document splitting on tag barcodes by setting
+[`PAPERLESS_CONSUMER_TAG_BARCODE_SPLIT`](configuration.md#PAPERLESS_CONSUMER_TAG_BARCODE_SPLIT)
+to `true`.
+
+When enabled, documents will be split at pages containing tag barcodes, similar to how
+ASN barcodes work. Key features:
+
+-   The page with the tag barcode is **retained** in the resulting document
+-   **Each split document extracts its own tags** - only tags on pages within that document are assigned
+-   Multiple tag barcodes can trigger multiple splits in the same document
+-   Works seamlessly with ASN barcodes - each split document gets its own ASN and tags
+
+This is useful for batch scanning where you place tag barcode pages between different
+documents to both separate and categorize them in a single operation.
+
+**Example:** A 6-page scan with TAG:invoice on page 3 and TAG:receipt on page 5 will create
+three documents: pages 1-2 (no tags), pages 3-4 (tagged "invoice"), and pages 5-6 (tagged "receipt").
+
 ## Automatic collation of double-sided documents {#collate}
 
 !!! note
@@ -722,8 +888,8 @@ followed by the even pages.
 
 It's important that the scan files get consumed in the correct order, and one at a time.
 You therefore need to make sure that Paperless is running while you upload the files into
-the directory; and if you're using [polling](configuration.md#polling), make sure that
+the directory; and if you're using polling, make sure that
-`CONSUMER_POLLING` is set to a value lower than it takes for the second scan to appear,
+`CONSUMER_POLLING_INTERVAL` is set to a value lower than it takes for the second scan to appear,
 like 5-10 or even lower.
 
 Another thing that might happen is that you start a double sided scan, but then forget

docs/api.md

@@ -1,4 +1,4 @@
-# The REST API
+# REST API
 
 Paperless-ngx now ships with a fully-documented REST API and a browsable
 web interface to explore it. The API browsable interface is available at
@@ -8,7 +8,7 @@ Further documentation is provided here for some endpoints and features.
 
 ## Authorization
 
-The REST api provides four different forms of authentication.
+The REST api provides five different forms of authentication.
 
 1.  Basic authentication
 
@@ -52,6 +52,14 @@ The REST api provides four different forms of authentication.
     [configuration](configuration.md#PAPERLESS_ENABLE_HTTP_REMOTE_USER_API)),
     you can authenticate against the API using Remote User auth.
 
+5.  Headless OIDC via [`django-allauth`](https://codeberg.org/allauth/django-allauth)
+
+    `django-allauth` exposes API endpoints under `api/auth/` which enable tools
+    like third-party apps to authenticate with social accounts that are
+    configured. See
+    [here](advanced_usage.md#openid-connect-and-social-authentication) for more
+    information on social accounts.
+
 ## Searching for documents
 
 Full text searching is available on the `/api/documents/` endpoint. Two
@@ -132,7 +140,7 @@ use cases:
 
 5. Documents with a custom field "address" (text) that is empty:
 
-    `?custom_field_query=["OR", ["address", "isnull", true], ["address", "exact", ""]]`
+    `?custom_field_query=["OR", [["address", "isnull", true], ["address", "exact", ""]]]`
 
 6. Documents that don't have a field called "foo":
 
@@ -192,8 +200,8 @@ The endpoint supports the following optional form fields:
 -   `tags`: Similar to correspondent. Specify this multiple times to
     have multiple tags added to the document.
 -   `archive_serial_number`: An optional archive serial number to set.
--   `custom_fields`: An array of custom field ids to assign (with an empty
+-   `custom_fields`: Either an array of custom field ids to assign (with an empty
-    value) to the document.
+    value) to the document or an object mapping field id -> value.
 
 The endpoint will immediately return HTTP 200 if the document consumption
 process was started successfully, with the UUID of the consumption task
@@ -203,6 +211,21 @@ However, querying the tasks endpoint with the returned UUID e.g.
 `/api/tasks/?task_id={uuid}` will provide information on the state of the
 consumption including the ID of a created document if consumption succeeded.
 
+## Document Versions
+
+Document versions are file-level versions linked to one root document.
+
+-   Root document metadata (title, tags, correspondent, document type, storage path, custom fields, permissions) remains shared.
+-   Version-specific file data (file, mime type, checksums, archive info, extracted text content) belongs to the selected/latest version.
+
+Version-aware endpoints:
+
+-   `GET /api/documents/{id}/`: returns root document data; `content` resolves to latest version content by default. Use `?version={version_id}` to resolve content for a specific version.
+-   `PATCH /api/documents/{id}/`: content updates target the selected version (`?version={version_id}`) or latest version by default; non-content metadata updates target the root document.
+-   `GET /api/documents/{id}/download/`, `GET /api/documents/{id}/preview/`, `GET /api/documents/{id}/thumb/`, `GET /api/documents/{id}/metadata/`: accept `?version={version_id}`.
+-   `POST /api/documents/{id}/update_version/`: uploads a new version using multipart form field `document` and optional `version_label`.
+-   `DELETE /api/documents/{root_id}/versions/{version_id}/`: deletes a non-root version.
+
 ## Permissions
 
 All objects (documents, tags, etc.) allow setting object-level permissions
@@ -282,6 +305,25 @@ The following methods are supported:
         -   `"merge": true or false` (defaults to false)
     -   The `merge` flag determines if the supplied permissions will overwrite all existing permissions (including
         removing them) or be merged with existing permissions.
+-   `edit_pdf`
+    -   Requires `parameters`:
+        -   `"doc_ids": [DOCUMENT_ID]` A list of a single document ID to edit.
+        -   `"operations": [OPERATION, ...]` A list of operations to perform on the documents. Each operation is a dictionary
+            with the following keys:
+            -   `"page": PAGE_NUMBER` The page number to edit (1-based).
+            -   `"rotate": DEGREES` Optional rotation in degrees (90, 180, 270).
+            -   `"doc": OUTPUT_DOCUMENT_INDEX` Optional index of the output document for split operations.
+    -   Optional `parameters`:
+        -   `"delete_original": true` to delete the original documents after editing.
+        -   `"update_document": true` to add the edited PDF as a new version of the root document.
+        -   `"include_metadata": true` to copy metadata from the original document to the edited document.
+-   `remove_password`
+    -   Requires `parameters`:
+        -   `"password": "PASSWORD_STRING"` The password to remove from the PDF documents.
+    -   Optional `parameters`:
+        -   `"update_document": true` to add the password-less PDF as a new version of the root document.
+        -   `"delete_original": true` to delete the original document after editing.
+        -   `"include_metadata": true` to copy metadata from the original document to the new password-less document.
 -   `merge`
     -   No additional `parameters` required.
     -   The ordering of the merged document is determined by the list of IDs.
@@ -327,41 +369,38 @@ operations, using the endpoint: `/api/bulk_edit_objects/`, which requires a json
 
 ## API Versioning
 
-The REST API is versioned since Paperless-ngx 1.3.0.
+The REST API is versioned.
 
 -   Versioning ensures that changes to the API don't break older
     clients.
 -   Clients specify the specific version of the API they wish to use
     with every request and Paperless will handle the request using the
     specified API version.
--   Even if the underlying data model changes, older API versions will
+-   Even if the underlying data model changes, supported older API
-    always serve compatible data.
+    versions continue to serve compatible data.
--   If no version is specified, Paperless will serve version 1 to ensure
+-   If no version is specified, Paperless serves the configured default
-    compatibility with older clients that do not request a specific API
+    API version (currently `10`).
-    version.
+-   Supported API versions are currently `9` and `10`.
 
 API versions are specified by submitting an additional HTTP `Accept`
 header with every request:
 
 ```
-Accept: application/json; version=6
+Accept: application/json; version=10
 ```
 
-If an invalid version is specified, Paperless 1.3.0 will respond with
+If an invalid version is specified, Paperless responds with
-"406 Not Acceptable" and an error message in the body. Earlier
+`406 Not Acceptable` and an error message in the body.
-versions of Paperless will serve API version 1 regardless of whether a
-version is specified via the `Accept` header.
 
 If a client wishes to verify whether it is compatible with any given
 server, the following procedure should be performed:
 
-1.  Perform an _authenticated_ request against any API endpoint. If the
+1.  Perform an _authenticated_ request against any API endpoint. The
-    server is on version 1.3.0 or newer, the server will add two custom
+    server will add two custom headers to the response:
-    headers to the response:
 
     ```
-    X-Api-Version: 2
+    X-Api-Version: 10
-    X-Version: 1.3.0
+    X-Version: <server-version>
     ```
 
 2.  Determine whether the client is compatible with this server based on
@@ -413,3 +452,19 @@ Initial API version.
     list of strings. When creating or updating a custom field value of a
     document for a select type custom field, the value should be the `id` of
     the option whereas previously was the index of the option.
+
+#### Version 8
+
+-   The user field of document notes now returns a simplified user object
+    rather than just the user ID.
+
+#### Version 9
+
+-   The document `created` field is now a date, not a datetime. The
+    `created_date` field is considered deprecated and will be removed in a
+    future version.
+
+#### Version 10
+
+-   The `show_on_dashboard` and `show_in_sidebar` fields of saved views have been
+    removed. Relevant settings are now stored in the UISettings model.

docs/assets/extra.css

@@ -1,13 +1,31 @@
-:root > * {
+:root>* {
-    --md-primary-fg-color: #17541f;
+    --paperless-green: #17541f;
-    --md-primary-fg-color--dark: #17541f;
+    --paperless-green-accent: #2b8a38;
-    --md-primary-fg-color--light: #17541f;
+    --md-primary-fg-color: var(--paperless-green);
-    --md-accent-fg-color: #2b8a38;
+    --md-primary-fg-color--dark: var(--paperless-green);
+    --md-primary-fg-color--light: var(--paperless-green-accent);
+    --md-accent-fg-color: var(--paperless-green-accent);
     --md-typeset-a-color: #21652a;
 }
 
+.md-header,
+.md-tabs {
+    background-color: var(--paperless-green);
+    color: #fff;
+}
+
+.md-tabs__link {
+    color: rgba(255, 255, 255, 0.82);
+}
+
+.md-tabs__link:hover,
+.md-tabs__link--active {
+    color: #fff;
+}
+
 [data-md-color-scheme="slate"] {
     --md-hue: 222;
+    --md-default-bg-color: hsla(var(--md-hue), 15%, 10%, 1);
 }
 
 @media (min-width: 768px) {
@@ -69,8 +87,8 @@ h4 code {
 }
 
 /* Hide config vars from sidebar, toc and move the border on mobile case their hidden */
-.md-nav.md-nav--secondary .md-nav__item .md-nav__link[href*="PAPERLESS_"],
+.md-nav.md-nav--secondary .md-nav__item:has(> .md-nav__link[href*="PAPERLESS_"]),
-.md-nav.md-nav--secondary .md-nav__item .md-nav__link[href*="USERMAP_"] {
+.md-nav.md-nav--secondary .md-nav__item:has(> .md-nav__link[href*="USERMAP_"]) {
     display: none;
 }
 
@@ -83,18 +101,3 @@ h4 code {
         border-top: .05rem solid var(--md-default-fg-color--lightest);
     }
 }
-
-/* Show search shortcut key */
-[data-md-toggle="search"]:not(:checked) ~ .md-header .md-search__form::after {
-    position: absolute;
-    top: .3rem;
-    right: .3rem;
-    display: block;
-    padding: .1rem .4rem;
-    color: var(--md-default-fg-color--lighter);
-    font-weight: bold;
-    font-size: .8rem;
-    border: .05rem solid var(--md-default-fg-color--lighter);
-    border-radius: .1rem;
-    content: "/";
-  }

docs/configuration.md

@@ -50,112 +50,208 @@ matcher.
 
 ### Database
 
-#### [`PAPERLESS_DBENGINE=<engine_name>`](#PAPERLESS_DBENGINE) {#PAPERLESS_DBENGINE}
+By default, Paperless uses **SQLite** with a database stored at `data/db.sqlite3`.
+For multi-user or higher-throughput deployments, **PostgreSQL** (recommended) or
+**MariaDB** can be used instead by setting [`PAPERLESS_DBENGINE`](#PAPERLESS_DBENGINE)
+and the relevant connection variables.
 
-: Optional, gives the ability to choose Postgres or MariaDB for
+#### [`PAPERLESS_DBENGINE=<engine>`](#PAPERLESS_DBENGINE) {#PAPERLESS_DBENGINE}
-database engine. Available options are `postgresql` and
-`mariadb`.
 
-    Default is `postgresql`.
+: Specifies the database engine to use. Accepted values are `sqlite`, `postgresql`,
+and `mariadb`.
+
+    Defaults to `sqlite` if not set.
+
+    PostgreSQL and MariaDB both require [`PAPERLESS_DBHOST`](#PAPERLESS_DBHOST) to be
+    set. SQLite does not use any other connection variables; the database file is always
+    located at `<PAPERLESS_DATA_DIR>/db.sqlite3`.
 
     !!! warning
-
+        Using MariaDB comes with some caveats.
-        Using MariaDB comes with some caveats. See [MySQL Caveats](advanced_usage.md#mysql-caveats).
+        See [MySQL Caveats](advanced_usage.md#mysql-caveats).
 
 #### [`PAPERLESS_DBHOST=<hostname>`](#PAPERLESS_DBHOST) {#PAPERLESS_DBHOST}
 
-: By default, sqlite is used as the database backend. This can be
+: Hostname of the PostgreSQL or MariaDB database server. Required when
-changed here.
+`PAPERLESS_DBENGINE` is `postgresql` or `mariadb`.
-
-    Set PAPERLESS_DBHOST and another database will be used instead of
-    sqlite.
 
 #### [`PAPERLESS_DBPORT=<port>`](#PAPERLESS_DBPORT) {#PAPERLESS_DBPORT}
 
-: Adjust port if necessary.
+: Port to use when connecting to PostgreSQL or MariaDB.
 
-    Default is 5432.
+    Defaults to `5432` for PostgreSQL and `3306` for MariaDB.
 
 #### [`PAPERLESS_DBNAME=<name>`](#PAPERLESS_DBNAME) {#PAPERLESS_DBNAME}
 
-: Database name in PostgreSQL or MariaDB.
+: Name of the PostgreSQL or MariaDB database to connect to.
 
-    Defaults to "paperless".
+    Defaults to `paperless`.
 
-#### [`PAPERLESS_DBUSER=<name>`](#PAPERLESS_DBUSER) {#PAPERLESS_DBUSER}
+#### [`PAPERLESS_DBUSER=<user>`](#PAPERLESS_DBUSER) {#PAPERLESS_DBUSER}
 
-: Database user in PostgreSQL or MariaDB.
+: Username for authenticating with the PostgreSQL or MariaDB database.
 
-    Defaults to "paperless".
+    Defaults to `paperless`.
 
 #### [`PAPERLESS_DBPASS=<password>`](#PAPERLESS_DBPASS) {#PAPERLESS_DBPASS}
 
-: Database password for PostgreSQL or MariaDB.
+: Password for the PostgreSQL or MariaDB database user.
 
-    Defaults to "paperless".
+    Defaults to `paperless`.
 
-#### [`PAPERLESS_DBSSLMODE=<mode>`](#PAPERLESS_DBSSLMODE) {#PAPERLESS_DBSSLMODE}
+#### [`PAPERLESS_DB_OPTIONS=<options>`](#PAPERLESS_DB_OPTIONS) {#PAPERLESS_DB_OPTIONS}
 
-: SSL mode to use when connecting to PostgreSQL or MariaDB.
+: Advanced database connection options as a semicolon-delimited key-value string.
+Keys and values are separated by `=`. Dot-notation produces nested option
+dictionaries; for example, `pool.max_size=20` sets
+`OPTIONS["pool"]["max_size"] = 20`.
 
-    See [the official documentation about
+    Options specified here are merged over the engine defaults. Unrecognised keys
-    sslmode for PostgreSQL](https://www.postgresql.org/docs/current/libpq-ssl.html).
+    are passed through to the underlying database driver without validation, so a
+    typo will be silently ignored rather than producing an error.
 
-    See [the official documentation about
+    Refer to your database driver's documentation for the full set of accepted keys:
-    sslmode for MySQL and MariaDB](https://dev.mysql.com/doc/refman/8.0/en/connection-options.html#option_general_ssl-mode).
 
-    *Note*: SSL mode values differ between PostgreSQL and MariaDB.
+    - PostgreSQL: [libpq connection parameters](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-PARAMKEYWORDS)
+    - MariaDB: [MariaDB Connector/Python](https://mariadb.com/kb/en/mariadb-connector-python/)
+    - SQLite: [SQLite PRAGMA statements](https://www.sqlite.org/pragma.html)
 
-    Default is `prefer` for PostgreSQL and `PREFERRED` for MariaDB.
+    !!! note "PostgreSQL connection pooling"
 
-#### [`PAPERLESS_DBSSLROOTCERT=<ca-path>`](#PAPERLESS_DBSSLROOTCERT) {#PAPERLESS_DBSSLROOTCERT}
+        Pool size is controlled via `pool.min_size` and `pool.max_size`. When
+        configuring pooling, ensure your PostgreSQL `max_connections` is large enough
+        to handle all pool connections across all workers:
+        `(web_workers + celery_workers) * pool.max_size + safety_margin`.
 
-: SSL root certificate path
+    **Examples:**
 
-    See [the official documentation about
+    ```bash title="PostgreSQL: require SSL, set a custom CA certificate, and limit the pool size"
-    sslmode for PostgreSQL](https://www.postgresql.org/docs/current/libpq-ssl.html).
+    PAPERLESS_DB_OPTIONS="sslmode=require;sslrootcert=/certs/ca.pem;pool.max_size=5"
-    Changes path of `root.crt`.
+    ```
 
-    See [the official documentation about
+    ```bash title="MariaDB: require SSL with a custom CA certificate"
-    sslmode for MySQL and MariaDB](https://dev.mysql.com/doc/refman/8.0/en/connection-options.html#option_general_ssl-ca).
+    PAPERLESS_DB_OPTIONS="ssl_mode=REQUIRED;ssl.ca=/certs/ca.pem"
+    ```
 
-    Defaults to unset, using the documented path in the home directory.
+    ```bash title="SQLite: set a busy timeout of 30 seconds"
+    # PostgreSQL: set a connection timeout
+    PAPERLESS_DB_OPTIONS="connect_timeout=10"
+    ```
 
-#### [`PAPERLESS_DBSSLCERT=<client-cert-path>`](#PAPERLESS_DBSSLCERT) {#PAPERLESS_DBSSLCERT}
+#### ~~[`PAPERLESS_DBSSLMODE`](#PAPERLESS_DBSSLMODE)~~ {#PAPERLESS_DBSSLMODE}
 
-: SSL client certificate path
+!!! failure "Removed in v3"
 
-    See [the official documentation about
+    Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
-    sslmode for PostgreSQL](https://www.postgresql.org/docs/current/libpq-ssl.html).
 
-    See [the official documentation about
+    ```bash title="PostgreSQL"
-    sslmode for MySQL and MariaDB](https://dev.mysql.com/doc/refman/8.0/en/connection-options.html#option_general_ssl-cert).
+    PAPERLESS_DB_OPTIONS="sslmode=require"
+    ```
 
-    Changes path of `postgresql.crt`.
+    ```bash title="MariaDB"
+    PAPERLESS_DB_OPTIONS="ssl_mode=REQUIRED"
+    ```
 
-    Defaults to unset, using the documented path in the home directory.
+#### ~~[`PAPERLESS_DBSSLROOTCERT`](#PAPERLESS_DBSSLROOTCERT)~~ {#PAPERLESS_DBSSLROOTCERT}
 
-#### [`PAPERLESS_DBSSLKEY=<client-cert-key>`](#PAPERLESS_DBSSLKEY) {#PAPERLESS_DBSSLKEY}
+!!! failure "Removed in v3"
 
-: SSL client key path
+    Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
 
-    See [the official documentation about
+    ```bash title="PostgreSQL"
-    sslmode for PostgreSQL](https://www.postgresql.org/docs/current/libpq-ssl.html).
+    PAPERLESS_DB_OPTIONS="sslrootcert=/path/to/ca.pem"
+    ```
 
-    See [the official documentation about
+    ```bash title="MariaDB"
-    sslmode for MySQL and MariaDB](https://dev.mysql.com/doc/refman/8.0/en/connection-options.html#option_general_ssl-key).
+    PAPERLESS_DB_OPTIONS="ssl.ca=/path/to/ca.pem"
+    ```
 
-    Changes path of `postgresql.key`.
+#### ~~[`PAPERLESS_DBSSLCERT`](#PAPERLESS_DBSSLCERT)~~ {#PAPERLESS_DBSSLCERT}
 
-    Defaults to unset, using the documented path in the home directory.
+!!! failure "Removed in v3"
 
-#### [`PAPERLESS_DB_TIMEOUT=<int>`](#PAPERLESS_DB_TIMEOUT) {#PAPERLESS_DB_TIMEOUT}
+    Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
 
-: Amount of time for a database connection to wait for the database to
+    ```bash title="PostgreSQL"
-unlock. Mostly applicable for sqlite based installation. Consider changing
+    PAPERLESS_DB_OPTIONS="sslcert=/path/to/client.crt"
-to postgresql if you are having concurrency problems with sqlite.
+    ```
 
-    Defaults to unset, keeping the Django defaults.
+    ```bash title="MariaDB"
+    PAPERLESS_DB_OPTIONS="ssl.cert=/path/to/client.crt"
+    ```
+
+#### ~~[`PAPERLESS_DBSSLKEY`](#PAPERLESS_DBSSLKEY)~~ {#PAPERLESS_DBSSLKEY}
+
+!!! failure "Removed in v3"
+
+    Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
+
+    ```bash title="PostgreSQL"
+    PAPERLESS_DB_OPTIONS="sslkey=/path/to/client.key"
+    ```
+
+    ```bash title="MariaDB"
+    PAPERLESS_DB_OPTIONS="ssl.key=/path/to/client.key"
+    ```
+
+#### ~~[`PAPERLESS_DB_TIMEOUT`](#PAPERLESS_DB_TIMEOUT)~~ {#PAPERLESS_DB_TIMEOUT}
+
+!!! failure "Removed in v3"
+
+    Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
+
+    ```bash title="SQLite"
+    PAPERLESS_DB_OPTIONS="timeout=30"
+    ```
+
+    ```bash title="PostgreSQL or MariaDB"
+    PAPERLESS_DB_OPTIONS="connect_timeout=30"
+    ```
+
+#### ~~[`PAPERLESS_DB_POOLSIZE`](#PAPERLESS_DB_POOLSIZE)~~ {#PAPERLESS_DB_POOLSIZE}
+
+!!! failure "Removed in v3"
+
+    Use [`PAPERLESS_DB_OPTIONS`](#PAPERLESS_DB_OPTIONS) instead.
+
+    ```bash
+    PAPERLESS_DB_OPTIONS="pool.max_size=10"
+    ```
+
+#### [`PAPERLESS_DB_READ_CACHE_ENABLED=<bool>`](#PAPERLESS_DB_READ_CACHE_ENABLED) {#PAPERLESS_DB_READ_CACHE_ENABLED}
+
+: Caches the database read query results into Redis. This can significantly improve application response times by caching database queries, at the cost of slightly increased memory usage.
+
+    Defaults to `false`.
+
+    !!! danger
+
+        **Do not modify the database outside the application while it is running.**
+        This includes actions such as restoring a backup, upgrading the database, or performing manual inserts. All external modifications must be done **only when the application is stopped**.
+        After making any such changes, you **must invalidate the DB read cache** using the `invalidate_cachalot` management command.
+
+#### [`PAPERLESS_READ_CACHE_TTL=<int>`](#PAPERLESS_READ_CACHE_TTL) {#PAPERLESS_READ_CACHE_TTL}
+
+: Specifies how long (in seconds) read data should be cached.
+
+    Allowed values are between `1` (one second) and `31536000` (one year). Defaults to `3600` (one hour).
+
+    !!! warning
+
+        A high TTL increases memory usage over time. Memory may be used until end of TTL, even if the cache is invalidated with the `invalidate_cachalot` command.
+
+In case of an out-of-memory (OOM) situation, Redis may stop accepting new data — including cache entries, scheduled tasks, and documents to consume.
+If your system has limited RAM, consider configuring a dedicated Redis instance for the read cache, with a memory limit and the eviction policy set to `allkeys-lru`.
+For more details, refer to the [Redis eviction policy documentation](https://redis.io/docs/latest/develop/reference/eviction/), and see the `PAPERLESS_READ_CACHE_REDIS_URL` setting to specify a separate Redis broker.
+
+#### [`PAPERLESS_READ_CACHE_REDIS_URL=<url>`](#PAPERLESS_READ_CACHE_REDIS_URL) {#PAPERLESS_READ_CACHE_REDIS_URL}
+
+: Defines the Redis instance used for the read cache.
+
+    Defaults to `None`.
+
+    !!! Note
+    If this value is not set, the same Redis instance used for scheduled tasks will be used for caching as well.
 
 ## Optional Services
 
@@ -200,7 +296,7 @@ and watch out for indentation if editing the YAML file.
 
 ### Email Parsing
 
-#### [`PAPERLESS_EMAIL_PARSE_DEFAULT_LAYOUT=<int>`(#PAPERLESS_EMAIL_PARSE_DEFAULT_LAYOUT) {#PAPERLESS_EMAIL_PARSE_DEFAULT_LAYOUT}
+#### [`PAPERLESS_EMAIL_PARSE_DEFAULT_LAYOUT=<int>`](#PAPERLESS_EMAIL_PARSE_DEFAULT_LAYOUT) {#PAPERLESS_EMAIL_PARSE_DEFAULT_LAYOUT}
 
 : The default layout to use for emails that are consumed as documents. Must be one of the integer choices below. Note that mail
 rules can specify this setting, thus this fallback is used for the default selection and for .eml files consumed by other means.
@@ -598,7 +694,7 @@ system. See the corresponding
 
 : Sync groups from the third party authentication system (e.g. OIDC) to Paperless-ngx. When enabled, users will be added or removed from groups based on their group membership in the third party authentication system. Groups must already exist in Paperless-ngx and have the same name as in the third party authentication system. Groups are updated upon logging in via the third party authentication system, see the corresponding [django-allauth documentation](https://docs.allauth.org/en/dev/socialaccount/signals.html).
 
-: In order to pass groups from the authentication system you will need to update your [PAPERLESS_SOCIALACCOUNT_PROVIDERS](#PAPERLESS_SOCIALACCOUNT_PROVIDERS) setting by adding a top-level "SCOPES" setting which includes "groups", e.g.:
+: In order to pass groups from the authentication system you will need to update your [PAPERLESS_SOCIALACCOUNT_PROVIDERS](#PAPERLESS_SOCIALACCOUNT_PROVIDERS) setting by adding a top-level "SCOPES" setting which includes "groups", or the custom groups claim configured in [`PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS_CLAIM`](#PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS_CLAIM) e.g.:
 
     ```json
     {"openid_connect":{"SCOPE": ["openid","profile","email","groups"]...
@@ -606,6 +702,12 @@ system. See the corresponding
 
     Defaults to False
 
+#### [`PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS_CLAIM=<str>`](#PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS_CLAIM) {#PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS_CLAIM}
+
+: Allows you to define a custom groups claim. See [PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS](#PAPERLESS_SOCIAL_ACCOUNT_SYNC_GROUPS) which is required for this setting to take effect.
+
+    Defaults to "groups"
+
 #### [`PAPERLESS_SOCIAL_ACCOUNT_DEFAULT_GROUPS=<comma-separated-list>`](#PAPERLESS_SOCIAL_ACCOUNT_DEFAULT_GROUPS) {#PAPERLESS_SOCIAL_ACCOUNT_DEFAULT_GROUPS}
 
 : A list of group names that users who signup via social accounts will be added to upon signup. Groups listed here must already exist.
@@ -629,7 +731,13 @@ If both the [PAPERLESS_ACCOUNT_DEFAULT_GROUPS](#PAPERLESS_ACCOUNT_DEFAULT_GROUPS
 
 !!! note
 
-    If you do not have a working email server set up you should set this to 'none'.
+    If you do not have a working email server set up this will be set to 'none'.
+
+#### [`PAPERLESS_ACCOUNT_EMAIL_UNKNOWN_ACCOUNTS=<bool>`](#PAPERLESS_ACCOUNT_EMAIL_UNKNOWN_ACCOUNTS) {#PAPERLESS_ACCOUNT_EMAIL_UNKNOWN_ACCOUNTS}
+
+: See the relevant [django-allauth documentation](https://docs.allauth.org/en/latest/account/configuration.html)
+
+    Defaults to True (from allauth)
 
 #### [`PAPERLESS_DISABLE_REGULAR_LOGIN=<bool>`](#PAPERLESS_DISABLE_REGULAR_LOGIN) {#PAPERLESS_DISABLE_REGULAR_LOGIN}
 
@@ -920,21 +1028,10 @@ paperless will process in parallel on a single document.
         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
+    If unset, paperless uses `max(floor(cpu_count / PAPERLESS_TASK_WORKERS), 1)`
-    count, with a slight favor towards threads per worker:
+    threads per worker. The idea behind this is that as long as there are enough cores,
-
+    the total number of threads should less than or equal to the total number of (logical)
-    | CPU core count | Workers | Threads |
+    CPU cores.
-    | -------------- | ------- | ------- |
-    | > 1            | > 1     | > 1     |
-    | > 2            | > 2     | > 1     |
-    | > 4            | > 2     | > 2     |
-    | > 6            | > 2     | > 3     |
-    | > 8            | > 2     | > 4     |
-    | > 12           | > 3     | > 4     |
-    | > 16           | > 4     | > 4     |
-
-    If you only specify PAPERLESS_TASK_WORKERS, paperless will adjust
-    PAPERLESS_THREADS_PER_WORKER automatically.
 
 #### [`PAPERLESS_WORKER_TIMEOUT=<num>`](#PAPERLESS_WORKER_TIMEOUT) {#PAPERLESS_WORKER_TIMEOUT}
 
@@ -958,7 +1055,23 @@ still perform some basic text pre-processing before matching.
 
 : See also `PAPERLESS_NLTK_DIR`.
 
-    Defaults to 1.
+    Defaults to true, enabling the feature.
+
+#### [`PAPERLESS_DATE_PARSER_LANGUAGES=<lang>`](#PAPERLESS_DATE_PARSER_LANGUAGES) {#PAPERLESS_DATE_PARSER_LANGUAGES}
+
+Specifies which language Paperless should use when parsing dates from documents.
+
+    This should be a language code supported by the dateparser library,
+    for example: "en", or a combination such as "en+de".
+    Locales are also supported (e.g., "en-AU").
+    Multiple languages can be combined using "+", for example: "en+de" or "en-AU+de".
+    For valid values, refer to the list of supported languages and locales in the [dateparser documentation](https://dateparser.readthedocs.io/en/latest/supported_locales.html).
+
+    Set this to match the languages in which most of your documents are written.
+    If not set, Paperless will attempt to infer the language(s) from the OCR configuration (`PAPERLESS_OCR_LANGUAGE`).
+
+!!! note
+This format differs from the `PAPERLESS_OCR_LANGUAGE` setting, which uses ISO 639-2 codes (3 letters, e.g., "eng+deu" for Tesseract OCR).
 
 #### [`PAPERLESS_EMAIL_TASK_CRON=<cron expression>`](#PAPERLESS_EMAIL_TASK_CRON) {#PAPERLESS_EMAIL_TASK_CRON}
 
@@ -989,17 +1102,27 @@ should be a valid crontab(5) expression describing when to run.
 
 #### [`PAPERLESS_SANITY_TASK_CRON=<cron expression>`](#PAPERLESS_SANITY_TASK_CRON) {#PAPERLESS_SANITY_TASK_CRON}
 
-: Configures the scheduled sanity checker frequency.
+: Configures the scheduled sanity checker frequency. The value should be a
+valid crontab(5) expression describing when to run.
 
 : If set to the string "disable", the sanity checker will not run automatically.
 
     Defaults to `30 0 * * sun` or Sunday at 30 minutes past midnight.
 
+#### [`PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON=<cron expression>`](#PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON) {#PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON}
+
+: Configures the scheduled workflow check frequency. The value should be a
+valid crontab(5) expression describing when to run.
+
+: If set to the string "disable", scheduled workflows will not run.
+
+    Defaults to `5 */1 * * *` or every hour at 5 minutes past the hour.
+
 #### [`PAPERLESS_ENABLE_COMPRESSION=<bool>`](#PAPERLESS_ENABLE_COMPRESSION) {#PAPERLESS_ENABLE_COMPRESSION}
 
 : Enables compression of the responses from the webserver.
 
-: Defaults to 1, enabling compression.
+: Defaults to true, enabling compression.
 
     !!! note
 
@@ -1057,15 +1180,16 @@ be used with caution!
 
 ## Document Consumption {#consume_config}
 
-#### [`PAPERLESS_CONSUMER_DISABLE=<bool>`](#PAPERLESS_CONSUMER_DISABLE) {#PAPERLESS_CONSUMER_DISABLE}
+#### [`PAPERLESS_CONSUMER_DISABLE`](#PAPERLESS_CONSUMER_DISABLE) {#PAPERLESS_CONSUMER_DISABLE}
 
-: Completely disable the directory-based consumer in docker. If you don't plan to consume documents
+: If set (to anything), this completely disables the directory-based consumer in docker. If you don't plan to consume documents
 via the consumption directory, you can disable the consumer to save resources.
 
 #### [`PAPERLESS_CONSUMER_DELETE_DUPLICATES=<bool>`](#PAPERLESS_CONSUMER_DELETE_DUPLICATES) {#PAPERLESS_CONSUMER_DELETE_DUPLICATES}
 
-: When the consumer detects a duplicate document, it will not touch
+: As of version 3.0 Paperless-ngx allows duplicate documents to be consumed by default, _except_ when
-the original document. This default behavior can be changed here.
+this setting is enabled. When enabled, Paperless will check if a document with the same hash already
+exists in the system and delete the duplicate file from the consumption directory without consuming it.
 
     Defaults to false.
 
@@ -1093,29 +1217,45 @@ don't exist yet.
 
 #### [`PAPERLESS_CONSUMER_IGNORE_PATTERNS=<json>`](#PAPERLESS_CONSUMER_IGNORE_PATTERNS) {#PAPERLESS_CONSUMER_IGNORE_PATTERNS}
 
-: By default, paperless ignores certain files and folders in the
+: Additional regex patterns for files to ignore in the consumption directory. Patterns are matched against filenames only (not full paths)
-consumption directory, such as system files created by the Mac OS
+using Python's `re.match()`, which anchors at the start of the filename.
-or hidden folders some tools use to store data.
 
-    This can be adjusted by configuring a custom json array with
+    See the [watchfiles documentation](https://watchfiles.helpmanual.io/api/filters/#watchfiles.BaseFilter.ignore_entity_patterns)
-    patterns to exclude.
 
-    For example, `.DS_STORE/*` will ignore any files found in a folder
+    This setting is for additional patterns beyond the built-in defaults. Common system files and directories are already ignored automatically.
-    named `.DS_STORE`, including `.DS_STORE/bar.pdf` and `foo/.DS_STORE/bar.pdf`
+    The patterns will be compiled via Python's standard `re` module.
 
-    A pattern like `._*` will ignore anything starting with `._`, including:
+    Example custom patterns:
-    `._foo.pdf` and `._bar/foo.pdf`
 
-    Defaults to
+    ```json
-    `[".DS_Store", ".DS_STORE", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini", "@eaDir/*", "Thumbs.db"]`.
+    ["^temp_", "\\.bak$", "^~"]
+    ```
 
-#### [`PAPERLESS_CONSUMER_BARCODE_SCANNER=<string>`](#PAPERLESS_CONSUMER_BARCODE_SCANNER) {#PAPERLESS_CONSUMER_BARCODE_SCANNER}
+    This would ignore:
 
-: Sets the barcode scanner used for barcode functionality.
+    - Files starting with `temp_` (e.g., `temp_scan.pdf`)
+    - Files ending with `.bak` (e.g., `document.pdf.bak`)
+    - Files starting with `~` (e.g., `~$document.docx`)
 
-    Currently, "PYZBAR" (the default) or "ZXING" might be selected.
+    Defaults to `[]` (empty list, uses only built-in defaults).
-    If you have problems that your Barcodes/QR-Codes are not detected
+
-    (especially with bad scan quality and/or small codes), try the other one.
+    The default ignores are `[.DS_Store, .DS_STORE, ._*, desktop.ini, Thumbs.db]` and cannot be overridden.
+
+#### [`PAPERLESS_CONSUMER_IGNORE_DIRS=<json>`](#PAPERLESS_CONSUMER_IGNORE_DIRS) {#PAPERLESS_CONSUMER_IGNORE_DIRS}
+
+: Additional directory names to ignore in the consumption directory. Directories matching these names (and all their contents) will be skipped.
+
+    This setting is for additional directories beyond the built-in defaults. Matching is done by directory name only, not full path.
+
+    Example:
+
+    ```json
+    ["temp", "incoming", ".hidden"]
+    ```
+
+    Defaults to `[]` (empty list, uses only built-in defaults).
+
+    The default ignores are `[.stfolder, .stversions, .localized, @eaDir, .Spotlight-V100, .Trashes, __MACOSX]` and cannot be overridden.
 
 #### [`PAPERLESS_PRE_CONSUME_SCRIPT=<filename>`](#PAPERLESS_PRE_CONSUME_SCRIPT) {#PAPERLESS_PRE_CONSUME_SCRIPT}
 
@@ -1206,48 +1346,48 @@ within your documents.
 
     Defaults to false.
 
-### Polling {#polling}
+#### [`PAPERLESS_CONSUMER_POLLING_INTERVAL=<num>`](#PAPERLESS_CONSUMER_POLLING_INTERVAL) {#PAPERLESS_CONSUMER_POLLING_INTERVAL}
 
-#### [`PAPERLESS_CONSUMER_POLLING=<num>`](#PAPERLESS_CONSUMER_POLLING) {#PAPERLESS_CONSUMER_POLLING}
+: Configures how the consumer detects new files in the consumption directory.
 
-: If paperless won't find documents added to your consume folder, it
+    When set to `0` (default), paperless uses native filesystem notifications for efficient, immediate detection of new files.
-might not be able to automatically detect filesystem changes. In
-that case, specify a polling interval in seconds here, which will
-then cause paperless to periodically check your consumption
-directory for changes. This will also disable listening for file
-system changes with `inotify`.
 
-    Defaults to 0, which disables polling and uses filesystem
+    When set to a positive number, paperless polls the consumption directory at that interval in seconds. Use polling for network filesystems (NFS, SMB/CIFS) where native notifications may not work reliably.
-    notifications.
 
-#### [`PAPERLESS_CONSUMER_POLLING_RETRY_COUNT=<num>`](#PAPERLESS_CONSUMER_POLLING_RETRY_COUNT) {#PAPERLESS_CONSUMER_POLLING_RETRY_COUNT}
+    Defaults to 0.
 
-: If consumer polling is enabled, sets the maximum number of times
+#### [`PAPERLESS_CONSUMER_STABILITY_DELAY=<num>`](#PAPERLESS_CONSUMER_STABILITY_DELAY) {#PAPERLESS_CONSUMER_STABILITY_DELAY}
-paperless will check for a file to remain unmodified. If a file's
-modification time and size are identical for two consecutive checks, it
-will be consumed.
 
-    Defaults to 5.
+: Sets the time in seconds that a file must remain unchanged (same size and modification time) before paperless will begin consuming it.
 
-#### [`PAPERLESS_CONSUMER_POLLING_DELAY=<num>`](#PAPERLESS_CONSUMER_POLLING_DELAY) {#PAPERLESS_CONSUMER_POLLING_DELAY}
+    Increase this value if you experience issues with files being consumed before they are fully written, particularly on slower network storage or
+    with certain scanner quirks
 
-: If consumer polling is enabled, sets the delay in seconds between
+    Defaults to 5.0 seconds.
-each check (above) paperless will do while waiting for a file to
-remain unmodified.
 
-    Defaults to 5.
+## Workflow webhooks
 
-### iNotify {#inotify}
+#### [`PAPERLESS_WEBHOOKS_ALLOWED_SCHEMES=<str>`](#PAPERLESS_WEBHOOKS_ALLOWED_SCHEMES) {#PAPERLESS_WEBHOOKS_ALLOWED_SCHEMES}
 
-#### [`PAPERLESS_CONSUMER_INOTIFY_DELAY=<num>`](#PAPERLESS_CONSUMER_INOTIFY_DELAY) {#PAPERLESS_CONSUMER_INOTIFY_DELAY}
+: A comma-separated list of allowed schemes for webhooks. This setting
+controls which URL schemes are permitted for webhook URLs.
 
-: Sets the time in seconds the consumer will wait for additional
+    Defaults to `http,https`.
-events from inotify before the consumer will consider a file ready
-and begin consumption. Certain scanners or network setups may
-generate multiple events for a single file, leading to multiple
-consumers working on the same file. Configure this to prevent that.
 
-    Defaults to 0.5 seconds.
+#### [`PAPERLESS_WEBHOOKS_ALLOWED_PORTS=<str>`](#PAPERLESS_WEBHOOKS_ALLOWED_PORTS) {#PAPERLESS_WEBHOOKS_ALLOWED_PORTS}
+
+: A comma-separated list of allowed ports for webhooks. This setting
+controls which ports are permitted for webhook URLs. For example, if you
+set this to `80,443`, webhooks will only be sent to URLs that use these
+ports.
+
+    Defaults to empty list, which allows all ports.
+
+#### [`PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS=<bool>`](#PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS) {#PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS}
+
+: If set to false, webhooks cannot be sent to internal URLs (e.g., localhost).
+
+    Defaults to true, which allows internal requests.
 
 ## Incoming Mail {#incoming_mail}
 
@@ -1444,6 +1584,20 @@ assigns or creates tags if a properly formatted barcode is detected.
 
     Please refer to the Python regex documentation for more information.
 
+#### [`PAPERLESS_CONSUMER_TAG_BARCODE_SPLIT=<bool>`](#PAPERLESS_CONSUMER_TAG_BARCODE_SPLIT) {#PAPERLESS_CONSUMER_TAG_BARCODE_SPLIT}
+
+: Enables splitting of documents on tag barcodes, similar to how ASN barcodes work.
+
+    When enabled, documents will be split into separate PDFs at pages containing
+    tag barcodes that match the configured `PAPERLESS_CONSUMER_TAG_BARCODE_MAPPING`
+    patterns. The page with the tag barcode will be retained in the new document.
+
+    Each split document will have the detected tags assigned to it.
+
+    This only has an effect if `PAPERLESS_CONSUMER_ENABLE_TAG_BARCODE` is also enabled.
+
+    Defaults to false.
+
 ## Audit Trail
 
 #### [`PAPERLESS_AUDIT_LOG_ENABLED=<bool>`](#PAPERLESS_AUDIT_LOG_ENABLED) {#PAPERLESS_AUDIT_LOG_ENABLED}
@@ -1504,6 +1658,16 @@ processing. This only has an effect if
 
     Defaults to `0 1 * * *`, once per day.
 
+## Share links
+
+#### [`PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON=<cron expression>`](#PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON) {#PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON}
+
+: Controls how often Paperless-ngx removes expired share link bundles (and their generated ZIP archives).
+
+: If set to the string "disable", expired bundles are not cleaned up automatically.
+
+    Defaults to `0 2 * * *`, once per day at 02:00.
+
 ## Binaries
 
 There are a few external software packages that Paperless expects to
@@ -1659,6 +1823,11 @@ started by the container.
 
 : Path to an image file in the /media/logo directory, must include 'logo', e.g. `/logo/Atari_logo.svg`
 
+!!! note
+
+    The logo file will be viewable by anyone with access to the Paperless instance login page,
+    so consider your choice of logo carefully and removing exif data from images before uploading.
+
 #### [`PAPERLESS_ENABLE_UPDATE_CHECK=<bool>`](#PAPERLESS_ENABLE_UPDATE_CHECK) {#PAPERLESS_ENABLE_UPDATE_CHECK}
 
 !!! note
@@ -1670,7 +1839,7 @@ started by the container.
 
 ## Email sending
 
-Setting an SMTP server for the backend will allow you to reset your
+Setting an SMTP server for the backend will allow you to use the Email workflow action, send documents from the UI as well as reset your
 password. All of these options come from their similarly-named [Django settings](https://docs.djangoproject.com/en/4.2/ref/settings/#email-host)
 
 #### [`PAPERLESS_EMAIL_HOST=<str>`](#PAPERLESS_EMAIL_HOST) {#PAPERLESS_EMAIL_HOST}
@@ -1700,3 +1869,87 @@ password. All of these options come from their similarly-named [Django settings]
 #### [`PAPERLESS_EMAIL_USE_SSL=<bool>`](#PAPERLESS_EMAIL_USE_SSL) {#PAPERLESS_EMAIL_USE_SSL}
 
 : Defaults to false.
+
+## Remote OCR
+
+#### [`PAPERLESS_REMOTE_OCR_ENGINE=<str>`](#PAPERLESS_REMOTE_OCR_ENGINE) {#PAPERLESS_REMOTE_OCR_ENGINE}
+
+: The remote OCR engine to use. Currently only Azure AI is supported as "azureai".
+
+    Defaults to None, which disables remote OCR.
+
+#### [`PAPERLESS_REMOTE_OCR_API_KEY=<str>`](#PAPERLESS_REMOTE_OCR_API_KEY) {#PAPERLESS_REMOTE_OCR_API_KEY}
+
+: The API key to use for the remote OCR engine.
+
+    Defaults to None.
+
+#### [`PAPERLESS_REMOTE_OCR_ENDPOINT=<str>`](#PAPERLESS_REMOTE_OCR_ENDPOINT) {#PAPERLESS_REMOTE_OCR_ENDPOINT}
+
+: The endpoint to use for the remote OCR engine. This is required for Azure AI.
+
+    Defaults to None.
+
+## AI {#ai}
+
+#### [`PAPERLESS_AI_ENABLED=<bool>`](#PAPERLESS_AI_ENABLED) {#PAPERLESS_AI_ENABLED}
+
+: Enables the AI features in Paperless. This includes the AI-based
+suggestions. This setting is required to be set to true in order to use the AI features.
+
+    Defaults to false.
+
+#### [`PAPERLESS_AI_LLM_EMBEDDING_BACKEND=<str>`](#PAPERLESS_AI_LLM_EMBEDDING_BACKEND) {#PAPERLESS_AI_LLM_EMBEDDING_BACKEND}
+
+: The embedding backend to use for RAG. This can be either "openai" or "huggingface".
+
+    Defaults to None.
+
+#### [`PAPERLESS_AI_LLM_EMBEDDING_MODEL=<str>`](#PAPERLESS_AI_LLM_EMBEDDING_MODEL) {#PAPERLESS_AI_LLM_EMBEDDING_MODEL}
+
+: The model to use for the embedding backend for RAG. This can be set to any of the embedding models supported by the current embedding backend. If not supplied, defaults to "text-embedding-3-small" for OpenAI and "sentence-transformers/all-MiniLM-L6-v2" for Huggingface.
+
+    Defaults to None.
+
+#### [`PAPERLESS_AI_LLM_BACKEND=<str>`](#PAPERLESS_AI_LLM_BACKEND) {#PAPERLESS_AI_LLM_BACKEND}
+
+: The AI backend to use. This can be either "openai" or "ollama". If set to "ollama", the AI
+features will be run locally on your machine. If set to "openai", the AI features will be run
+using the OpenAI API. This setting is required to be set to use the AI features.
+
+    Defaults to None.
+
+    !!! note
+
+        The OpenAI API is a paid service. You will need to set up an OpenAI account and
+        will be charged for usage incurred by Paperless-ngx features and your document data
+        will (of course) be sent to the OpenAI API. Paperless-ngx does not endorse the use of the
+        OpenAI API in any way.
+
+        Refer to the OpenAI terms of service, and use at your own risk.
+
+#### [`PAPERLESS_AI_LLM_MODEL=<str>`](#PAPERLESS_AI_LLM_MODEL) {#PAPERLESS_AI_LLM_MODEL}
+
+: The model to use for the AI backend, i.e. "gpt-3.5-turbo", "gpt-4" or any of the models supported by the
+current backend. If not supplied, defaults to "gpt-3.5-turbo" for OpenAI and "llama3.1" for Ollama.
+
+    Defaults to None.
+
+#### [`PAPERLESS_AI_LLM_API_KEY=<str>`](#PAPERLESS_AI_LLM_API_KEY) {#PAPERLESS_AI_LLM_API_KEY}
+
+: The API key to use for the AI backend. This is required for the OpenAI backend (optional for others).
+
+    Defaults to None.
+
+#### [`PAPERLESS_AI_LLM_ENDPOINT=<str>`](#PAPERLESS_AI_LLM_ENDPOINT) {#PAPERLESS_AI_LLM_ENDPOINT}
+
+: The endpoint / url to use for the AI backend. This is required for the Ollama backend (optional for others).
+
+    Defaults to None.
+
+#### [`PAPERLESS_AI_LLM_INDEX_TASK_CRON=<cron expression>`](#PAPERLESS_AI_LLM_INDEX_TASK_CRON) {#PAPERLESS_AI_LLM_INDEX_TASK_CRON}
+
+: Configures the schedule to update the AI embeddings of text content and metadata for all documents. Only performed if
+AI is enabled and the LLM embedding backend is set.
+
+    Defaults to `10 2 * * *`, once per day.

docs/development.md

@@ -75,13 +75,13 @@ first-time setup.
 4.  Install the Python dependencies:
 
     ```bash
-    $ uv sync --group dev
+    uv sync --group dev
     ```
 
 5.  Install pre-commit hooks:
 
     ```bash
-    $ uv run pre-commit install
+    uv run prek install
     ```
 
 6.  Apply migrations and create a superuser (also can be done via the web UI) for your development instance:
@@ -89,21 +89,21 @@ first-time setup.
     ```bash
     # src/
 
-    $ uv run manage.py migrate
+    uv run manage.py migrate
-    $ uv run manage.py createsuperuser
+    uv run manage.py createsuperuser
     ```
 
 7.  You can now either ...
 
-    -   install redis or
+    -   install Redis or
 
-    -   use the included `scripts/start_services.sh` to use docker to fire
+    -   use the included `scripts/start_services.sh` to use Docker to fire
-        up a redis instance (and some other services such as tika,
+        up a Redis instance (and some other services such as Tika,
-        gotenberg and a database server) or
+        Gotenberg and a database server) or
 
-    -   spin up a bare redis container
+    -   spin up a bare Redis container
 
-        ```
+        ```bash
         docker run -d -p 6379:6379 --restart unless-stopped redis:latest
         ```
 
@@ -118,18 +118,18 @@ work well for development, but you can use whatever you want.
 Configure the IDE to use the `src/`-folder as the base source folder.
 Configure the following launch configurations in your IDE:
 
--   `python3 manage.py runserver`
+-   `uv run manage.py runserver`
--   `python3 manage.py document_consumer`
+-   `uv run manage.py document_consumer`
--   `celery --app paperless worker -l DEBUG` (or any other log level)
+-   `uv run celery --app paperless worker -l DEBUG` (or any other log level)
 
 To start them all:
 
 ```bash
 # src/
 
-$ python3 manage.py runserver & \
+uv run manage.py runserver & \
-  python3 manage.py document_consumer & \
+  uv run manage.py document_consumer & \
-  celery --app paperless worker -l DEBUG
+  uv run celery --app paperless worker -l DEBUG
 ```
 
 You might need the front end to test your back end code.
@@ -140,14 +140,14 @@ To build the front end once use this command:
 ```bash
 # src-ui/
 
-$ pnpm install
+pnpm install
-$ ng build --configuration production
+pnpm ng build --configuration production
 ```
 
 ### Testing
 
 -   Run `pytest` in the `src/` directory to execute all tests. This also
-    generates a HTML coverage report. When runnings test, `paperless.conf`
+    generates a HTML coverage report. When running tests, `paperless.conf`
     is loaded as well. However, the tests rely on the default
     configuration. This is not ideal. But for now, make sure no settings
     except for DEBUG are overridden when testing.
@@ -175,7 +175,7 @@ To add a new development package `uv add --dev <package>`
 
 ## Front end development
 
-The front end is built using AngularJS. In order to get started, you need Node.js (version 14.15+) and
+The front end is built using AngularJS. In order to get started, you need Node.js (version 24+) and
 `pnpm`.
 
 !!! note
@@ -199,7 +199,7 @@ The front end is built using AngularJS. In order to get started, you need Node.j
 4.  You can launch a development server by running:
 
     ```bash
-    ng serve
+    pnpm ng serve
     ```
 
     This will automatically update whenever you save. However, in-place
@@ -217,21 +217,21 @@ commit. See [above](#code-formatting-with-pre-commit-hooks) for installation ins
 command such as
 
 ```bash
-$ git ls-files -- '*.ts' | xargs pre-commit run prettier --files
+git ls-files -- '*.ts' | xargs uv run prek run prettier --files
 ```
 
 Front end testing uses Jest and Playwright. Unit tests and e2e tests,
 respectively, can be run non-interactively with:
 
 ```bash
-$ ng test
+pnpm ng test
-$ npx playwright test
+pnpm playwright test
 ```
 
 Playwright also includes a UI which can be run with:
 
 ```bash
-$ npx playwright test --ui
+pnpm playwright test --ui
 ```
 
 ### Building the frontend
@@ -239,7 +239,7 @@ $ npx playwright test --ui
 In order to build the front end and serve it as part of Django, execute:
 
 ```bash
-$ ng build --configuration production
+pnpm ng build --configuration production
 ```
 
 This will build the front end and put it in a location from which the
@@ -312,10 +312,10 @@ end (such as error messages).
 -   The source language of the project is "en_US".
 -   Localization files end up in the folder `src/locale/`.
 -   In order to extract strings from the application, call
-    `python3 manage.py makemessages -l en_US`. This is important after
+    `uv run manage.py makemessages -l en_US`. This is important after
     making changes to translatable strings.
 -   The message files need to be compiled for them to show up in the
-    application. Call `python3 manage.py compilemessages` to do this.
+    application. Call `uv run manage.py compilemessages` to do this.
     The generated files don't get committed into git, since these are
     derived artifacts. The build pipeline takes care of executing this
     command.
@@ -338,13 +338,13 @@ LANGUAGES = [
 
 ## Building the documentation
 
-The documentation is built using material-mkdocs, see their [documentation](https://squidfunk.github.io/mkdocs-material/reference/).
+The documentation is built using Zensical, see their [documentation](https://zensical.org/docs/).
 If you want to build the documentation locally, this is how you do it:
 
 1.  Build the documentation
 
     ```bash
-    $ uv run mkdocs build --config-file mkdocs.yml
+    $ uv run zensical build
     ```
 
     _alternatively..._
@@ -355,10 +355,10 @@ If you want to build the documentation locally, this is how you do it:
     something.
 
     ```bash
-    $ uv run mkdocs serve
+    $ uv run zensical serve
     ```
 
-## Building the Docker image
+## Building the Docker image {#docker_build}
 
 The docker image is primarily built by the GitHub actions workflow, but
 it can be faster when developing to build and tag an image locally.
@@ -470,9 +470,158 @@ To get started:
 
 2. VS Code will prompt you with "Reopen in container". Do so and wait for the environment to start.
 
-3. Initialize the project by running the task **Project Setup: Run all Init Tasks**. This
+3. In case your host operating system is Windows:
+
+    - The Source Control view in Visual Studio Code might show: "The detected Git repository is potentially unsafe as the folder is owned by someone other than the current user." Use "Manage Unsafe Repositories" to fix this.
+    - Git might have detecteded modifications for all files, because Windows is using CRLF line endings. Run `git checkout .` in the containers terminal to fix this issue.
+
+4. Initialize the project by running the task **Project Setup: Run all Init Tasks**. This
    will initialize the database tables and create a superuser. Then you can compile the front end
    for production or run the frontend in debug mode.
 
-4. The project is ready for debugging, start either run the fullstack debug or individual debug
+5. The project is ready for debugging, start either run the fullstack debug or individual debug
    processes. Yo spin up the project without debugging run the task **Project Start: Run all Services**
+
+## Developing Date Parser Plugins
+
+Paperless-ngx uses a plugin system for date parsing, allowing you to extend or replace the default date parsing behavior. Plugins are discovered using [Python entry points](https://setuptools.pypa.io/en/latest/userguide/entry_point.html).
+
+### Creating a Date Parser Plugin
+
+To create a custom date parser plugin, you need to:
+
+1. Create a class that inherits from `DateParserPluginBase`
+2. Implement the required abstract method
+3. Register your plugin via an entry point
+
+#### 1. Implementing the Parser Class
+
+Your parser must extend `documents.plugins.date_parsing.DateParserPluginBase` and implement the `parse` method:
+
+```python
+from collections.abc import Iterator
+import datetime
+
+from documents.plugins.date_parsing import DateParserPluginBase
+
+
+class MyDateParserPlugin(DateParserPluginBase):
+    """
+    Custom date parser implementation.
+    """
+
+    def parse(self, filename: str, content: str) -> Iterator[datetime.datetime]:
+        """
+        Parse dates from the document's filename and content.
+
+        Args:
+            filename: The original filename of the document
+            content: The extracted text content of the document
+
+        Yields:
+            datetime.datetime: Valid datetime objects found in the document
+        """
+        # Your parsing logic here
+        # Use self.config to access configuration settings
+
+        # Example: parse dates from filename first
+        if self.config.filename_date_order:
+            # Your filename parsing logic
+            yield some_datetime
+
+        # Then parse dates from content
+        # Your content parsing logic
+        yield another_datetime
+```
+
+#### 2. Configuration and Helper Methods
+
+Your parser instance is initialized with a `DateParserConfig` object accessible via `self.config`. This provides:
+
+-   `languages: list[str]` - List of language codes for date parsing
+-   `timezone_str: str` - Timezone string for date localization
+-   `ignore_dates: set[datetime.date]` - Dates that should be filtered out
+-   `reference_time: datetime.datetime` - Current time for filtering future dates
+-   `filename_date_order: str | None` - Date order preference for filenames (e.g., "DMY", "MDY")
+-   `content_date_order: str` - Date order preference for content
+
+The base class provides two helper methods you can use:
+
+```python
+def _parse_string(
+    self,
+    date_string: str,
+    date_order: str,
+) -> datetime.datetime | None:
+    """
+    Parse a single date string using dateparser with configured settings.
+    """
+
+def _filter_date(
+    self,
+    date: datetime.datetime | None,
+) -> datetime.datetime | None:
+    """
+    Validate a parsed datetime against configured rules.
+    Filters out dates before 1900, future dates, and ignored dates.
+    """
+```
+
+#### 3. Resource Management (Optional)
+
+If your plugin needs to acquire or release resources (database connections, API clients, etc.), override the context manager methods. Paperless-ngx will always use plugins as context managers, ensuring resources can be released even in the event of errors.
+
+#### 4. Registering Your Plugin
+
+Register your plugin using a setuptools entry point in your package's `pyproject.toml`:
+
+```toml
+[project.entry-points."paperless_ngx.date_parsers"]
+my_parser = "my_package.parsers:MyDateParserPlugin"
+```
+
+The entry point name (e.g., `"my_parser"`) is used for sorting when multiple plugins are found. Paperless-ngx will use the first plugin alphabetically by name if multiple plugins are discovered.
+
+### Plugin Discovery
+
+Paperless-ngx automatically discovers and loads date parser plugins at runtime. The discovery process:
+
+1. Queries the `paperless_ngx.date_parsers` entry point group
+2. Validates that each plugin is a subclass of `DateParserPluginBase`
+3. Sorts valid plugins alphabetically by entry point name
+4. Uses the first valid plugin, or falls back to the default `RegexDateParserPlugin` if none are found
+
+If multiple plugins are installed, a warning is logged indicating which plugin was selected.
+
+### Example: Simple Date Parser
+
+Here's a minimal example that only looks for ISO 8601 dates:
+
+```python
+import datetime
+import re
+from collections.abc import Iterator
+
+from documents.plugins.date_parsing.base import DateParserPluginBase
+
+
+class ISODateParserPlugin(DateParserPluginBase):
+    """
+    Parser that only matches ISO 8601 formatted dates (YYYY-MM-DD).
+    """
+
+    ISO_REGEX = re.compile(r"\b(\d{4}-\d{2}-\d{2})\b")
+
+    def parse(self, filename: str, content: str) -> Iterator[datetime.datetime]:
+        # Combine filename and content for searching
+        text = f"{filename} {content}"
+
+        for match in self.ISO_REGEX.finditer(text):
+            date_string = match.group(1)
+            # Use helper method to parse with configured timezone
+            date = self._parse_string(date_string, "YMD")
+            # Use helper method to validate the date
+            filtered_date = self._filter_date(date)
+            if filtered_date is not None:
+                yield filtered_date
+```

docs/faq.md

@@ -1,3 +1,7 @@
+---
+title: FAQs
+---
+
 # Frequently Asked Questions
 
 ## _What's the general plan for Paperless-ngx?_
@@ -63,8 +67,10 @@ elsewhere. Here are a couple notes about that.
     Paperless also supports various Office documents (.docx, .doc, odt,
     .ppt, .pptx, .odp, .xls, .xlsx, .ods).
 
-Paperless-ngx determines the type of a file by inspecting its content.
+Paperless-ngx determines the type of a file by inspecting its content
-The file extensions do not matter.
+rather than its file extensions. However, files processed via the
+consumption directory will be rejected if they have a file extension that
+not supported by any of the available parsers.
 
 ## _Will paperless-ngx run on Raspberry Pi?_
 
@@ -112,30 +118,6 @@ able to run paperless, you're a bit on your own. If you can't run the
 docker image, the documentation has instructions for bare metal
 installs.
 
-## _How do I proxy this with NGINX?_
-
-**A:** See [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Using-a-Reverse-Proxy-with-Paperless-ngx#nginx).
-
-## _How do I get WebSocket support with Apache mod_wsgi_?
-
-**A:** `mod_wsgi` by itself does not support ASGI. Paperless will
-continue to work with WSGI, but certain features such as status
-notifications about document consumption won't be available.
-
-If you want to continue using `mod_wsgi`, you will have to run an
-ASGI-enabled web server as well that processes WebSocket connections,
-and configure Apache to redirect WebSocket connections to this server.
-Multiple options for ASGI servers exist:
-
--   `gunicorn` with `uvicorn` as the worker implementation (the default
-    of paperless)
--   `daphne` as a standalone server, which is the reference
-    implementation for ASGI.
--   `uvicorn` as a standalone server
-
-You may also find the [Django documentation](https://docs.djangoproject.com/en/5.1/howto/deployment/asgi/) on ASGI
-useful to review.
-
 ## _What about the Redis licensing change and using one of the open source forks_?
 
 Currently (October 2024), forks of Redis such as Valkey or Redirect are not officially supported by our upstream

docs/index.md

@@ -1,3 +1,7 @@
+---
+title: Home
+---
+
 <div class="grid-left" markdown>
 ![image](assets/logo_full_black.svg#only-light){.index-logo}
 ![image](assets/logo_full_white.svg#only-dark){.index-logo}
@@ -25,12 +29,14 @@ physical documents into a searchable online archive so you can keep, well, _less
 ## Features
 
 -   **Organize and index** your scanned documents with tags, correspondents, types, and more.
--   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
 -   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
--   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   _New!_ Supports remote OCR with Azure AI (opt-in).
 -   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
 -   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
--   Supports PDF documents, images, plain text files, Office documents (Word, Excel, Powerpoint, and LibreOffice equivalents)[^1] and more.
+-   **New**: Paperless-ngx can now leverage AI (Large Language Models or LLMs) for document suggestions. This is an optional feature that can be enabled (and is disabled by default).
+-   Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.
 -   Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely with different configurations assigned to different documents.
 -   **Beautiful, modern web application** that features:
     -   Customizable dashboard with statistics.
@@ -197,7 +203,7 @@ People interested in continuing the work on paperless-ngx are encouraged to reac
 
 ### Translation
 
-Paperless-ngx is available in many languages that are coordinated on [Crowdin](https://crwd.in/paperless-ngx). If you want to help out by translating paperless-ngx into your language, please head over to the [Paperless-ngx project at Crowdin](https://crwd.in/paperless-ngx), and thank you!
+Paperless-ngx is available in many languages that are coordinated on [Crowdin](https://crowdin.com/project/paperless-ngx). If you want to help out by translating paperless-ngx into your language, please head over to the [Paperless-ngx project at Crowdin](https://crowdin.com/project/paperless-ngx), and thank you!
 
 ## Scanners & Software
 

docs/migration-v3.md

@@ -0,0 +1,105 @@
+# v3 Migration Guide
+
+## Consumer Settings Changes
+
+The v3 consumer command uses a [different library](https://watchfiles.helpmanual.io/) to unify
+the watching for new files in the consume directory. For the user, this removes several configuration options related to delays and retries
+and replaces with a single unified setting. It also adjusts how the consumer ignore filtering happens, replaced `fnmatch` with `regex` and
+separating the directory ignore from the file ignore.
+
+### Summary
+
+| Old Setting                    | New Setting                                                                         | Notes                                                                                |
+| ------------------------------ | ----------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
+| `CONSUMER_POLLING`             | [`CONSUMER_POLLING_INTERVAL`](configuration.md#PAPERLESS_CONSUMER_POLLING_INTERVAL) | Renamed for clarity                                                                  |
+| `CONSUMER_INOTIFY_DELAY`       | [`CONSUMER_STABILITY_DELAY`](configuration.md#PAPERLESS_CONSUMER_STABILITY_DELAY)   | Unified for all modes                                                                |
+| `CONSUMER_POLLING_DELAY`       | _Removed_                                                                           | Use `CONSUMER_STABILITY_DELAY`                                                       |
+| `CONSUMER_POLLING_RETRY_COUNT` | _Removed_                                                                           | Automatic with stability tracking                                                    |
+| `CONSUMER_IGNORE_PATTERNS`     | [`CONSUMER_IGNORE_PATTERNS`](configuration.md#PAPERLESS_CONSUMER_IGNORE_PATTERNS)   | **Now regex, not fnmatch**; user patterns are added to (not replacing) default ones  |
+| _New_                          | [`CONSUMER_IGNORE_DIRS`](configuration.md#PAPERLESS_CONSUMER_IGNORE_DIRS)           | Additional directories to ignore; user entries are added to (not replacing) defaults |
+
+## Encryption Support
+
+Document and thumbnail encryption is no longer supported. This was previously deprecated in [paperless-ng 0.9.3](https://github.com/paperless-ngx/paperless-ngx/blob/dev/docs/changelog.md#paperless-ng-093)
+
+Users must decrypt their document using the `decrypt_documents` command before upgrading.
+
+## Barcode Scanner Changes
+
+Support for [pyzbar](https://github.com/NaturalHistoryMuseum/pyzbar) has been removed. The underlying libzbar library has
+seen no updates in 16 years and is largely unmaintained, and the pyzbar Python wrapper last saw a release in March 2022. In
+practice, pyzbar struggled with barcode detection reliability, particularly on skewed, low-contrast, or partially
+obscured barcodes. [zxing-cpp](https://github.com/zxing-cpp/zxing-cpp) is actively maintained, significantly more
+reliable at finding barcodes, and now ships pre-built wheels for both x86_64 and arm64, removing the need to build the library.
+
+The `CONSUMER_BARCODE_SCANNER` setting has been removed. zxing-cpp is now the only backend.
+
+### Summary
+
+| Old Setting                | New Setting | Notes                             |
+| -------------------------- | ----------- | --------------------------------- |
+| `CONSUMER_BARCODE_SCANNER` | _Removed_   | zxing-cpp is now the only backend |
+
+### Action Required
+
+-   If you were already using `CONSUMER_BARCODE_SCANNER=ZXING`, simply remove the setting.
+-   If you had `CONSUMER_BARCODE_SCANNER=PYZBAR` or were using the default, no functional changes are needed beyond
+    removing the setting. zxing-cpp supports all the same barcode formats and you should see improved detection
+    reliability.
+-   The `libzbar0` / `libzbar-dev` system packages are no longer required and can be removed from any custom Docker
+    images or host installations.
+
+## Database Engine
+
+`PAPERLESS_DBENGINE` is now required to use PostgreSQL or MariaDB. Previously, the
+engine was inferred from the presence of `PAPERLESS_DBHOST`, with `PAPERLESS_DBENGINE`
+only needed to select MariaDB over PostgreSQL.
+
+SQLite users require no changes, though they may explicitly set their engine if desired.
+
+#### Action Required
+
+PostgreSQL and MariaDB users must add `PAPERLESS_DBENGINE` to their environment:
+
+```yaml
+# v2 (PostgreSQL inferred from PAPERLESS_DBHOST)
+PAPERLESS_DBHOST: postgres
+
+# v3 (engine must be explicit)
+PAPERLESS_DBENGINE: postgresql
+PAPERLESS_DBHOST: postgres
+```
+
+See [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) for accepted values.
+
+## Database Advanced Options
+
+The individual SSL, timeout, and pooling variables have been removed in favor of a
+single [`PAPERLESS_DB_OPTIONS`](configuration.md#PAPERLESS_DB_OPTIONS) string. This
+consolidates a growing set of engine-specific variables into one place, and allows
+any option supported by the underlying database driver to be set without requiring a
+dedicated environment variable for each.
+
+The removed variables and their replacements are:
+
+| Removed Variable          | Replacement in `PAPERLESS_DB_OPTIONS`                                        |
+| ------------------------- | ---------------------------------------------------------------------------- |
+| `PAPERLESS_DBSSLMODE`     | `sslmode=<value>` (PostgreSQL) or `ssl_mode=<value>` (MariaDB)               |
+| `PAPERLESS_DBSSLROOTCERT` | `sslrootcert=<path>` (PostgreSQL) or `ssl.ca=<path>` (MariaDB)               |
+| `PAPERLESS_DBSSLCERT`     | `sslcert=<path>` (PostgreSQL) or `ssl.cert=<path>` (MariaDB)                 |
+| `PAPERLESS_DBSSLKEY`      | `sslkey=<path>` (PostgreSQL) or `ssl.key=<path>` (MariaDB)                   |
+| `PAPERLESS_DB_POOLSIZE`   | `pool.max_size=<value>` (PostgreSQL only)                                    |
+| `PAPERLESS_DB_TIMEOUT`    | `timeout=<value>` (SQLite) or `connect_timeout=<value>` (PostgreSQL/MariaDB) |
+
+The deprecated variables will continue to function for now but will be removed in a
+future release. A deprecation warning is logged at startup for each deprecated variable
+that is still set.
+
+#### Action Required
+
+Users with any of the deprecated variables set should migrate to `PAPERLESS_DB_OPTIONS`.
+Multiple options are combined in a single value:
+
+```bash
+PAPERLESS_DB_OPTIONS="sslmode=require;sslrootcert=/certs/ca.pem;pool.max_size=10"
+```

docs/setup.md

@@ -1,52 +1,77 @@
-## Installation
+---
+title: Setup
+---
 
-You can go multiple routes to setup and run Paperless:
+# Installation
 
--   [Use the script to setup a Docker install](#docker_script)
+!!! tip "Quick Start"
--   [Use the Docker compose templates](#docker)
--   [Build the Docker image yourself](#docker_build)
--   [Install Paperless-ngx directly on your system manually ("bare metal")](#bare_metal)
--   A user-maintained list of commercial hosting providers can be found [in the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Related-Projects)
-
-The Docker routes are quick & easy. These are the recommended routes.
-This configures all the stuff from the above automatically so that it
-just works and uses sensible defaults for all configuration options.
-Here you find a cheat-sheet for docker beginners: [CLI
-Basics](https://www.sehn.tech/refs/devops-with-docker/)
-
-The bare metal route is complicated to setup but makes it easier should
-you want to contribute some code back. You need to configure and run the
-above mentioned components yourself.
-
-### Use the Installation Script {#docker_script}
-
-Paperless provides an interactive installation script to setup a Docker Compose
-installation. The script asks for a couple configuration options, and will then create the
-necessary configuration files, pull the docker image, start Paperless-ngx and create your superuser
-account. The script essentially automatically performs the steps described in [Docker setup](#docker).
-
-1.  Make sure that Docker and Docker Compose are [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
-
-2.  Download and run the installation script:
 
+    If you just want Paperless-ngx running quickly, use our installation script:
     ```shell-session
     bash -c "$(curl --location --silent --show-error https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
     ```
+    _If piping into a shell directly from the internet makes you nervous, inspect [the script](https://github.com/paperless-ngx/paperless-ngx/blob/main/install-paperless-ngx.sh) first!_
 
-    !!! note
+## Overview
 
-        macOS users will need to install [gnu-sed](https://formulae.brew.sh/formula/gnu-sed) with support
+Choose the installation route that best fits your setup:
-        for running as `sed` as well as [wget](https://formulae.brew.sh/formula/wget).
 
-### Use Docker Compose {#docker}
+| Route                                                                                                             | Best for                                                                            | Effort |
+| ----------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | ------ |
+| [Installation script](#docker_script)                                                                             | Fastest first-time setup with guided prompts (recommended for most users)           | Low    |
+| [Docker Compose templates](#docker)                                                                               | Manual control over compose files and settings                                      | Medium |
+| [Bare metal](#bare_metal)                                                                                         | Advanced setups, packaging, and development-adjacent workflows                      | High   |
+| [Hosted providers (wiki)](https://github.com/paperless-ngx/paperless-ngx/wiki/Related-Projects#hosting-providers) | Managed hosting options maintained by the community — check details carefully | Varies |
 
-1.  Make sure that Docker and Docker Compose are [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
+For most users, Docker is the best option. It is faster to set up,
+easier to maintain, and ships with sensible defaults.
 
-2.  Go to the [/docker/compose directory on the project
+The bare-metal route gives you more control, but it requires manual
+installation and operation of all components. It is usually best suited
+for advanced users and contributors.
+
+!!! info
+
+    Because [superuser](usage.md#superusers) accounts have full access to all objects and documents, you may want to create a separate user account for daily use,
+    or "downgrade" your superuser account to a normal user account after setup.
+
+## Installation Script {#docker_script}
+
+Paperless-ngx provides an interactive script for Docker Compose setups.
+It asks a few configuration questions, then creates the required files,
+pulls the image, starts the containers, and creates your [superuser](usage.md#superusers)
+account. In short, it automates the [Docker Compose setup](#docker) described below.
+
+#### Prerequisites
+
+-   Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
+-   macOS users will need [GNU sed](https://formulae.brew.sh/formula/gnu-sed) with support for running as `sed` as well as [wget](https://formulae.brew.sh/formula/wget).
+
+#### Run the installation script
+
+```shell-session
+bash -c "$(curl --location --silent --show-error https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
+```
+
+#### After installation
+
+Paperless-ngx should be available at `http://127.0.0.1:8000` (or similar,
+depending on your configuration) and you will be able to login with the
+credentials you provided during the installation script.
+
+## Docker Compose Install {#docker}
+
+#### Prerequisites
+
+-   Docker and Docker Compose must be [installed](https://docs.docker.com/engine/install/){:target="\_blank"}.
+
+#### Installation
+
+1.  Go to the [/docker/compose directory on the project
     page](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose){:target="\_blank"}
-    and download one of the `docker-compose.*.yml` files, depending on which database backend
+    and download one `docker-compose.*.yml` file for your preferred
-    you want to use. Place the files in a local directory and rename it `docker-compose.yml`. Download the
+    database backend. Save it in a local directory as `docker-compose.yml`.
-    `docker-compose.env` file and the `.env` file as well in the same directory.
+    Also download `docker-compose.env` and `.env` into that same directory.
 
     If you want to enable optional support for Office and other documents, download a
     file with `-tika` in the file name.
@@ -56,15 +81,16 @@ account. The script essentially automatically performs the steps described in [D
         For new installations, it is recommended to use PostgreSQL as the
         database backend.
 
-3.  Modify `docker-compose.yml` as needed. For example, you may want to change the paths to the
+2.  Modify `docker-compose.yml` as needed. For example, you may want to
-    consumption, media etc. directories to use 'bind mounts'.
+    change the paths for `consume`, `media`, and other directories to
+    use bind mounts.
     Find the line that specifies where to mount the directory, e.g.:
 
     ```yaml
     - ./consume:/usr/src/paperless/consume
     ```
 
-    Replace the part _before_ the colon with a local directory of your choice:
+    Replace the part _before_ the colon with your local directory:
 
     ```yaml
     - /home/jonaswinkler/paperless-inbox:/usr/src/paperless/consume
@@ -78,38 +104,15 @@ account. The script essentially automatically performs the steps described in [D
         - 8010:8000
     ```
 
-    **Rootless**
+3.  Modify `docker-compose.env` with any configuration options you need.
-
-    !!! warning
-
-        It is currently not possible to run the container rootless if additional languages are specified via `PAPERLESS_OCR_LANGUAGES`.
-
-    If you want to run Paperless as a rootless container, you will need
-    to do the following in your `docker-compose.yml`:
-
-    -   set the `user` running the container to map to the `paperless`
-        user in the container. This value (`user_id` below), should be
-        the same id that `USERMAP_UID` and `USERMAP_GID` are set to in
-        the next step. See `USERMAP_UID` and `USERMAP_GID`
-        [here](configuration.md#docker).
-
-    Your entry for Paperless should contain something like:
-
-    > ```
-    > webserver:
-    >   image: ghcr.io/paperless-ngx/paperless-ngx:latest
-    >   user: <user_id>
-    > ```
-
-4.  Modify `docker-compose.env` with any configuration options you'd like.
     See the [configuration documentation](configuration.md) for all options.
 
     You may also need to set `USERMAP_UID` and `USERMAP_GID` to
-    the uid and gid of your user on the host system. Use `id -u` and
+    the UID and GID of your user on the host system. Use `id -u` and
-    `id -g` to get these. This ensures that both the container and the host
+    `id -g` to get these values. This ensures both the container and the
-    user have write access to the consumption directory. If your UID
+    host user can write to the consumption directory. If your UID and
-    and GID on the host system is 1000 (the default for the first normal
+    GID are `1000` (the default for the first normal user on many
-    user on most systems), it will work out of the box without any
+    systems), this usually works out of the box without
     modifications. Run `id "username"` to check.
 
     !!! note
@@ -118,79 +121,62 @@ account. The script essentially automatically performs the steps described in [D
         appending `_FILE` to configuration values. For example [`PAPERLESS_DBUSER`](configuration.md#PAPERLESS_DBUSER)
         can be set using `PAPERLESS_DBUSER_FILE=/var/run/secrets/password.txt`.
 
-    !!! warning
+4.  Run `docker compose pull`. This pulls the image from the GitHub container registry
-
+    by default, but you can pull from Docker Hub by changing the `image`
-        Some file systems such as NFS network shares don't support file
-        system notifications with `inotify`. When storing the consumption
-        directory on such a file system, paperless will not pick up new
-        files with the default configuration. You will need to use
-        [`PAPERLESS_CONSUMER_POLLING`](configuration.md#PAPERLESS_CONSUMER_POLLING), which will disable inotify. See
-        [here](configuration.md#polling).
-
-5.  Run `docker compose pull`. This will pull the image from the GitHub container registry
-    by default but you can change the image to pull from Docker Hub by changing the `image`
     line to `image: paperlessngx/paperless-ngx:latest`.
 
-6.  Run `docker compose up -d`. This will create and start the necessary containers.
+5.  Run `docker compose up -d`. This will create and start the necessary containers.
 
-7.  Congratulations! Your Paperless-ngx instance should now be accessible at `http://127.0.0.1:8000`
+#### After installation
-    (or similar, depending on your configuration). When you first access the web interface, you will be
-    prompted to create a superuser account.
 
-### Build the Docker image yourself {#docker_build}
+Your Paperless-ngx instance should now be accessible at
+`http://127.0.0.1:8000` (or similar, depending on your configuration).
+When you first access the web interface, you will be prompted to create
+a [superuser](usage.md#superusers) account.
 
-1.  Clone the entire repository of paperless:
+#### Optional Advanced Compose Configurations {#advanced_compose data-toc-label="Advanced Compose Configurations"}
 
-    ```shell-session
+**Rootless**
-    git clone https://github.com/paperless-ngx/paperless-ngx
-    ```
 
-    The main branch always reflects the latest stable version.
+!!! warning
 
-2.  Copy one of the `docker/compose/docker-compose.*.yml` to
+    It is currently not possible to run the container rootless if additional languages are specified via `PAPERLESS_OCR_LANGUAGES`.
-    `docker-compose.yml` in the root folder, depending on which database
-    backend you want to use. Copy `docker-compose.env` into the project
-    root as well.
 
-3.  In the `docker-compose.yml` file, find the line that instructs
+If you want to run Paperless as a rootless container, make this
-    Docker Compose to pull the paperless image from Docker Hub:
+change in `docker-compose.yml`:
 
-    ```yaml
+-   Set the `user` running the container to map to the `paperless`
-    webserver:
+    user in the container. This value (`user_id` below) should be
-        image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    the same ID that `USERMAP_UID` and `USERMAP_GID` are set to in
-    ```
+    `docker-compose.env`. See `USERMAP_UID` and `USERMAP_GID`
+    [here](configuration.md#docker).
 
-    and replace it with a line that instructs Docker Compose to build
+Your entry for Paperless should contain something like:
-    the image from the current working directory instead:
 
-    ```yaml
+> ```
-    webserver:
+> webserver:
-        build:
+>   image: ghcr.io/paperless-ngx/paperless-ngx:latest
-            context: .
+>   user: <user_id>
-    ```
+> ```
 
-4.  Follow the [Docker setup](#docker) above except when asked to run
+**File systems without inotify support (e.g. NFS)**
-    `docker compose pull` to pull the image, run
 
-    ```shell-session
+Some file systems, such as NFS network shares, don't support file system
-    docker compose build
+notifications with `inotify`. When the consumption directory is on such a
-    ```
+file system, Paperless-ngx will not pick up new files with the default
+configuration. Use [`PAPERLESS_CONSUMER_POLLING`](configuration.md#PAPERLESS_CONSUMER_POLLING)
+to enable polling and disable inotify. See [here](configuration.md#polling).
 
-    instead to build the image.
+## Bare Metal Install {#bare_metal}
 
-### Bare Metal Route {#bare_metal}
+#### Prerequisites
 
-Paperless runs on linux only. The following procedure has been tested on
+-   Paperless runs on Linux only, Windows is not supported.
-a minimal installation of Debian/Buster, which is the current stable
+-   Python 3.11, 3.12, 3.13, or 3.14 is required. As a policy, Paperless-ngx aims to support at least the three most recent Python versions and drops support for versions as they reach end-of-life. Newer versions may work, but some dependencies may not be fully compatible.
-release at the time of writing. Windows is not and will never be
-supported.
 
-Paperless requires Python 3. At this time, 3.10 - 3.12 are tested versions.
+#### Installation
-Newer versions may work, but some dependencies may not fully support newer versions.
-Support for older Python versions may be dropped as they reach end of life or as newer versions
-are released, dependency support is confirmed, etc.
 
-1.  Install dependencies. Paperless requires the following packages.
+1.  Install dependencies. Paperless requires the following packages:
 
     -   `python3`
     -   `python3-pip`
@@ -204,13 +190,12 @@ are released, dependency support is confirmed, etc.
     -   `libpq-dev` for PostgreSQL
     -   `libmagic-dev` for mime type detection
     -   `mariadb-client` for MariaDB compile time
-    -   `libzbar0` for barcode detection
     -   `poppler-utils` for barcode detection
 
     Use this list for your preferred package management:
 
     ```
-    python3 python3-pip python3-dev imagemagick fonts-liberation gnupg libpq-dev default-libmysqlclient-dev pkg-config libmagic-dev libzbar0 poppler-utils
+    python3 python3-pip python3-dev imagemagick fonts-liberation gnupg libpq-dev default-libmysqlclient-dev pkg-config libmagic-dev poppler-utils
     ```
 
     These dependencies are required for OCRmyPDF, which is used for text
@@ -254,8 +239,8 @@ are released, dependency support is confirmed, etc.
 
 2.  Install `redis` >= 6.0 and configure it to start automatically.
 
-3.  Optional. Install `postgresql` and configure a database, user and
+3.  Optional: Install `postgresql` and configure a database, user, and
-    password for paperless. If you do not wish to use PostgreSQL,
+    password for Paperless-ngx. If you do not wish to use PostgreSQL,
     MariaDB and SQLite are available as well.
 
     !!! note
@@ -264,61 +249,60 @@ are released, dependency support is confirmed, etc.
         extension](https://code.djangoproject.com/wiki/JSON1Extension) is
         enabled. This is usually the case, but not always.
 
-4.  Create a system user with a new home folder under which you wish
+4.  Create a system user with a new home folder in which you want
-    to run paperless.
+    to run Paperless-ngx.
 
     ```shell-session
     adduser paperless --system --home /opt/paperless --group
     ```
 
-5.  Get the release archive from
+5.  Download a release archive from
-    <https://github.com/paperless-ngx/paperless-ngx/releases> for example with
+    <https://github.com/paperless-ngx/paperless-ngx/releases>. For example:
 
     ```shell-session
-    curl -O -L https://github.com/paperless-ngx/paperless-ngx/releases/download/v1.10.2/paperless-ngx-v1.10.2.tar.xz
+    curl -O -L https://github.com/paperless-ngx/paperless-ngx/releases/download/vX.Y.Z/paperless-ngx-vX.Y.Z.tar.xz
     ```
 
     Extract the archive with
 
     ```shell-session
-    tar -xf paperless-ngx-v1.10.2.tar.xz
+    tar -xf paperless-ngx-vX.Y.Z.tar.xz
     ```
 
-    and copy the contents to the
+    and copy the contents to the home directory of the user you created
-    home folder of the user you created before (`/opt/paperless`).
+    earlier (`/opt/paperless`).
 
-    Optional: If you cloned the git repo, you will have to
+    Optional: If you cloned the Git repository, you will need to
-    compile the frontend yourself, see [here](development.md#front-end-development)
+    compile the frontend yourself. See [here](development.md#front-end-development)
     and use the `build` step, not `serve`.
 
-6.  Configure paperless. See [configuration](configuration.md) for details.
+6.  Configure Paperless-ngx. See [configuration](configuration.md) for details.
     Edit the included `paperless.conf` and adjust the settings to your
-    needs. Required settings for getting
+    needs. Required settings for getting Paperless-ngx running are:
-    paperless running are:
 
-    -   [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) should point to your redis server, such as
+    -   [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) should point to your Redis server, such as
-        <redis://localhost:6379>.
+        `redis://localhost:6379`.
-    -   [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) optional, and should be one of `postgres`,
+    -   [`PAPERLESS_DBENGINE`](configuration.md#PAPERLESS_DBENGINE) is optional, and should be one of `postgres`,
         `mariadb`, or `sqlite`
     -   [`PAPERLESS_DBHOST`](configuration.md#PAPERLESS_DBHOST) should be the hostname on which your
         PostgreSQL server is running. Do not configure this to use
         SQLite instead. Also configure port, database name, user and
         password as necessary.
-    -   [`PAPERLESS_CONSUMPTION_DIR`](configuration.md#PAPERLESS_CONSUMPTION_DIR) should point to a folder which
+    -   [`PAPERLESS_CONSUMPTION_DIR`](configuration.md#PAPERLESS_CONSUMPTION_DIR) should point to the folder
-        paperless should watch for documents. You might want to have
+        that Paperless-ngx should watch for incoming documents.
-        this somewhere else. Likewise, [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) and
+        Likewise, [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) and
-        [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) define where paperless stores its data.
+        [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) define where Paperless-ngx stores its data.
-        If you like, you can point both to the same directory.
+        If needed, these can point to the same directory.
     -   [`PAPERLESS_SECRET_KEY`](configuration.md#PAPERLESS_SECRET_KEY) should be a random sequence of
         characters. It's used for authentication. Failure to do so
         allows third parties to forge authentication credentials.
-    -   [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) if you are behind a reverse proxy. This should
+    -   Set [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) if you are behind a reverse proxy. This should
         point to your domain. Please see
         [configuration](configuration.md) for more
         information.
 
-    Many more adjustments can be made to paperless, especially the OCR
+    You can make many more adjustments, especially for OCR.
-    part. The following options are recommended for everyone:
+    The following options are recommended for most users:
 
     -   Set [`PAPERLESS_OCR_LANGUAGE`](configuration.md#PAPERLESS_OCR_LANGUAGE) to the language most of your
         documents are written in.
@@ -326,17 +310,16 @@ are released, dependency support is confirmed, etc.
 
     !!! warning
 
-        Ensure your Redis instance [is secured](https://redis.io/docs/getting-started/#securing-redis).
+        Ensure your Redis instance [is secured](https://redis.io/docs/latest/operate/oss_and_stack/management/security/).
 
-7.  Create the following directories if they are missing:
+7.  Create the following directories if they do not already exist:
 
     -   `/opt/paperless/media`
     -   `/opt/paperless/data`
     -   `/opt/paperless/consume`
 
-    Adjust as necessary if you configured different folders.
+    Adjust these paths if you configured different folders.
-    Ensure that the paperless user has write permissions for every one
+    Then verify that the `paperless` user has write permissions:
-    of these folders with
 
     ```shell-session
     ls -l -d /opt/paperless/media
@@ -350,45 +333,44 @@ are released, dependency support is confirmed, etc.
     sudo chown paperless:paperless /opt/paperless/consume
     ```
 
-8.  Install python requirements from the `requirements.txt` file.
+8.  Install Python dependencies from `requirements.txt`.
 
     ```shell-session
     sudo -Hu paperless pip3 install -r requirements.txt
     ```
 
-    This will install all python dependencies in the home directory of
+    This will install all Python dependencies in the home directory of
     the new paperless user.
 
     !!! tip
 
-        It is up to you if you wish to use a virtual environment or not for the Python
+        You can use a virtual environment if you prefer. If you do,
-        dependencies.  This is an alternative to the above and may require adjusting
+        you may need to adjust the example scripts for your virtual
-        the example scripts to utilize the virtual environment paths
+        environment paths.
 
     !!! tip
 
         If you use modern Python tooling, such as `uv`, installation will not include
-        dependencies for Postgres or Mariadb.  You can select those extras with `--extra <EXTRA>`
+        dependencies for PostgreSQL or MariaDB. You can select those
-        or all with `--all-extras`
+        extras with `--extra <EXTRA>`, or install all extras with
+        `--all-extras`.
 
-9.  Go to `/opt/paperless/src`, and execute the following command:
+9.  Go to `/opt/paperless/src` and execute the following command:
 
     ```bash
     # This creates the database schema.
     sudo -Hu paperless python3 manage.py migrate
     ```
 
-    When you first access the web interface you will be prompted to create a superuser account.
+10. Optional: Test that Paperless-ngx is working by running
-
-10. Optional: Test that paperless is working by executing
 
     ```bash
     # Manually starts the webserver
     sudo -Hu paperless python3 manage.py runserver
     ```
 
-    and pointing your browser to http://localhost:8000 if
+    Then point your browser to `http://localhost:8000` if
-    accessing from the same devices on which paperless is installed.
+    accessing from the same device on which Paperless-ngx is installed.
     If accessing from another machine, set up systemd services. You may need
     to set `PAPERLESS_DEBUG=true` in order for the development server to work
     normally in your browser.
@@ -396,23 +378,24 @@ are released, dependency support is confirmed, etc.
     !!! warning
 
         This is a development server which should not be used in production.
-        It is not audited for security and performance is inferior to
+        It is not audited for security, and performance is inferior to
-        production ready web servers.
+        production-ready web servers.
 
     !!! tip
 
         This will not start the consumer. Paperless does this in a separate
         process.
 
-11. Setup systemd services to run paperless automatically. You may use
+11. Set up systemd services to run Paperless-ngx automatically. You may use
     the service definition files included in the `scripts` folder as a
     starting point.
 
-    Paperless needs the `webserver` script to run the webserver, the
+    Paperless needs:
-    `consumer` script to watch the input folder, `taskqueue` for the
+
-    background workers used to handle things like document consumption
+    -   The `webserver` script to run the webserver.
-    and the `scheduler` script to run tasks such as email checking at
+    -   The `consumer` script to watch the input folder.
-    certain times .
+    -   The `taskqueue` script for background workers (document consumption, etc.).
+    -   The `scheduler` script for periodic tasks such as email checking.
 
     !!! note
 
@@ -421,9 +404,9 @@ are released, dependency support is confirmed, etc.
         `Require=paperless-webserver.socket` in the `webserver` script
         and configure `granian` to listen on port 80 (set `GRANIAN_PORT`).
 
-    These services rely on redis and optionally the database server, but
+    These services rely on Redis and optionally the database server, but
     don't need to be started in any particular order. The example files
-    depend on redis being started. If you use a database server, you
+    depend on Redis being started. If you use a database server, you
     should add additional dependencies.
 
     !!! note
@@ -433,19 +416,16 @@ are released, dependency support is confirmed, etc.
 
     !!! warning
 
-        If celery won't start (check with
+        If Celery won't start, check
         `sudo systemctl status paperless-task-queue.service` for
-        paperless-task-queue.service and paperless-scheduler.service
+        `paperless-task-queue.service` and `paperless-scheduler.service`.
-        ) you need to change the path in the files. Example:
+        You may need to change the path in the files. Example:
         `ExecStart=/opt/paperless/.local/bin/celery --app paperless worker --loglevel INFO`
 
-12. Optional: Install a samba server and make the consumption folder
+12. Configure ImageMagick to allow processing of PDF documents. Most
-    available as a network share.
-
-13. Configure ImageMagick to allow processing of PDF documents. Most
     distributions have this disabled by default, since PDF documents can
-    contain malware. If you don't do this, paperless will fall back to
+    contain malware. If you don't do this, Paperless-ngx will fall back to
-    ghostscript for certain steps such as thumbnail generation.
+    Ghostscript for certain steps such as thumbnail generation.
 
     Edit `/etc/ImageMagick-6/policy.xml` and adjust
 
@@ -459,32 +439,38 @@ are released, dependency support is confirmed, etc.
     <policy domain="coder" rights="read|write" pattern="PDF" />
     ```
 
-14. Optional: Install the
+**Optional: Install the [jbig2enc](https://ocrmypdf.readthedocs.io/en/latest/jbig2.html) encoder.**
-    [jbig2enc](https://ocrmypdf.readthedocs.io/en/latest/jbig2.html)
+This will reduce the size of generated PDF documents. You'll most likely need to compile this yourself, because this
-    encoder. This will reduce the size of generated PDF documents.
+software has been patented until around 2017 and binary packages are not available for most distributions.
-    You'll most likely need to compile this by yourself, because this
-    software has been patented until around 2017 and binary packages are
-    not available for most distributions.
 
-15. Optional: If using the NLTK machine learning processing (see
+**Optional: download the NLTK data**
-    [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) for details),
+If using the NLTK machine-learning processing (see [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) for details),
-    download the NLTK data for the Snowball
+download the NLTK data for the Snowball Stemmer, Stopwords and Punkt tokenizer to `/usr/share/nltk_data`. Refer to the [NLTK
-    Stemmer, Stopwords and Punkt tokenizer to `/usr/share/nltk_data`. Refer to the [NLTK
+instructions](https://www.nltk.org/data.html) for details on how to download the data.
-    instructions](https://www.nltk.org/data.html) for details on how to
-    download the data.
 
-# Migrating to Paperless-ngx
+#### After installation
 
-Migration is possible both from Paperless-ng or directly from the
+Your Paperless-ngx instance should now be accessible at `http://localhost:8000` (or similar, depending on your configuration).
-'original' Paperless.
+When you first access the web interface you will be prompted to create a [superuser](usage.md#superusers) account.
 
-## Migrating from Paperless-ng
+## Build the Docker image yourself {#docker_build data-toc-label="Building the Docker image"}
 
-Paperless-ngx is meant to be a drop-in replacement for Paperless-ng and
+Building the Docker image yourself is typically used for development, but it can also be used for production
-thus upgrading should be trivial for most users, especially when using
+if you want to customize the image. See [Building the Docker image](development.md#docker_build) in the
-docker. However, as with any major change, it is recommended to take a
+development documentation.
+
+## Migrating to Paperless-ngx
+
+You can migrate to Paperless-ngx from Paperless-ng or from the original
+Paperless project.
+
+<h3 id="migration_ng">Migrating from Paperless-ng</h3>
+
+Paperless-ngx is meant to be a drop-in replacement for Paperless-ng, and
+upgrading should be trivial for most users, especially when using
+Docker. However, as with any major change, it is recommended to take a
 full backup first. Once you are ready, simply change the docker image to
-point to the new source. E.g. if using Docker Compose, edit
+point to the new source. For example, if using Docker Compose, edit
 `docker-compose.yml` and change:
 
 ```
@@ -497,66 +483,64 @@ to
 image: ghcr.io/paperless-ngx/paperless-ngx:latest
 ```
 
-and then run `docker compose up -d` which will pull the new image
+and then run `docker compose up -d`, which will pull the new image and
-recreate the container. That's it!
+recreate the container. That's it.
 
 Users who installed with the bare-metal route should also update their
 Git clone to point to `https://github.com/paperless-ngx/paperless-ngx`,
-e.g. using the command
+for example using:
 `git remote set-url origin https://github.com/paperless-ngx/paperless-ngx`
 and then pull the latest version.
 
-## Migrating from Paperless
+<h3 id="migration_paperless">Migrating from Paperless</h3>
 
-At its core, paperless-ngx is still paperless and fully compatible.
+At its core, Paperless-ngx is still Paperless and fully compatible.
 However, some things have changed under the hood, so you need to adapt
-your setup depending on how you installed paperless.
+your setup depending on how you installed Paperless.
 
-This setup describes how to update an existing paperless Docker
+This section describes how to update an existing Paperless Docker
-installation. The important things to keep in mind are as follows:
+installation. Keep these points in mind:
 
 -   Read the [changelog](changelog.md) and
     take note of breaking changes.
--   You should decide if you want to stick with SQLite or want to
+-   Decide whether to stay on SQLite or migrate to PostgreSQL.
-    migrate your database to PostgreSQL. See [documentation](#sqlite_to_psql)
+    Both work fine with Paperless-ngx.
-    for details on
+    However, if you already have a database server running
-    how to move your data from SQLite to PostgreSQL. Both work fine with
+    for other services, you might as well use it for Paperless as well.
-    paperless. However, if you already have a database server running
+-   The task scheduler of Paperless, which is used to execute periodic
-    for other services, you might as well use it for paperless as well.
--   The task scheduler of paperless, which is used to execute periodic
     tasks such as email checking and maintenance, requires a
-    [redis](https://redis.io/) message broker instance. The
+    [Redis](https://redis.io/) message broker instance. The
     Docker Compose route takes care of that.
 -   The layout of the folder structure for your documents and data
-    remains the same, so you can just plug your old docker volumes into
+    remains the same, so you can plug your old Docker volumes into
     paperless-ngx and expect it to find everything where it should be.
 
-Migration to paperless-ngx is then performed in a few simple steps:
+Migration to Paperless-ngx is then performed in a few simple steps:
 
-1.  Stop paperless.
+1.  Stop Paperless.
 
     ```bash
     cd /path/to/current/paperless
     docker compose down
     ```
 
-2.  Do a backup for two purposes: If something goes wrong, you still
+2.  Create a backup for two reasons: if something goes wrong, you still
-    have your data. Second, if you don't like paperless-ngx, you can
+    have your data; and if you don't like paperless-ngx, you can
-    switch back to paperless.
+    switch back to Paperless.
 
-3.  Download the latest release of paperless-ngx. You can either go with
+3.  Download the latest release of Paperless-ngx. You can either use
     the Docker Compose files from
     [here](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose)
     or clone the repository to build the image yourself (see
-    [above](#docker_build)). You can
+    [development docs](development.md#docker_build)). You can either replace your current paperless
-    either replace your current paperless folder or put paperless-ngx in
+    folder or put Paperless-ngx in
     a different location.
 
     !!! warning
 
         Paperless-ngx includes a `.env` file. This will set the project name
-        for docker compose to `paperless`, which will also define the name
+        for Docker Compose to `paperless`, which will also define the
-        of the volumes by paperless-ngx. However, if you experience that
+        volume names created by Paperless-ngx. However, if you notice that
         paperless-ngx is not using your old paperless volumes, verify the
         names of your volumes with
 
@@ -572,10 +556,10 @@ Migration to paperless-ngx is then performed in a few simple steps:
     after you migrated your existing SQLite database.
 
 5.  Adjust `docker-compose.yml` and `docker-compose.env` to your needs.
-    See [Docker setup](#docker) details on
+    See [Docker setup](#docker) for details on
-    which edits are advised.
+    which edits are recommended.
 
-6.  [Update paperless.](administration.md#updating)
+6.  Follow the update procedure in [Update paperless](administration.md#updating).
 
 7.  In order to find your existing documents with the new search
     feature, you need to invoke a one-time operation that will create
@@ -586,136 +570,99 @@ Migration to paperless-ngx is then performed in a few simple steps:
     ```
 
     This will migrate your database and create the search index. After
-    that, paperless will take care of maintaining the index by itself.
+    that, Paperless-ngx will maintain the index automatically.
 
-8.  Start paperless-ngx.
+8.  Start Paperless-ngx.
 
     ```bash
     docker compose up -d
     ```
 
-    This will run paperless in the background and automatically start it
+    This will run Paperless-ngx in the background and automatically start it
     on system boot.
 
-9.  Paperless installed a permanent redirect to `admin/` in your
+9.  Paperless may have installed a permanent redirect to `admin/` in your
     browser. This redirect is still in place and prevents access to the
-    new UI. Clear your browsing cache in order to fix this.
+    new UI. Clear your browser cache to fix this.
 
 10. Optionally, follow the instructions below to migrate your existing
     data to PostgreSQL.
 
-## Migrating from LinuxServer.io Docker Image
+<h3 id="migration_lsio">Migrating from LinuxServer.io Docker Image</h3>
 
-As with any upgrades and large changes, it is highly recommended to
+As with any upgrade or large change, it is highly recommended to
 create a backup before starting. This assumes the image was running
 using Docker Compose, but the instructions are translatable to Docker
 commands as well.
 
-1.  Stop and remove the paperless container
+1.  Stop and remove the Paperless container.
-2.  If using an external database, stop the container
+2.  If using an external database, stop that container.
-3.  Update Redis configuration
+3.  Update Redis configuration.
 
     1. If `REDIS_URL` is already set, change it to [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS)
        and continue to step 4.
 
-    1. Otherwise, in the `docker-compose.yml` add a new service for
+    1. Otherwise, add a new Redis service in `docker-compose.yml`,
-       Redis, following [the example compose
+       following [the example compose
        files](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose)
 
     1. Set the environment variable [`PAPERLESS_REDIS`](configuration.md#PAPERLESS_REDIS) so it points to
-       the new Redis container
+       the new Redis container.
 
-4.  Update user mapping
+4.  Update user mapping.
 
-    1. If set, change the environment variable `PUID` to `USERMAP_UID`
+    1. If set, change the environment variable `PUID` to `USERMAP_UID`.
 
-    1. If set, change the environment variable `PGID` to `USERMAP_GID`
+    1. If set, change the environment variable `PGID` to `USERMAP_GID`.
 
-5.  Update configuration paths
+5.  Update configuration paths.
 
-    1. Set the environment variable [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) to `/config`
+    1. Set the environment variable [`PAPERLESS_DATA_DIR`](configuration.md#PAPERLESS_DATA_DIR) to `/config`.
 
-6.  Update media paths
+6.  Update media paths.
 
     1. Set the environment variable [`PAPERLESS_MEDIA_ROOT`](configuration.md#PAPERLESS_MEDIA_ROOT) to
-       `/data/media`
+       `/data/media`.
 
-7.  Update timezone
+7.  Update timezone.
 
     1. Set the environment variable [`PAPERLESS_TIME_ZONE`](configuration.md#PAPERLESS_TIME_ZONE) to the same
-       value as `TZ`
+       value as `TZ`.
 
-8.  Modify the `image:` to point to
+8.  Modify `image:` to point to
     `ghcr.io/paperless-ngx/paperless-ngx:latest` or a specific version
     if preferred.
 9.  Start the containers as before, using `docker compose`.
 
-## Moving data from SQLite to PostgreSQL or MySQL/MariaDB {#sqlite_to_psql}
+## Running Paperless-ngx on less powerful devices {#less-powerful-devices data-toc-label="Less Powerful Devices"}
 
-The best way to migrate between database types is to perform an [export](administration.md#exporter) and then
+Paperless runs on Raspberry Pi. Some tasks can be slow on lower-powered
-[import](administration.md#importer) into a clean installation of Paperless-ngx.
+hardware, but a few settings can improve performance:
-
-## Moving back to Paperless
-
-Lets say you migrated to Paperless-ngx and used it for a while, but
-decided that you don't like it and want to move back (If you do, send
-me a mail about what part you didn't like!), you can totally do that
-with a few simple steps.
-
-Paperless-ngx modified the database schema slightly, however, these
-changes can be reverted while keeping your current data, so that your
-current data will be compatible with original Paperless. Thumbnails
-were also changed from PNG to WEBP format and will need to be
-re-generated.
-
-Execute this:
-
-```shell-session
-$ cd /path/to/paperless
-$ docker compose run --rm webserver migrate documents 0023
-```
-
-Or without docker:
-
-```shell-session
-$ cd /path/to/paperless/src
-$ python3 manage.py migrate documents 0023
-```
-
-After regenerating thumbnails, you'll need to clear your cookies
-(Paperless-ngx comes with updated dependencies that do cookie-processing
-differently) and probably your cache as well.
-
-# Considerations for less powerful devices {#less-powerful-devices}
-
-Paperless runs on Raspberry Pi. However, some things are rather slow on
-the Pi and configuring some options in paperless can help improve
-performance immensely:
 
 -   Stick with SQLite to save some resources. See [troubleshooting](troubleshooting.md#log-reports-creating-paperlesstask-failed)
     if you encounter issues with SQLite locking.
 -   If you do not need the filesystem-based consumer, consider disabling it
     entirely by setting [`PAPERLESS_CONSUMER_DISABLE`](configuration.md#PAPERLESS_CONSUMER_DISABLE) to `true`.
--   Consider setting [`PAPERLESS_OCR_PAGES`](configuration.md#PAPERLESS_OCR_PAGES) to 1, so that paperless will
+-   Consider setting [`PAPERLESS_OCR_PAGES`](configuration.md#PAPERLESS_OCR_PAGES) to 1, so that Paperless
-    only OCR the first page of your documents. In most cases, this page
+    OCRs only the first page of your documents. In most cases, this page
     contains enough information to be able to find it.
 -   [`PAPERLESS_TASK_WORKERS`](configuration.md#PAPERLESS_TASK_WORKERS) and [`PAPERLESS_THREADS_PER_WORKER`](configuration.md#PAPERLESS_THREADS_PER_WORKER) are
     configured to use all cores. The Raspberry Pi models 3 and up have 4
-    cores, meaning that paperless will use 2 workers and 2 threads per
+    cores, meaning that Paperless will use 2 workers and 2 threads per
     worker. This may result in sluggish response times during
     consumption, so you might want to lower these settings (example: 2
     workers and 1 thread to always have some computing power left for
     other tasks).
 -   Keep [`PAPERLESS_OCR_MODE`](configuration.md#PAPERLESS_OCR_MODE) at its default value `skip` and consider
-    OCR'ing your documents before feeding them into paperless. Some
+    OCRing your documents before feeding them into Paperless. Some
     scanners are able to do this!
 -   Set [`PAPERLESS_OCR_SKIP_ARCHIVE_FILE`](configuration.md#PAPERLESS_OCR_SKIP_ARCHIVE_FILE) to `with_text` to skip archive
-    file generation for already ocr'ed documents, or `always` to skip it
+    file generation for already OCRed documents, or `always` to skip it
     for all documents.
 -   If you want to perform OCR on the device, consider using
     `PAPERLESS_OCR_CLEAN=none`. This will speed up OCR times and use
     less memory at the expense of slightly worse OCR results.
--   If using docker, consider setting [`PAPERLESS_WEBSERVER_WORKERS`](configuration.md#PAPERLESS_WEBSERVER_WORKERS) to 1. This will save some memory.
+-   If using Docker, consider setting [`PAPERLESS_WEBSERVER_WORKERS`](configuration.md#PAPERLESS_WEBSERVER_WORKERS) to 1. This will save some memory.
 -   Consider setting [`PAPERLESS_ENABLE_NLTK`](configuration.md#PAPERLESS_ENABLE_NLTK) to false, to disable the
     more advanced language processing, which can take more memory and
     processing time.
@@ -727,17 +674,19 @@ For details, refer to [configuration](configuration.md).
     Updating the
     [automatic matching algorithm](advanced_usage.md#automatic-matching) takes quite a bit of time. However, the update mechanism
     checks if your data has changed before doing the heavy lifting. If you
-    experience the algorithm taking too much cpu time, consider changing the
+    experience the algorithm taking too much CPU time, consider changing the
     schedule in the admin interface to daily. You can also manually invoke
     the task by changing the date and time of the next run to today/now.
 
     The actual matching of the algorithm is fast and works on Raspberry Pi
     as well as on any other device.
 
-# Using nginx as a reverse proxy {#nginx}
+## Additional considerations
 
-Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Using-a-Reverse-Proxy-with-Paperless-ngx#nginx) for user-maintained documentation of using nginx with Paperless-ngx.
+**Using a reverse proxy with Paperless-ngx**
 
-# Enhancing security {#security}
+Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Using-a-Reverse-Proxy-with-Paperless-ngx#nginx) for user-maintained documentation on using nginx with Paperless-ngx.
 
-Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Using-Security-Tools-with-Paperless-ngx) for user-maintained documentation of how to configure security tools like Fail2ban with Paperless-ngx.
+**Enhancing security**
+
+Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Using-Security-Tools-with-Paperless-ngx) for user-maintained documentation on configuring security tools like Fail2ban with Paperless-ngx.

docs/troubleshooting.md

@@ -33,7 +33,7 @@ warns that
 `OCR for XX failed, but we're going to stick with what we've got since FORGIVING_OCR is enabled`,
 then you might need to install the [Tesseract language
 files](https://packages.ubuntu.com/search?keywords=tesseract-ocr)
-marching your document's languages.
+matching your document's languages.
 
 As an example, if you are running Paperless-ngx from any Ubuntu or
 Debian box, and your documents are written in Spanish you may need to
@@ -46,9 +46,9 @@ run:
 If you notice that the consumer will only pickup files in the
 consumption directory at startup, but won't find any other files added
 later, you will need to enable filesystem polling with the configuration
-option [`PAPERLESS_CONSUMER_POLLING`](configuration.md#PAPERLESS_CONSUMER_POLLING).
+option [`PAPERLESS_CONSUMER_POLLING_INTERVAL`](configuration.md#PAPERLESS_CONSUMER_POLLING_INTERVAL).
 
-This will disable listening to filesystem changes with inotify and
+This will disable automatic listening for filesystem changes and
 paperless will manually check the consumption directory for changes
 instead.
 
@@ -130,7 +130,7 @@ command:
     - 'gotenberg'
     - '--chromium-disable-javascript=true'
     - '--chromium-allow-list=file:///tmp/.*'
-    - '--api-timeout=60'
+    - '--api-timeout=60s'
 ```
 
 ## Permission denied errors in the consumption directory
@@ -234,47 +234,9 @@ FileNotFoundError: [Errno 2] No such file or directory: '/tmp/ocrmypdf.io.yhk3zb
 
 This probably indicates paperless tried to consume the same file twice.
 This can happen for a number of reasons, depending on how documents are
-placed into the consume folder. If paperless is using inotify (the
+placed into the consume folder, such as how a scanner may modify a file multiple times as it scans.
-default) to check for documents, try adjusting the
+Try adjusting the
-[inotify configuration](configuration.md#inotify). If polling is enabled, try adjusting the
+[file stability delay](configuration.md#PAPERLESS_CONSUMER_STABILITY_DELAY) to a larger value.
-[polling configuration](configuration.md#polling).
-
-## Consumer fails waiting for file to remain unmodified.
-
-You might find messages like these in your log files:
-
-```
-[ERROR] [paperless.management.consumer] Timeout while waiting on file /usr/src/paperless/src/../consume/SCN_0001.pdf to remain unmodified.
-```
-
-This indicates paperless timed out while waiting for the file to be
-completely written to the consume folder. Adjusting
-[polling configuration](configuration.md#polling) values should resolve the issue.
-
-!!! note
-
-    The user will need to manually move the file out of the consume folder
-    and back in, for the initial failing file to be consumed.
-
-## Consumer fails reporting "OS reports file as busy still".
-
-You might find messages like these in your log files:
-
-```
-[WARNING] [paperless.management.consumer] Not consuming file /usr/src/paperless/src/../consume/SCN_0001.pdf: OS reports file as busy still
-```
-
-This indicates paperless was unable to open the file, as the OS reported
-the file as still being in use. To prevent a crash, paperless did not
-try to consume the file. If paperless is using inotify (the default) to
-check for documents, try adjusting the
-[inotify configuration](configuration.md#inotify). If polling is enabled, try adjusting the
-[polling configuration](configuration.md#polling).
-
-!!! note
-
-    The user will need to manually move the file out of the consume folder
-    and back in, for the initial failing file to be consumed.
 
 ## Log reports "Creating PaperlessTask failed".
 
@@ -335,7 +297,7 @@ You may see errors when deleting documents like:
 Data too long for column 'transaction_id' at row 1
 ```
 
-This error can occur in installations which have upgraded from a version of Paperless-ngx that used Django 4 (Paperless-ngx versions prior to v2.13.0) with a MariaDB/MySQL database. Due to the backawards-incompatible change in Django 5, the column "documents_document.transaction_id" will need to be re-created, which can be done with a one-time run of the following management command:
+This error can occur in installations which have upgraded from a version of Paperless-ngx that used Django 4 (Paperless-ngx versions prior to v2.13.0) with a MariaDB/MySQL database. Due to the backwards-incompatible change in Django 5, the column "documents_document.transaction_id" will need to be re-created, which can be done with a one-time run of the following management command:
 
 ```shell-session
 $ python3 manage.py convert_mariadb_uuid

docs/usage.md

@@ -1,4 +1,8 @@
-# Usage Overview
+---
+title: Basic Usage
+---
+
+# Usage
 
 Paperless-ngx is an application that manages your personal documents. With
 the (optional) help of a document scanner (see [the scanners wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Scanner-&-Software-Recommendations)), Paperless-ngx transforms your unwieldy
@@ -30,6 +34,9 @@ Each document has data fields that you can assign to them:
 -   A _document type_ is used to demarcate the type of a document such
     as letter, bank statement, invoice, contract, etc. It is used to
     identify what a document is about.
+-   The document _storage path_ is the location where the document files
+    are stored. See [Storage Paths](advanced_usage.md#storage-paths) for
+    more information.
 -   The _date added_ of a document is the date the document was scanned
     into paperless. You cannot and should not change this date.
 -   The _date created_ of a document is the date the document was
@@ -82,6 +89,17 @@ You can view the document, edit its metadata, assign tags, correspondents,
 document types, and custom fields. You can also view the document history,
 download the document or share it via a share link.
 
+### Document File Versions
+
+Think of versions as **file history** for a document.
+
+-   Versions track the underlying file and extracted text content (OCR/text).
+-   Metadata such as tags, correspondent, document type, storage path and custom fields stay on the "root" document.
+-   Version files follow normal filename formatting (including storage paths) and add a `_vN` suffix (for example `_v1`, `_v2`).
+-   By default, search and document content use the latest version.
+-   In document detail, selecting a version switches the preview, file metadata and content (and download etc buttons) to that version.
+-   Deleting a non-root version keeps metadata and falls back to the latest remaining version.
+
 ### Management Lists
 
 Paperless-ngx includes management lists for tags, correspondents, document types
@@ -89,7 +107,17 @@ and more. These areas allow you to view, add, edit, delete and manage permission
 for these objects. You can also manage saved views, mail accounts, mail rules,
 workflows and more from the management sections.
 
-## Adding documents to paperless
+### Nested Tags
+
+Paperless-ngx v2.19 introduces support for nested tags, allowing you to create a
+hierarchy of tags, which may be useful for organizing your documents. Tags can
+have a 'parent' tag, creating a tree-like structure, to a maximum depth of 5. When
+a tag is added to a document, all of its parent tags are also added automatically
+and similarly, when a tag is removed from a document, all of its child tags are
+also removed. Additionally, assigning a parent to an existing tag will automatically
+update all documents that have this tag assigned, adding the parent tag as well.
+
+## Adding documents to Paperless-ngx
 
 Once you've got Paperless setup, you need to start feeding documents
 into it. When adding documents to paperless, it will perform the
@@ -115,7 +143,8 @@ following operations on your documents:
 
     No matter which options you choose, Paperless will always store the
     original document that it found in the consumption directory or in the
-    mail and will never overwrite that document. Archived versions are
+    mail and will never overwrite that document (except when using certain
+    document actions, which make that clear). Archived versions are
     stored alongside the original versions. Any files found in the
     consumption directory will stored inside the Paperless-ngx file
     structure and will not be retained in the consumption directory.
@@ -159,7 +188,7 @@ process.
 Please see [the wiki](https://github.com/paperless-ngx/paperless-ngx/wiki/Related-Projects) for a user-maintained list of related projects and
 software (e.g. for mobile devices) that is compatible with Paperless-ngx.
 
-### Email {#usage-email}
+### Incoming Email {#incoming-mail}
 
 You can tell paperless-ngx to consume documents from your email
 accounts. This is a very flexible and powerful feature, if you regularly
@@ -247,6 +276,10 @@ different means. These are as follows:
 Paperless is set up to check your mails every 10 minutes. This can be
 configured via [`PAPERLESS_EMAIL_TASK_CRON`](configuration.md#PAPERLESS_EMAIL_TASK_CRON)
 
+#### Processed Mail
+
+Paperless keeps track of emails it has processed in order to avoid processing the same mail multiple times. This uses the message `UID` provided by the mail server, which should be unique for each message. You can view and manage processed mails from the web UI under Mail > Processed Mails. If you need to re-process a message, you can delete the corresponding processed mail entry, which will allow Paperless-ngx to process the email again the next time the mail fetch task runs.
+
 #### OAuth Email Setup
 
 Paperless-ngx supports OAuth2 authentication for Gmail and Outlook email accounts. To set up an email account with OAuth2, you will need to create a 'developer' app with the respective provider and obtain the client ID and client secret and set the appropriate [configuration variables](configuration.md#email_oauth). You will also need to set either [`PAPERLESS_OAUTH_CALLBACK_BASE_URL`](configuration.md#PAPERLESS_OAUTH_CALLBACK_BASE_URL) or [`PAPERLESS_URL`](configuration.md#PAPERLESS_URL) to the correct value for the OAuth2 flow to work correctly.
@@ -260,6 +293,55 @@ Once setup, navigating to the email settings page in Paperless-ngx will allow yo
 You can also submit a document using the REST API, see [POSTing documents](api.md#file-uploads)
 for details.
 
+## Document Suggestions
+
+Paperless-ngx can suggest tags, correspondents, document types and storage paths for documents based on the content of the document. This is done using a (non-LLM) machine learning model that is trained on the documents in your database. The suggestions are shown in the document detail page and can be accepted or rejected by the user.
+
+## AI Features
+
+Paperless-ngx includes several features that use AI to enhance the document management experience. These features are optional and can be enabled or disabled in the settings. If you are using the AI features, you may want to also enable the "LLM index" feature, which supports Retrieval-Augmented Generation (RAG) designed to improve the quality of AI responses. The LLM index feature is not enabled by default and requires additional configuration.
+
+!!! warning
+
+    Remember that Paperless-ngx will send document content to the AI provider you have configured, so consider the privacy implications of using these features, especially if using a remote model (e.g. OpenAI), instead of the default local model.
+
+The AI features work by creating an embedding of the text content and metadata of documents, which is then used for various tasks such as similarity search and question answering. This uses the FAISS vector store.
+
+### AI-Enhanced Suggestions
+
+If enabled, Paperless-ngx can use an AI LLM model to suggest document titles, dates, tags, correspondents and document types for documents. This feature will always be "opt-in" and does not disable the existing classifier-based suggestion system. Currently, both remote (via the OpenAI API) and local (via Ollama) models are supported, see [configuration](configuration.md#ai) for details.
+
+### Document Chat
+
+Paperless-ngx can use an AI LLM model to answer questions about a document or across multiple documents. Again, this feature works best when RAG is enabled. The chat feature is available in the upper app toolbar and will switch between chatting across multiple documents or a single document based on the current view.
+
+## Sharing documents from Paperless-ngx
+
+Paperless-ngx supports sharing documents with other users by assigning them [permissions](#object-permissions)
+to the document. Document files can also be shared externally via [share links](#share-links), [email](#email-sharing)
+or using [email](#workflow-action-email) or [webhook](#workflow-action-webhook) actions in workflows.
+
+### Share Links
+
+"Share links" are public links to files (or an archive of files) and can be created and managed under the 'Send' button on the document detail screen or from the bulk editor.
+
+-   Share links do not require a user to login and thus link directly to a file or bundled download.
+-   Links are unique and are of the form `{paperless-url}/share/{randomly-generated-slug}`.
+-   Links can optionally have an expiration time set.
+-   After a link expires or is deleted users will be redirected to the regular paperless-ngx login.
+-   From the document detail screen you can create a share link for that single document.
+-   From the bulk editor you can create a **share link bundle** for any selection. Paperless-ngx prepares a ZIP archive in the background and exposes a single share link. You can revisit the "Manage share link bundles" dialog to monitor progress, retry failed bundles, or delete links.
+
+!!! tip
+
+    If your paperless-ngx instance is behind a reverse-proxy you may want to create an exception to bypass any authentication layers that are part of your setup in order to make links truly publicly-accessible. Of course, do so with caution.
+
+### Email Sharing {#email-sharing}
+
+Paperless-ngx supports directly sending documents via email. If an email server has been [configured](configuration.md#email-sending)
+the "Send" button on the document detail page will include an "Email" option. You can also share files via email automatically by using
+a [workflow action](#workflow-action-email).
+
 ## Permissions
 
 Permissions in Paperless-ngx are based around ['global' permissions](#global-permissions) as well as
@@ -301,6 +383,11 @@ permissions can be granted to limit access to certain parts of the UI (and corre
 
 Superusers can access all parts of the front and backend application as well as any and all objects. Superuser status can only be granted by another superuser.
 
+!!! tip
+
+    Because superuser accounts can see all objects and documents, you may want to use a regular account for day-to-day use. Additional superuser accounts can
+    be created via [cli](administration.md#create-superuser) or granted superuser status from an existing superuser account.
+
 #### Admin Status
 
 Admin status (Django 'staff status') grants access to viewing the paperless logs and the system status dialog
@@ -312,25 +399,25 @@ Global permissions define what areas of the app and API endpoints users can acce
 determine if a user can create, edit, delete or view _any_ documents, but individual documents themselves
 still have "object-level" permissions.
 
-| Type          | Details                                                                                                                                                                  |
+| Type          | Details                                                                                                                                                                                                                         |
-| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| AppConfig     | _Change_ or higher permissions grants access to the "Application Configuration" area.                                                                                    |
+| AppConfig     | _Change_ or higher permissions grants access to the "Application Configuration" area.                                                                                                                                           |
-| Correspondent | Add, edit, delete or view Correspondents.                                                                                                                                |
+| Correspondent | Add, edit, delete or view Correspondents.                                                                                                                                                                                       |
-| CustomField   | Add, edit, delete or view Custom Fields.                                                                                                                                 |
+| CustomField   | Add, edit, delete or view Custom Fields.                                                                                                                                                                                        |
-| Document      | Add, edit, delete or view Documents.                                                                                                                                     |
+| Document      | Add, edit, delete or view Documents.                                                                                                                                                                                            |
-| DocumentType  | Add, edit, delete or view Document Types.                                                                                                                                |
+| DocumentType  | Add, edit, delete or view Document Types.                                                                                                                                                                                       |
-| Group         | Add, edit, delete or view Groups.                                                                                                                                        |
+| Group         | Add, edit, delete or view Groups.                                                                                                                                                                                               |
-| MailAccount   | Add, edit, delete or view Mail Accounts.                                                                                                                                 |
+| MailAccount   | Add, edit, delete or view Mail Accounts.                                                                                                                                                                                        |
-| MailRule      | Add, edit, delete or view Mail Rules.                                                                                                                                    |
+| MailRule      | Add, edit, delete or view Mail Rules.                                                                                                                                                                                           |
-| Note          | Add, edit, delete or view Notes.                                                                                                                                         |
+| Note          | Add, edit, delete or view Notes.                                                                                                                                                                                                |
-| PaperlessTask | View or dismiss (_Change_) File Tasks.                                                                                                                                   |
+| PaperlessTask | View or dismiss (_Change_) File Tasks.                                                                                                                                                                                          |
-| SavedView     | Add, edit, delete or view Saved Views.                                                                                                                                   |
+| SavedView     | Add, edit, delete or view Saved Views.                                                                                                                                                                                          |
-| ShareLink     | Add, delete or view Share Links.                                                                                                                                         |
+| ShareLink     | Add, delete or view Share Links.                                                                                                                                                                                                |
-| StoragePath   | Add, edit, delete or view Storage Paths.                                                                                                                                 |
+| StoragePath   | Add, edit, delete or view Storage Paths.                                                                                                                                                                                        |
-| Tag           | Add, edit, delete or view Tags.                                                                                                                                          |
+| Tag           | Add, edit, delete or view Tags.                                                                                                                                                                                                 |
-| UISettings    | Add, edit, delete or view the UI settings that are used by the web app.<br/>:warning: **Users that will access the web UI must be granted at least _View_ permissions.** |
+| UISettings    | Add, edit, delete or view the UI settings that are used by the web app.<br/>:warning: **Users that will access the web UI must be granted at least _View_ permissions.**                                                        |
-| User          | Add, edit, delete or view Users.                                                                                                                                         |
+| User          | Add, edit, delete or view Users.                                                                                                                                                                                                |
-| Workflow      | Add, edit, delete or view Workflows.<br/>Note that Workflows are global, in other words all users who can access workflows have access to the same set of them.          |
+| Workflow      | Add, edit, delete or view Workflows.<br/>Note that Workflows are global; all users who can access workflows see the same set. Workflows have other permission implications — see [Workflow permissions](#workflow-permissions). |
 
 #### Detailed Explanation of Object Permissions {#object-permissions}
 
@@ -369,9 +456,9 @@ fields and permissions, which will be merged.
 
 ### Workflow Triggers
 
-#### Types
+#### Types {#workflow-trigger-types}
 
-Currently, there are three events that correspond to workflow trigger 'types':
+Currently, there are four events that correspond to workflow trigger 'types':
 
 1. **Consumption Started**: _before_ a document is consumed, so events can include filters by source (mail, consumption
    folder or API), file path, file name, mail rule
@@ -379,11 +466,12 @@ Currently, there are three events that correspond to workflow trigger 'types':
    but the document content has been extracted and metadata such as document type, tags, etc. have been set, so these can now
    be used for filtering.
 3. **Document Updated**: when a document is updated. Similar to 'added' events, triggers can include filtering by content matching,
-   tags, doc type, or correspondent.
+   tags, doc type, correspondent or storage path.
 4. **Scheduled**: a scheduled trigger that can be used to run workflows at a specific time. The date used can be either the document
-   added, created, updated date or you can specify a (date) custom field. You can also specify a day offset from the date.
+   added, created, updated date or you can specify a (date) custom field. You can also specify a day offset from the date (positive
+   offsets will trigger after the date, negative offsets will trigger before).
 
-The following flow diagram illustrates the three document trigger types:
+The following flow diagram illustrates the four document trigger types:
 
 ```mermaid
 flowchart TD
@@ -399,6 +487,10 @@ flowchart TD
     'Updated'
     trigger(s)"}
 
+    scheduled{"Documents
+    matching
+    trigger(s)"}
+
     A[New Document] --> consumption
     consumption --> |Yes| C[Workflow Actions Run]
     consumption --> |No| D
@@ -411,6 +503,11 @@ flowchart TD
     updated --> |Yes| J[Workflow Actions Run]
     updated --> |No| K
     J --> K[Document Saved]
+    L[Scheduled Task Check<br/>hourly at :05] --> M[Get All Scheduled Triggers]
+    M --> scheduled
+    scheduled --> |Yes| N[Workflow Actions Run]
+    scheduled --> |No| O[Document Saved]
+    N --> O
 ```
 
 #### Filters {#workflow-trigger-filters}
@@ -418,22 +515,32 @@ flowchart TD
 Workflows allow you to filter by:
 
 -   Source, e.g. documents uploaded via consume folder, API (& the web UI) and mail fetch
--   File name, including wildcards e.g. \*.pdf will apply to all pdfs
+-   File name, including wildcards e.g. \*.pdf will apply to all pdfs.
 -   File path, including wildcards. Note that enabling `PAPERLESS_CONSUMER_RECURSIVE` would allow, for
     example, automatically assigning documents to different owners based on the upload directory.
 -   Mail rule. Choosing this option will force 'mail fetch' to be the workflow source.
--   Content matching (`Added` and `Updated` triggers only). Filter document content using the matching settings.
+-   Content matching (`Added`, `Updated` and `Scheduled` triggers only). Filter document content using the matching settings.
--   Tags (`Added` and `Updated` triggers only). Filter for documents with any of the specified tags
+
--   Document type (`Added` and `Updated` triggers only). Filter documents with this doc type
+There are also 'advanced' filters available for `Added`, `Updated` and `Scheduled` triggers:
--   Correspondent (`Added` and `Updated` triggers only). Filter documents with this correspondent
+
+-   Any Tags: Filter for documents with any of the specified tags.
+-   All Tags: Filter for documents with all of the specified tags.
+-   No Tags: Filter for documents with none of the specified tags.
+-   Document type: Filter documents with this document type.
+-   Not Document types: Filter documents without any of these document types.
+-   Correspondent: Filter documents with this correspondent.
+-   Not Correspondents: Filter documents without any of these correspondents.
+-   Storage path: Filter documents with this storage path.
+-   Not Storage paths: Filter documents without any of these storage paths.
+-   Custom field query: Filter documents with a custom field query (the same as used for the document list filters).
 
 ### Workflow Actions
 
-#### Types
+#### Types {#workflow-action-types}
 
 The following workflow action types are available:
 
-##### Assignment
+##### Assignment {#workflow-action-assignment}
 
 "Assignment" actions can assign:
 
@@ -443,7 +550,7 @@ The following workflow action types are available:
 -   View and / or edit permissions to users or groups
 -   Custom fields. Note that no value for the field will be set
 
-##### Removal
+##### Removal {#workflow-action-removal}
 
 "Removal" actions can remove either all of or specific sets of the following:
 
@@ -452,7 +559,7 @@ The following workflow action types are available:
 -   View and / or edit permissions
 -   Custom fields
 
-##### Email
+##### Email {#workflow-action-email}
 
 "Email" actions can send documents via email. This action requires a mail server to be [configured](configuration.md#email-sending). You can specify:
 
@@ -460,7 +567,7 @@ The following workflow action types are available:
 -   The subject and body of the email, which can include placeholders, see [placeholders](usage.md#workflow-placeholders) below
 -   Whether to include the document as an attachment
 
-##### Webhook
+##### Webhook {#workflow-action-webhook}
 
 "Webhook" actions send a POST request to a specified URL. You can specify:
 
@@ -469,44 +576,79 @@ The following workflow action types are available:
 -   Encoding for the request body, either JSON or form data
 -   The request headers as key-value pairs
 
+For security reasons, webhooks can be limited to specific ports and disallowed from connecting to local URLs. See the relevant
+[configuration settings](configuration.md#workflow-webhooks) to change this behavior. If you are allowing non-admins to create workflows,
+you may want to adjust these settings to prevent abuse.
+
+##### Move to Trash {#workflow-action-move-to-trash}
+
+"Move to Trash" actions move the document to the trash. The document can be restored
+from the trash until the trash is emptied (after the configured delay or manually).
+
+The "Move to Trash" action will always be executed at the end of the workflow run,
+regardless of its position in the action list. After a "Move to Trash" action is executed
+no other workflow will be executed on the document.
+
+If a "Move to Trash" action is executed in a consume pipeline, the consumption
+will be aborted and the file will be deleted.
+
 #### Workflow placeholders
 
-Some workflow text can include placeholders but the available options differ depending on the type of
+Titles and webhook payloads can be generated by workflows using [Jinja templates](https://jinja.palletsprojects.com/en/3.1.x/templates/).
-workflow trigger. This is because at the time of consumption (when the text is to be set), no automatic tags etc. have been
+This allows for complex logic to be used, including [logical structures](https://jinja.palletsprojects.com/en/3.1.x/templates/#list-of-control-structures)
-applied. You can use the following placeholders with any trigger type:
+and [filters](https://jinja.palletsprojects.com/en/3.1.x/templates/#id11).
+The template is provided as a string.
 
--   `{correspondent}`: assigned correspondent name
+Using Jinja2 Templates is also useful for [Date localization](advanced_usage.md#date-localization) in the title.
--   `{document_type}`: assigned document type name
+
--   `{owner_username}`: assigned owner username
+The available inputs differ depending on the type of workflow trigger.
--   `{added}`: added datetime
+This is because at the time of consumption (when the text is to be set), no automatic tags etc. have been
--   `{added_year}`: added year
+applied. You can use the following placeholders in the template with any trigger type:
--   `{added_year_short}`: added year
+
--   `{added_month}`: added month
+-   `{{correspondent}}`: assigned correspondent name
--   `{added_month_name}`: added month name
+-   `{{document_type}}`: assigned document type name
--   `{added_month_name_short}`: added month short name
+-   `{{owner_username}}`: assigned owner username
--   `{added_day}`: added day
+-   `{{added}}`: added datetime
--   `{added_time}`: added time in HH:MM format
+-   `{{added_year}}`: added year
--   `{original_filename}`: original file name without extension
+-   `{{added_year_short}}`: added year
--   `{filename}`: current file name without extension
+-   `{{added_month}}`: added month
+-   `{{added_month_name}}`: added month name
+-   `{{added_month_name_short}}`: added month short name
+-   `{{added_day}}`: added day
+-   `{{added_time}}`: added time in HH:MM format
+-   `{{original_filename}}`: original file name without extension
+-   `{{filename}}`: current file name without extension (for "added" workflows this may not be final yet, you can use `{{original_filename}}`)
+-   `{{doc_title}}`: current document title (cannot be used in title assignment)
 
 The following placeholders are only available for "added" or "updated" triggers
 
--   `{created}`: created datetime
+-   `{{created}}`: created datetime
--   `{created_year}`: created year
+-   `{{created_year}}`: created year
--   `{created_year_short}`: created year
+-   `{{created_year_short}}`: created year
--   `{created_month}`: created month
+-   `{{created_month}}`: created month
--   `{created_month_name}`: created month name
+-   `{{created_month_name}}`: created month name
--   `{created_month_name_short}`: created month short name
+-   `{{created_month_name_short}}`: created month short name
--   `{created_day}`: created day
+-   `{{created_day}}`: created day
--   `{created_time}`: created time in HH:MM format
+-   `{{created_time}}`: created time in HH:MM format
--   `{doc_url}`: URL to the document in the web UI. Requires the `PAPERLESS_URL` setting to be set.
+-   `{{doc_url}}`: URL to the document in the web UI. Requires the `PAPERLESS_URL` setting to be set.
+-   `{{doc_id}}`: Document ID
+
+##### Examples
+
+```jinja2
+{{ created | localize_date('MMMM', 'en_US') }}
+<!-- Output: "January" -->
+
+{{ added | localize_date('MMMM', 'de_DE') }}
+<!-- Output: "Juni" --> # codespell:ignore
+```
 
 ### Workflow permissions
 
 All users who have application permissions for editing workflows can see the same set
 of workflows. In other words, workflows themselves intentionally do not have an owner or permissions.
 
-Given their potentially far-reaching capabilities, you may want to restrict access to workflows.
+Given their potentially far-reaching capabilities, including changing the permissions of existing documents, you may want to restrict access to workflows.
 
 Upon migration, existing installs will grant access to workflows to users who can add
 documents (and superusers who can always access all parts of the app).
@@ -544,27 +686,16 @@ The following custom field types are supported:
 -   `Document Link`: reference(s) to other document(s) displayed as links, automatically creates a symmetrical link in reverse
 -   `Select`: a pre-defined list of strings from which the user can choose
 
-## Share Links
-
-Paperless-ngx added the ability to create shareable links to files in version 2.0. You can find the button for this on the document detail screen.
-
--   Share links do not require a user to login and thus link directly to a file.
--   Links are unique and are of the form `{paperless-url}/share/{randomly-generated-slug}`.
--   Links can optionally have an expiration time set.
--   After a link expires or is deleted users will be redirected to the regular paperless-ngx login.
-
-!!! tip
-
-    If your paperless-ngx instance is behind a reverse-proxy you may want to create an exception to bypass any authentication layers that are part of your setup in order to make links truly publicly-accessible. Of course, do so with caution.
-
 ## PDF Actions
 
-Paperless-ngx supports four basic editing operations for PDFs (these operations currently cannot be performed on non-PDF files):
+Paperless-ngx supports basic editing operations for PDFs (these operations currently cannot be performed on non-PDF files). When viewing an individual document you can
+open the 'PDF Editor' to use a simple UI for re-arranging, rotating, deleting pages and splitting documents.
 
 -   Merging documents: available when selecting multiple documents for 'bulk editing'.
--   Rotating documents: available when selecting multiple documents for 'bulk editing' and from an individual document's details page.
+-   Rotating documents: available when selecting multiple documents for 'bulk editing' and via the pdf editor on an individual document's details page.
--   Splitting documents: available from an individual document's details page.
+-   Splitting documents: via the pdf editor on an individual document's details page.
--   Deleting pages: available from an individual document's details page.
+-   Deleting pages: via the pdf editor on an individual document's details page.
+-   Re-arranging pages: via the pdf editor on an individual document's details page.
 
 !!! important
 
@@ -582,7 +713,7 @@ When you first delete a document it is moved to the 'trash' until either it is e
 You can set how long documents remain in the trash before being automatically deleted with [`PAPERLESS_EMPTY_TRASH_DELAY`](configuration.md#PAPERLESS_EMPTY_TRASH_DELAY), which defaults
 to 30 days. Until the file is actually deleted (e.g. the trash is emptied), all files and database content remains intact and can be restored at any point up until that time.
 
-Additionally you may configure a directory where deleted files are moved to when they the trash is emptied with [`PAPERLESS_EMPTY_TRASH_DIR`](configuration.md#PAPERLESS_EMPTY_TRASH_DIR).
+Additionally you may configure a directory where deleted files are moved to when the trash is emptied with [`PAPERLESS_EMPTY_TRASH_DIR`](configuration.md#PAPERLESS_EMPTY_TRASH_DIR).
 Note that the empty trash directory only stores the original file, the archive file and all database information is permanently removed once a document is fully deleted.
 
 ## Best practices {#basic-searching}
@@ -827,6 +958,21 @@ how regularly you intend to scan documents and use paperless.
     performed the task associated with the document, move it to the
     inbox.
 
+## Remote OCR
+
+!!! important
+
+    This feature is disabled by default and will always remain strictly "opt-in".
+
+Paperless-ngx supports performing OCR on documents using remote services. At the moment, this is limited to
+[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
+This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
+Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
+the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
+
+Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
+or page limitations (e.g. with a free tier).
+
 ## Architecture
 
 Paperless-ngx consists of the following components:

install-paperless-ngx.sh

@@ -52,12 +52,12 @@ if ! command -v wget &> /dev/null ; then
 fi
 
 if ! command -v docker &> /dev/null ; then
-	echo "docker executable not found. Is docker installed?"
+	echo "docker executable not found. Is Docker installed?"
 	exit 1
 fi
 
 if ! docker compose &> /dev/null ; then
-	echo "docker compose plugin not found. Is docker compose installed?"
+	echo "docker compose plugin not found. Is Docker Compose installed?"
 	exit 1
 fi
 
@@ -66,7 +66,7 @@ fi
 if ! docker stats --no-stream &> /dev/null ; then
 	echo ""
 	echo "WARN: It look like the current user does not have Docker permissions."
-	echo "WARN: Use 'sudo usermod -aG docker $USER' to assign Docker permissions to the user (may require restarting shell)."
+	echo "WARN: Use 'sudo usermod -aG docker $USER' to assign Docker permissions to the user (may require restarting the shell)."
 	echo ""
 	sleep 3
 fi
@@ -135,7 +135,7 @@ DATABASE_BACKEND=$ask_result
 
 echo ""
 echo "Paperless is able to use Apache Tika to support Office documents such as"
-echo "Word, Excel, Powerpoint, and Libreoffice equivalents. This feature"
+echo "Word, Excel, PowerPoint, and LibreOffice equivalents. This feature"
 echo "requires more resources due to the required services."
 echo ""
 
@@ -157,7 +157,7 @@ echo ""
 echo "Specify the user id and group id you wish to run paperless as."
 echo "Paperless will also change ownership on the data, media and consume"
 echo "folder to the specified values, so it's a good idea to supply the user id"
-echo "and group id of your unix user account."
+echo "and group id of your Unix user account."
 echo "If unsure, leave default."
 echo ""
 
@@ -212,7 +212,7 @@ if [[ "$DATABASE_BACKEND" == "sqlite" ]] ; then
 	echo -n "SQLite database, the "
 fi
 echo "search index and other data."
-echo "As with the media folder, leave empty to have this managed by docker."
+echo "As with the media folder, leave empty to have this managed by Docker."
 echo ""
 echo "CAUTION: If specified, you must specify an absolute path starting with /"
 echo "or a relative path starting with ./ here."
@@ -224,7 +224,7 @@ DATA_FOLDER=$ask_result
 if [[ "$DATABASE_BACKEND" == "postgres" || "$DATABASE_BACKEND" == "mariadb" ]] ; then
 	echo ""
 	echo "The database folder, where your database stores its data."
-	echo "Leave empty to have this managed by docker."
+	echo "Leave empty to have this managed by Docker."
 	echo ""
 	echo "CAUTION: If specified, you must specify an absolute path starting with /"
 	echo "or a relative path starting with ./ here."
@@ -276,18 +276,18 @@ echo ""
 echo "Target folder: $TARGET_FOLDER"
 echo "Consume folder: $CONSUME_FOLDER"
 if [[ -z $MEDIA_FOLDER ]] ; then
-	echo "Media folder: Managed by docker"
+	echo "Media folder: Managed by Docker"
 else
 	echo "Media folder: $MEDIA_FOLDER"
 fi
 if [[ -z $DATA_FOLDER ]] ; then
-	echo "Data folder: Managed by docker"
+	echo "Data folder: Managed by Docker"
 else
 	echo "Data folder: $DATA_FOLDER"
 fi
 if [[ "$DATABASE_BACKEND" == "postgres" || "$DATABASE_BACKEND" == "mariadb" ]] ; then
 	if [[ -z $DATABASE_FOLDER ]] ; then
-		echo "Database folder: Managed by docker"
+		echo "Database folder: Managed by Docker"
 	else
 		echo "Database folder: $DATABASE_FOLDER"
 	fi
@@ -374,7 +374,7 @@ fi
 # of the provided folder
 if [[ -n $DATABASE_FOLDER ]] ; then
 	if [[ "$DATABASE_BACKEND" == "postgres" ]] ; then
-		sed -i "s#- pgdata:/var/lib/postgresql/data#- $DATABASE_FOLDER:/var/lib/postgresql/data#g" docker-compose.yml
+		sed -i "s#- pgdata:/var/lib/postgresql#- $DATABASE_FOLDER:/var/lib/postgresql#g" docker-compose.yml
 		sed -i "/^\s*pgdata:/d" docker-compose.yml
 	elif [[ "$DATABASE_BACKEND" == "mariadb" ]]; then
 		sed -i "s#- dbdata:/var/lib/mysql#- $DATABASE_FOLDER:/var/lib/mysql#g" docker-compose.yml

mkdocs.yml

@@ -1,87 +0,0 @@
-site_name: Paperless-ngx
-theme:
-  name: material
-  logo: assets/logo.svg
-  font:
-    text: Roboto
-    code: Roboto Mono
-  palette:
-    # Palette toggle for automatic mode
-    - media: "(prefers-color-scheme)"
-      toggle:
-        icon: material/brightness-auto
-        name: Switch to light mode
-
-    # Palette toggle for light mode
-    - media: "(prefers-color-scheme: light)"
-      scheme: default
-      toggle:
-        icon: material/brightness-7
-        name: Switch to dark mode
-
-    # Palette toggle for dark mode
-    - media: "(prefers-color-scheme: dark)"
-      scheme: slate
-      toggle:
-        icon: material/brightness-4
-        name: Switch to system preference
-  features:
-    - navigation.tabs
-    - navigation.top
-    - toc.integrate
-    - content.code.annotate
-  icon:
-    repo: fontawesome/brands/github
-  favicon: assets/favicon.png
-repo_url: https://github.com/paperless-ngx/paperless-ngx
-repo_name: paperless-ngx/paperless-ngx
-edit_uri: blob/main/docs/
-extra_css:
-  - assets/extra.css
-markdown_extensions:
-  - attr_list
-  - md_in_html
-  - def_list
-  - admonition
-  - tables
-  - pymdownx.highlight:
-      anchor_linenums: true
-  - pymdownx.superfences
-  - pymdownx.inlinehilite
-  - pymdownx.snippets
-  - footnotes
-  - pymdownx.superfences:
-      custom_fences:
-        - name: mermaid
-          class: mermaid
-          format: !!python/name:pymdownx.superfences.fence_code_format
-  - pymdownx.emoji:
-      emoji_index: !!python/name:material.extensions.emoji.twemoji
-      emoji_generator: !!python/name:material.extensions.emoji.to_svg
-strict: true
-nav:
-    - index.md
-    - setup.md
-    - 'Basic Usage': usage.md
-    - configuration.md
-    - administration.md
-    - advanced_usage.md
-    - 'REST API': api.md
-    - development.md
-    - 'FAQs': faq.md
-    - troubleshooting.md
-    - changelog.md
-copyright: Copyright © 2016 - 2023 Daniel Quinn, Jonas Winkler, and the Paperless-ngx team
-extra:
-  social:
-    - icon: fontawesome/brands/github
-      link: https://github.com/paperless-ngx/paperless-ngx
-    - icon: fontawesome/brands/docker
-      link: https://hub.docker.com/r/paperlessngx/paperless-ngx
-    - icon: material/chat
-      link: https://matrix.to/#/#paperless:matrix.org
-plugins:
-  - search
-  - glightbox:
-       skip_classes:
-         - no-lightbox

paperless-ngx.code-workspace

@@ -33,6 +33,8 @@
 			"**/coverage.json": true
 		},
 		"python.defaultInterpreterPath": ".venv/bin/python3",
+		"python.analysis.inlayHints.pytestParameters": true,
+		"python.testing.pytestEnabled": true,
 	},
 	"extensions": {
 		"recommendations": ["ms-python.python", "charliermarsh.ruff", "editorconfig.editorconfig"],

paperless.conf.example

@@ -1,10 +1,6 @@
 # Have a look at the docs for documentation.
 # https://docs.paperless-ngx.com/configuration/
 
-# Debug. Only enable this for development.
-
-#PAPERLESS_DEBUG=false
-
 # Required services
 
 #PAPERLESS_REDIS=redis://localhost:6379
@@ -59,10 +55,10 @@
 #PAPERLESS_TASK_WORKERS=1
 #PAPERLESS_THREADS_PER_WORKER=1
 #PAPERLESS_TIME_ZONE=UTC
-#PAPERLESS_CONSUMER_POLLING=10
+#PAPERLESS_CONSUMER_POLLING_INTERVAL=10
 #PAPERLESS_CONSUMER_DELETE_DUPLICATES=false
 #PAPERLESS_CONSUMER_RECURSIVE=false
-#PAPERLESS_CONSUMER_IGNORE_PATTERNS=[".DS_STORE/*", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini"]
+#PAPERLESS_CONSUMER_IGNORE_PATTERNS=[]  # Defaults are built in; add filename regexes, e.g. ["^\\.DS_Store$", "^desktop\\.ini$"]
 #PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=false
 #PAPERLESS_CONSUMER_ENABLE_BARCODES=false
 #PAPERLESS_CONSUMER_BARCODE_STRING=PATCHT
@@ -70,6 +66,7 @@
 #PAPERLESS_CONSUMER_BARCODE_DPI=300
 #PAPERLESS_CONSUMER_ENABLE_TAG_BARCODE=false
 #PAPERLESS_CONSUMER_TAG_BARCODE_MAPPING={"TAG:(.*)": "\\g<1>"}
+#PAPERLESS_CONSUMER_TAG_BARCODE_SPLIT=false
 #PAPERLESS_CONSUMER_ENABLE_COLLATE_DOUBLE_SIDED=false
 #PAPERLESS_CONSUMER_COLLATE_DOUBLE_SIDED_SUBDIR_NAME=double-sided
 #PAPERLESS_CONSUMER_COLLATE_DOUBLE_SIDED_TIFF_SUPPORT=false

pyproject.toml

@@ -1,84 +1,99 @@
 [project]
 name = "paperless-ngx"
-version = "2.15.0"
+version = "2.20.10"
-description = "A community-supported supercharged version of paperless: scan, index and archive all your physical documents"
+description = "A community-supported supercharged document management system: scan, index and archive all your physical documents"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 classifiers = [
   "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
 ]
 # TODO: Move certain things to groups and then utilize that further
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
-  "bleach~=6.2.0",
+  "azure-ai-documentintelligence>=1.0.2",
-  "celery[redis]~=5.4.0",
+  "babel>=2.17",
+  "bleach~=6.3.0",
+  "celery[redis]~=5.6.2",
   "channels~=4.2",
   "channels-redis~=4.2",
   "concurrent-log-handler~=0.9.25",
   "dateparser~=1.2",
   # WARNING: django does not use semver.
   #          Only patch versions are guaranteed to not introduce breaking changes.
-  "django~=5.1.7",
+  "django~=5.2.10",
-  "django-allauth[socialaccount,mfa]~=65.4.0",
+  "django-allauth[mfa,socialaccount]~=65.14.0",
-  "django-auditlog~=3.0.0",
+  "django-auditlog~=3.4.1",
-  "django-celery-results~=2.5.1",
+  "django-cachalot~=2.9.0",
+  "django-celery-results~=2.6.0",
   "django-compression-middleware~=0.5.0",
-  "django-cors-headers~=4.7.0",
+  "django-cors-headers~=4.9.0",
-  "django-extensions~=3.2.3",
+  "django-extensions~=4.1",
   "django-filter~=25.1",
-  "django-guardian~=2.4.0",
+  "django-guardian~=3.3.0",
-  "django-multiselectfield~=0.1.13",
+  "django-multiselectfield~=1.0.1",
+  "django-rich~=2.2.0",
   "django-soft-delete~=1.0.18",
-  "djangorestframework~=3.15",
+  "django-treenode>=0.23.2",
-  "djangorestframework-guardian~=0.3.0",
+  "djangorestframework~=3.16",
+  "djangorestframework-guardian~=0.4.0",
   "drf-spectacular~=0.28",
-  "drf-spectacular-sidecar~=2025.3.1",
+  "drf-spectacular-sidecar~=2026.1.1",
   "drf-writable-nested~=0.7.1",
-  "filelock~=3.17.0",
+  "faiss-cpu>=1.10",
+  "filelock~=3.24.3",
   "flower~=2.0.1",
-  "gotenberg-client~=0.9.0",
+  "gotenberg-client~=0.13.1",
   "httpx-oauth~=0.16",
-  "imap-tools~=1.10.0",
+  "ijson>=3.2",
-  "inotifyrecursive~=0.3",
+  "imap-tools~=1.11.0",
   "jinja2~=3.1.5",
   "langdetect~=1.0.9",
+  "llama-index-core>=0.14.12",
+  "llama-index-embeddings-huggingface>=0.6.1",
+  "llama-index-embeddings-openai>=0.5.1",
+  "llama-index-llms-ollama>=0.9.1",
+  "llama-index-llms-openai>=0.6.13",
+  "llama-index-vector-stores-faiss>=0.5.2",
   "nltk~=3.9.1",
-  "ocrmypdf~=16.10.0",
+  "ocrmypdf~=16.13.0",
-  "pathvalidate~=3.2.3",
+  "openai>=1.76",
+  "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",
   "python-dateutil~=2.9.0",
-  "python-dotenv~=1.0.1",
+  "python-dotenv~=1.2.1",
   "python-gnupg~=0.5.4",
   "python-ipware~=3.0.0",
   "python-magic~=0.4.27",
-  "pyzbar~=0.1.9",
+  "rapidfuzz~=3.14.0",
-  "rapidfuzz~=3.12.1",
   "redis[hiredis]~=5.2.1",
-  "scikit-learn~=1.6.1",
+  "regex>=2025.9.18",
+  "scikit-learn~=1.7.0",
+  "sentence-transformers>=4.1",
   "setproctitle~=1.3.4",
-  "tika-client~=0.9.0",
+  "tika-client~=0.10.0",
-  "tqdm~=4.67.1",
+  "torch~=2.10.0",
-  "watchdog~=6.0",
+  "watchfiles>=1.1.1",
-  "whitenoise~=6.9",
+  "whitenoise~=6.11",
-  "whoosh~=2.7",
+  "whoosh-reloaded>=2.7.5",
-  "zxing-cpp~=2.3.0",
+  "zxing-cpp~=3.0.0",
 ]
 
 optional-dependencies.mariadb = [
   "mysqlclient~=2.2.7",
 ]
 optional-dependencies.postgres = [
-  "psycopg[c]==3.2.5",
+  "psycopg[c,pool]==3.3",
   # Direct dependency for proper resolution of the pre-built wheels
-  "psycopg-c==3.2.5",
+  "psycopg-c==3.3",
+  "psycopg-pool==3.3",
 ]
 optional-dependencies.webserver = [
-  "granian[uvloop]~=2.2.0",
+  "granian[uvloop]~=2.7.0",
 ]
 
 [dependency-groups]
@@ -90,29 +105,29 @@ dev = [
 ]
 
 docs = [
-  "mkdocs-glightbox~=0.4.0",
+  "zensical>=0.0.21",
-  "mkdocs-material~=9.6.4",
 ]
 
 testing = [
   "daphne",
   "factory-boy~=3.3.1",
+  "faker~=40.5.1",
   "imagehash",
-  "pytest~=8.3.3",
+  "pytest~=9.0.0",
-  "pytest-cov~=6.0.0",
+  "pytest-cov~=7.0.0",
-  "pytest-django~=4.10.0",
+  "pytest-django~=4.12.0",
-  "pytest-env",
+  "pytest-env~=1.5.0",
   "pytest-httpx",
-  "pytest-mock",
+  "pytest-mock~=3.15.1",
-  "pytest-rerunfailures",
+  #"pytest-randomly~=4.0.1",
+  "pytest-rerunfailures~=16.1",
   "pytest-sugar",
-  "pytest-xdist",
+  "pytest-xdist~=3.8.0",
 ]
 
 lint = [
-  "pre-commit~=4.1.0",
+  "prek~=0.3.0",
-  "pre-commit-uv~=4.1.3",
+  "ruff~=0.15.0",
-  "ruff~=0.9.9",
 ]
 
 typing = [
@@ -120,20 +135,49 @@ typing = [
   "django-filter-stubs",
   "django-stubs[compatible-mypy]",
   "djangorestframework-stubs[compatible-mypy]",
+  "lxml-stubs",
+  "microsoft-python-type-stubs @ git+https://github.com/microsoft/python-type-stubs.git",
   "mypy",
+  "mypy-baseline",
+  "pyrefly",
   "types-bleach",
+  "types-channels",
   "types-colorama",
   "types-dateparser",
   "types-markdown",
   "types-pygments",
   "types-python-dateutil",
+  "types-pytz",
   "types-redis",
   "types-setuptools",
-  "types-tqdm",
+]
+
+[tool.uv]
+required-version = ">=0.9.0"
+package = false
+environments = [
+  "sys_platform == 'darwin'",
+  "sys_platform == 'linux'",
+]
+
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
+[tool.uv.sources]
+# Markers are chosen to select these almost exclusively when building the Docker image
+psycopg-c = [
+  { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-trixie-3.3.0/psycopg_c-3.3.0-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },
+  { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-trixie-3.3.0/psycopg_c-3.3.0-cp312-cp312-linux_aarch64.whl", marker = "sys_platform == 'linux' and platform_machine == 'aarch64' and python_version == '3.12'" },
+]
+
+torch = [
+  { index = "pytorch-cpu" },
 ]
 
 [tool.ruff]
-target-version = "py310"
+target-version = "py311"
 line-length = 88
 src = [
   "src",
@@ -172,6 +216,7 @@ lint.extend-select = [
 ]
 lint.ignore = [
   "DJ001",
+  "PLC0415",
   "RUF012",
   "SIM105",
 ]
@@ -200,87 +245,39 @@ lint.per-file-ignores."docker/wait-for-redis.py" = [
   "INP001",
   "T201",
 ]
-lint.per-file-ignores."src/documents/file_handling.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/management/commands/document_consumer.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/management/commands/document_exporter.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/migrations/1012_fix_archive_files.py" = [
-  "PTH",
-] # TODO Enable & remove
 lint.per-file-ignores."src/documents/models.py" = [
   "SIM115",
 ]
-lint.per-file-ignores."src/documents/parsers.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/signals/handlers.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_consumer.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_file_handling.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_management.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_management_consumer.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_management_exporter.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_migration_archive_files.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_migration_document_pages_count.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_migration_mime_type.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/tests/test_sanity_check.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/documents/views.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/paperless/checks.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/paperless/settings.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/paperless/views.py" = [
-  "PTH",
-] # TODO Enable & remove
-lint.per-file-ignores."src/paperless_mail/mail.py" = [
-  "PTH",
-] # TODO Enable & remove
 lint.per-file-ignores."src/paperless_tesseract/tests/test_parser.py" = [
-  "PTH",
   "RUF001",
-] # TODO PTH Enable & remove
+]
 lint.isort.force-single-line = true
 
-[tool.pytest.ini_options]
+[tool.codespell]
-minversion = "8.0"
+write-changes = true
-pythonpath = [
+ignore-words-list = "criterias,afterall,valeu,ureue,equest,ure,assertIn,Oktober,commitish"
-  "src",
+skip = "src-ui/src/locale/*,src-ui/pnpm-lock.yaml,src-ui/e2e/*,src/paperless_mail/tests/samples/*,src/documents/tests/samples/*,*.po,*.json"
-]
+
+[tool.pytest]
+minversion = "9.0"
+pythonpath = [ "src" ]
+
+strict_config = true
+strict_markers = true
+strict_parametrization_ids = true
+strict_xfail = true
+
 testpaths = [
   "src/documents/tests/",
   "src/paperless/tests/",
   "src/paperless_mail/tests/",
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
+  "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
+  "src/paperless_ai/tests",
 ]
+
 addopts = [
   "--pythonwarnings=all",
   "--cov",
@@ -288,18 +285,39 @@ addopts = [
   "--cov-report=xml",
   "--numprocesses=auto",
   "--maxprocesses=16",
-  "--quiet",
+  "--dist=loadscope",
   "--durations=50",
+  "--durations-min=0.5",
   "--junitxml=junit.xml",
-  "-o junit_family=legacy",
+  "-o",
+  "junit_family=legacy",
 ]
+
 norecursedirs = [ "src/locale/", ".venv/", "src-ui/" ]
 
 DJANGO_SETTINGS_MODULE = "paperless.settings"
 
+markers = [
+  "live: Integration tests requiring external services (Gotenberg, Tika, nginx, etc)",
+  "nginx: Tests that make HTTP requests to the local nginx service",
+  "gotenberg: Tests requiring Gotenberg service",
+  "tika: Tests requiring Tika service",
+  "greenmail: Tests requiring Greenmail service",
+  "date_parsing: Tests which cover date parsing from content or filename",
+  "management: Tests which cover management commands/functionality",
+]
+
 [tool.pytest_env]
 PAPERLESS_DISABLE_DBHANDLER = "true"
 PAPERLESS_CACHE_BACKEND = "django.core.cache.backends.locmem.LocMemCache"
+PAPERLESS_CHANNELS_BACKEND = "channels.layers.InMemoryChannelLayer"
+
+[tool.coverage.report]
+exclude_also = [
+  "if settings.AUDIT_LOG_ENABLED:",
+  "if AUDIT_LOG_ENABLED:",
+  "if TYPE_CHECKING:",
+]
 
 [tool.coverage.run]
 source = [
@@ -312,18 +330,11 @@ omit = [
   "paperless/auth.py",
 ]
 
-[tool.coverage.report]
-exclude_also = [
-  "if settings.AUDIT_LOG_ENABLED:",
-  "if AUDIT_LOG_ENABLED:",
-  "if TYPE_CHECKING:",
-]
-
 [tool.mypy]
+mypy_path = "src"
 plugins = [
   "mypy_django_plugin.main",
   "mypy_drf_plugin.main",
-  "numpy.typing.mypy_plugin",
 ]
 check_untyped_defs = true
 disallow_any_generics = true
@@ -332,24 +343,15 @@ disallow_untyped_defs = true
 warn_redundant_casts = true
 warn_unused_ignores = true
 
-[tool.uv]
+[tool.pyrefly]
-required-version = ">=0.5.14"
+search-path = [ "src" ]
-package = false
+baseline = ".pyrefly-baseline.json"
-environments = [
+python-platform = "linux"
-  "sys_platform == 'darwin'",
-  "sys_platform == 'linux'",
-]
-
-[tool.uv.sources]
-# Markers are chosen to select these almost exclusively when building the Docker image
-psycopg-c = [
-  { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.5/psycopg_c-3.2.5-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },
-  { url = "https://github.com/paperless-ngx/builder/releases/download/psycopg-3.2.5/psycopg_c-3.2.5-cp312-cp312-linux_aarch64.whl", marker = "sys_platform == 'linux' and platform_machine == 'aarch64' and python_version == '3.12'" },
-]
-zxing-cpp = [
-  { url = "https://github.com/paperless-ngx/builder/releases/download/zxing-2.3.0/zxing_cpp-2.3.0-cp312-cp312-linux_x86_64.whl", marker = "sys_platform == 'linux' and platform_machine == 'x86_64' and python_version == '3.12'" },
-  { url = "https://github.com/paperless-ngx/builder/releases/download/zxing-2.3.0/zxing_cpp-2.3.0-cp312-cp312-linux_aarch64.whl", marker = "sys_platform == 'linux' and platform_machine == 'aarch64' and python_version == '3.12'" },
-]
 
 [tool.django-stubs]
 django_settings_module = "paperless.settings"
+
+[tool.mypy-baseline]
+baseline_path = ".mypy-baseline.txt"
+sort_baseline = true
+ignore_categories = [ "note" ]

scripts/post-consumption-example.sh

@@ -6,6 +6,7 @@ A document with an id of ${DOCUMENT_ID} was just consumed.  I know the
 following additional information about it:
 
 * Generated File Name: ${DOCUMENT_FILE_NAME}
+* Document type: ${DOCUMENT_TYPE}
 * Archive Path: ${DOCUMENT_ARCHIVE_PATH}
 * Source Path: ${DOCUMENT_SOURCE_PATH}
 * Created: ${DOCUMENT_CREATED}
@@ -18,6 +19,4 @@ following additional information about it:
 * Correspondent: ${DOCUMENT_CORRESPONDENT}
 * Tags: ${DOCUMENT_TAGS}
 
-It was consumed with the passphrase ${PASSPHRASE}
-
 "

src-ui/.eslintrc.json

@@ -1,51 +0,0 @@
-{
-  "root": true,
-  "ignorePatterns": [
-    "projects/**/*",
-    "/src/app/components/common/pdf-viewer/**"
-  ],
-  "overrides": [
-    {
-      "files": [
-        "*.ts"
-      ],
-      "parserOptions": {
-        "project": [
-          "tsconfig.json"
-        ],
-        "createDefaultProgram": true
-      },
-      "extends": [
-        "plugin:@angular-eslint/recommended",
-        "plugin:@angular-eslint/template/process-inline-templates"
-      ],
-      "rules": {
-        "@angular-eslint/directive-selector": [
-          "error",
-          {
-            "type": "attribute",
-            "prefix": "pngx",
-            "style": "camelCase"
-          }
-        ],
-        "@angular-eslint/component-selector": [
-          "error",
-          {
-            "type": "element",
-            "prefix": "pngx",
-            "style": "kebab-case"
-          }
-        ]
-      }
-    },
-    {
-      "files": [
-        "*.html"
-      ],
-      "extends": [
-        "plugin:@angular-eslint/template/recommended"
-      ],
-      "rules": {}
-    }
-  ]
-}

src-ui/__mocks__/pdfjs-dist.ts

@@ -0,0 +1,13 @@
+export const getDocument = jest.fn(() => ({
+  promise: Promise.resolve({ numPages: 3 }),
+}))
+
+export const GlobalWorkerOptions = { workerSrc: '' }
+export const VerbosityLevel = { ERRORS: 0 }
+
+globalThis.pdfjsLib = {
+  getDocument,
+  GlobalWorkerOptions,
+  VerbosityLevel,
+  AbortException: class AbortException extends Error {},
+}

src-ui/angular.json

@@ -27,9 +27,11 @@
           "el-GR": "src/locale/messages.el_GR.xlf",
           "en-GB": "src/locale/messages.en_GB.xlf",
           "es-ES": "src/locale/messages.es_ES.xlf",
+          "fa-IR": "src/locale/messages.fa_IR.xlf",
           "fi-FI": "src/locale/messages.fi_FI.xlf",
           "fr-FR": "src/locale/messages.fr_FR.xlf",
           "hu-HU": "src/locale/messages.hu_HU.xlf",
+          "id-ID": "src/locale/messages.id_ID.xlf",
           "it-IT": "src/locale/messages.it_IT.xlf",
           "ja-JP": "src/locale/messages.ja_JP.xlf",
           "lb-LU": "src/locale/messages.lb_LU.xlf",
@@ -47,6 +49,7 @@
           "sv-SE": "src/locale/messages.sv_SE.xlf",
           "tr-TR": "src/locale/messages.tr_TR.xlf",
           "uk-UA": "src/locale/messages.uk_UA.xlf",
+          "vi-VN": "src/locale/messages.vi_VN.xlf",
           "zh-CN": "src/locale/messages.zh_CN.xlf",
           "zh-TW": "src/locale/messages.zh_TW.xlf"
         }
@@ -59,10 +62,12 @@
                 "path": "./extra-webpack.config.ts"
             },
             "outputPath": "dist/paperless-ui",
+            "main": "src/main.ts",
             "outputHashing": "none",
             "index": "src/index.html",
-            "main": "src/main.ts",
+            "polyfills": [
-            "polyfills": "src/polyfills.ts",
+              "src/polyfills.ts"
+            ],
             "tsConfig": "tsconfig.app.json",
             "localize": true,
             "assets": [
@@ -81,16 +86,18 @@
             ],
             "scripts": [],
             "allowedCommonJsDependencies": [
-              "ng2-pdf-viewer",
               "file-saver",
               "utif"
             ],
-            "vendorChunk": true,
             "extractLicenses": false,
-            "buildOptimizer": false,
             "sourceMap": true,
             "optimization": false,
-            "namedChunks": true
+            "namedChunks": true,
+            "stylePreprocessorOptions": {
+              "includePaths": [
+                "."
+              ]
+            }
           },
           "configurations": {
             "production": {
@@ -106,8 +113,6 @@
               "sourceMap": false,
               "namedChunks": false,
               "extractLicenses": true,
-              "vendorChunk": false,
-              "buildOptimizer": true,
               "budgets": [
                 {
                   "type": "initial",
@@ -150,16 +155,7 @@
           "builder": "@angular-builders/jest:run",
           "options": {
             "tsConfig": "tsconfig.spec.json",
-            "assets": [
+            "zoneless": false
-              "src/favicon.ico",
-              "src/apple-touch-icon.png",
-              "src/assets",
-              "src/manifest.webmanifest"
-            ],
-            "styles": [
-              "src/styles.scss"
-            ],
-            "scripts": []
           }
         },
         "lint": {
@@ -187,6 +183,30 @@
     },
     "@angular-eslint/schematics:library": {
       "setParserOptionsProject": true
+    },
+    "@schematics/angular:component": {
+      "type": "component"
+    },
+    "@schematics/angular:directive": {
+      "type": "directive"
+    },
+    "@schematics/angular:service": {
+      "type": "service"
+    },
+    "@schematics/angular:guard": {
+      "typeSeparator": "."
+    },
+    "@schematics/angular:interceptor": {
+      "typeSeparator": "."
+    },
+    "@schematics/angular:module": {
+      "typeSeparator": "."
+    },
+    "@schematics/angular:pipe": {
+      "typeSeparator": "."
+    },
+    "@schematics/angular:resolver": {
+      "typeSeparator": "."
     }
   }
 }

src-ui/e2e/dashboard/dashboard.spec.ts

@@ -52,11 +52,11 @@ test('dashboard saved view document links', async ({ page }) => {
 test('test slim sidebar', async ({ page }) => {
   await page.routeFromHAR(REQUESTS_HAR1, { notFound: 'fallback' })
   await page.goto('/dashboard')
-  await page.locator('#sidebarMenu').getByRole('button').click()
+  await page.locator('.sidebar-slim-toggler').click()
   await expect(
     page.getByRole('link', { name: 'Dashboard' }).getByText('Dashboard')
   ).toBeHidden()
-  await page.locator('#sidebarMenu').getByRole('button').click()
+  await page.locator('.sidebar-slim-toggler').click()
   await expect(
     page.getByRole('link', { name: 'Dashboard' }).getByText('Dashboard')
   ).toBeVisible()

src-ui/e2e/dashboard/requests/api-dashboard1.har

@@ -58,7 +58,7 @@
           "content": {
             "size": -1,
             "mimeType": "application/json",
-            "text": "{\"user\":{\"id\":2,\"username\":\"testuser\",\"is_superuser\":false,\"groups\":[]},\"settings\":{\"language\":\"\",\"bulk_edit\":{\"confirmation_dialogs\":true,\"apply_on_close\":false},\"documentListSize\":50,\"dark_mode\":{\"use_system\":false,\"enabled\":\"false\",\"thumb_inverted\":\"true\"},\"theme\":{\"color\":\"#9fbf2f\"},\"document_details\":{\"native_pdf_viewer\":false},\"date_display\":{\"date_locale\":\"\",\"date_format\":\"mediumDate\"},\"notifications\":{\"consumer_new_documents\":true,\"consumer_success\":true,\"consumer_failed\":true,\"consumer_suppress_on_dashboard\":true},\"comments_enabled\":true,\"slim_sidebar\":false,\"update_checking\":{\"enabled\":false,\"backend_setting\":\"default\"},\"saved_views\":{\"warn_on_unsaved_change\":true},\"notes_enabled\":true,\"tour_complete\":true},\"permissions\":[\"delete_schedule\",\"view_note\",\"view_taskattributes\",\"delete_ormq\",\"add_ormq\",\"change_tag\",\"change_chordcounter\",\"delete_savedviewfilterrule\",\"delete_comment\",\"add_session\",\"add_mailrule\",\"add_tokenproxy\",\"delete_taskresult\",\"view_failure\",\"add_tag\",\"view_savedviewfilterrule\",\"view_paperlesstask\",\"change_mailaccount\",\"change_frontendsettings\",\"delete_group\",\"add_userobjectpermission\",\"add_failure\",\"delete_mailrule\",\"view_userobjectpermission\",\"change_schedule\",\"delete_note\",\"view_ormq\",\"add_note\",\"add_chordcounter\",\"delete_token\",\"change_failure\",\"add_savedviewfilterrule\",\"delete_user\",\"view_correspondent\",\"view_schedule\",\"change_tokenproxy\",\"view_user\",\"delete_task\",\"delete_correspondent\",\"delete_chordcounter\",\"delete_document\",\"view_taskresult\",\"change_document\",\"add_frontendsettings\",\"view_mailrule\",\"change_ormq\",\"delete_taskattributes\",\"view_logentry\",\"view_mailaccount\",\"view_log\",\"delete_success\",\"view_frontendsettings\",\"view_documenttype\",\"change_taskresult\",\"view_permission\",\"add_groupobjectpermission\",\"change_user\",\"view_document\",\"change_userobjectpermission\",\"add_user\",\"add_correspondent\",\"add_token\",\"add_mailaccount\",\"change_group\",\"add_group\",\"delete_processedmail\",\"delete_contenttype\",\"add_savedview\",\"view_chordcounter\",\"delete_tokenproxy\",\"change_groupresult\",\"delete_session\",\"view_savedview\",\"view_processedmail\",\"add_comment\",\"view_storagepath\",\"delete_documenttype\",\"add_processedmail\",\"view_group\",\"change_processedmail\",\"view_session\",\"delete_storagepath\",\"delete_paperlesstask\",\"add_groupresult\",\"delete_savedview\",\"delete_userobjectpermission\",\"view_tokenproxy\",\"add_task\",\"view_tag\",\"add_taskresult\",\"change_documenttype\",\"change_mailrule\",\"add_document\",\"change_comment\",\"view_task\",\"view_groupresult\",\"change_contenttype\",\"view_groupobjectpermission\",\"change_task\",\"add_log\",\"add_success\",\"change_savedview\",\"delete_frontendsettings\",\"view_success\",\"add_permission\",\"change_correspondent\",\"add_paperlesstask\",\"change_paperlesstask\",\"add_contenttype\",\"view_comment\",\"change_logentry\",\"delete_logentry\",\"delete_mailaccount\",\"change_session\",\"delete_groupresult\",\"add_logentry\",\"change_savedviewfilterrule\",\"change_success\",\"delete_tag\",\"add_taskattributes\",\"change_groupobjectpermission\",\"delete_failure\",\"add_uisettings\",\"view_token\",\"add_schedule\",\"delete_log\",\"delete_uisettings\",\"change_permission\",\"delete_groupobjectpermission\",\"change_token\",\"view_uisettings\",\"change_uisettings\",\"delete_permission\",\"add_storagepath\",\"change_storagepath\",\"view_contenttype\",\"change_note\",\"change_log\",\"change_taskattributes\",\"add_documenttype\"]}"
+            "text": "{\"user\":{\"id\":2,\"username\":\"testuser\",\"is_superuser\":false,\"groups\":[]},\"settings\":{\"language\":\"\",\"bulk_edit\":{\"confirmation_dialogs\":true,\"apply_on_close\":false},\"documentListSize\":50,\"dark_mode\":{\"use_system\":false,\"enabled\":\"false\",\"thumb_inverted\":\"true\"},\"theme\":{\"color\":\"#9fbf2f\"},\"document_details\":{\"native_pdf_viewer\":false},\"date_display\":{\"date_locale\":\"\",\"date_format\":\"mediumDate\"},\"notifications\":{\"consumer_new_documents\":true,\"consumer_success\":true,\"consumer_failed\":true,\"consumer_suppress_on_dashboard\":true},\"comments_enabled\":true,\"slim_sidebar\":false,\"update_checking\":{\"enabled\":false,\"backend_setting\":\"default\"},\"saved_views\":{\"warn_on_unsaved_change\":true,\"dashboard_views_visible_ids\":[7,4],\"sidebar_views_visible_ids\":[7,4,11]},\"notes_enabled\":true,\"tour_complete\":true},\"permissions\":[\"delete_schedule\",\"view_note\",\"view_taskattributes\",\"delete_ormq\",\"add_ormq\",\"change_tag\",\"change_chordcounter\",\"delete_savedviewfilterrule\",\"delete_comment\",\"add_session\",\"add_mailrule\",\"add_tokenproxy\",\"delete_taskresult\",\"view_failure\",\"add_tag\",\"view_savedviewfilterrule\",\"view_paperlesstask\",\"change_mailaccount\",\"change_frontendsettings\",\"delete_group\",\"add_userobjectpermission\",\"add_failure\",\"delete_mailrule\",\"view_userobjectpermission\",\"change_schedule\",\"delete_note\",\"view_ormq\",\"add_note\",\"add_chordcounter\",\"delete_token\",\"change_failure\",\"add_savedviewfilterrule\",\"delete_user\",\"view_correspondent\",\"view_schedule\",\"change_tokenproxy\",\"view_user\",\"delete_task\",\"delete_correspondent\",\"delete_chordcounter\",\"delete_document\",\"view_taskresult\",\"change_document\",\"add_frontendsettings\",\"view_mailrule\",\"change_ormq\",\"delete_taskattributes\",\"view_logentry\",\"view_mailaccount\",\"view_log\",\"delete_success\",\"view_frontendsettings\",\"view_documenttype\",\"change_taskresult\",\"view_permission\",\"add_groupobjectpermission\",\"change_user\",\"view_document\",\"change_userobjectpermission\",\"add_user\",\"add_correspondent\",\"add_token\",\"add_mailaccount\",\"change_group\",\"add_group\",\"delete_processedmail\",\"delete_contenttype\",\"add_savedview\",\"view_chordcounter\",\"delete_tokenproxy\",\"change_groupresult\",\"delete_session\",\"view_savedview\",\"view_processedmail\",\"add_comment\",\"view_storagepath\",\"delete_documenttype\",\"add_processedmail\",\"view_group\",\"change_processedmail\",\"view_session\",\"delete_storagepath\",\"delete_paperlesstask\",\"add_groupresult\",\"delete_savedview\",\"delete_userobjectpermission\",\"view_tokenproxy\",\"add_task\",\"view_tag\",\"add_taskresult\",\"change_documenttype\",\"change_mailrule\",\"add_document\",\"change_comment\",\"view_task\",\"view_groupresult\",\"change_contenttype\",\"view_groupobjectpermission\",\"change_task\",\"add_log\",\"add_success\",\"change_savedview\",\"delete_frontendsettings\",\"view_success\",\"add_permission\",\"change_correspondent\",\"add_paperlesstask\",\"change_paperlesstask\",\"add_contenttype\",\"view_comment\",\"change_logentry\",\"delete_logentry\",\"delete_mailaccount\",\"change_session\",\"delete_groupresult\",\"add_logentry\",\"change_savedviewfilterrule\",\"change_success\",\"delete_tag\",\"add_taskattributes\",\"change_groupobjectpermission\",\"delete_failure\",\"add_uisettings\",\"view_token\",\"add_schedule\",\"delete_log\",\"delete_uisettings\",\"change_permission\",\"delete_groupobjectpermission\",\"change_token\",\"view_uisettings\",\"change_uisettings\",\"delete_permission\",\"add_storagepath\",\"change_storagepath\",\"view_contenttype\",\"change_note\",\"change_log\",\"change_taskattributes\",\"add_documenttype\"]}"
           },
           "headersSize": -1,
           "bodySize": -1,