Merge branch 'dev' into feature-pw-removal-workflow-action

Added a test for the remove_password function to ensure it deletes the original document when specified.

.codecov.yml

@@ -1,7 +1,6 @@
-# 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
@@ -10,70 +9,35 @@ component_management:
     - component_id: frontend
       paths:
         - src-ui/**
-# https://docs.codecov.com/docs/flags#step-2-flag-management-in-yaml
-# https://docs.codecov.com/docs/carryforward-flags
 flags:
-  # Backend Python versions
-  backend-python-3.10:
+  backend:
     paths:
       - src/**
     carryforward: true
-  backend-python-3.11:
-    paths:
-      - src/**
-    carryforward: true
-  backend-python-3.12:
-    paths:
-      - src/**
-    carryforward: true
-  # Frontend (shards merge into single flag)
-  frontend-node-24.x:
+  frontend:
     paths:
       - src-ui/**
     carryforward: true
+# https://docs.codecov.com/docs/pull-request-comments
 comment:
   layout: "header, diff, components, flags, files"
+  # 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:
-      backend:
-        flags:
-          - backend-python-3.10
-          - backend-python-3.11
-          - backend-python-3.12
-        paths:
-          - src/**
+      default:
         # 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:
-      backend:
-        flags:
-          - backend-python-3.10
-          - backend-python-3.11
-          - backend-python-3.12
-        paths:
-          - src/**
-        target: 100%
-        threshold: 25%
-      frontend:
-        flags:
-          - frontend-node-24.x
-        paths:
-          - src-ui/**
+      default:
+        # For the changed lines only, target 100% covered, but
+        # allow as low as 75%
         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

.github/release-drafter.yml

@@ -44,7 +44,6 @@ 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

@@ -88,13 +88,13 @@ jobs:
         if: always()
         uses: codecov/codecov-action@v5
         with:
-          flags: backend-python-${{ matrix.python-version }}
+          flags: backend,backend-python-${{ matrix.python-version }}
           files: junit.xml
           report_type: test_results
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         with:
-          flags: backend-python-${{ matrix.python-version }}
+          flags: backend,backend-python-${{ matrix.python-version }}
           files: coverage.xml
           report_type: coverage
       - name: Stop containers

.github/workflows/ci-docker.yml

@@ -35,7 +35,7 @@ jobs:
       contents: read
       packages: write
     outputs:
-      should-push: ${{ steps.check-push.outputs.should-push }}
+      can-push: ${{ steps.check-push.outputs.can-push }}
       push-external: ${{ steps.check-push.outputs.push-external }}
       repository: ${{ steps.repo.outputs.name }}
       ref-name: ${{ steps.ref.outputs.name }}
@@ -59,28 +59,16 @@ jobs:
         env:
           REF_NAME: ${{ steps.ref.outputs.name }}
         run: |
-          # should-push: Should we push to GHCR?
-          # True for:
-          #   1. Pushes (tags/dev/beta) - filtered via the workflow triggers
-          #   2. Internal PRs where the branch name starts with 'feature-' - filtered here when a PR is synced
-
-          should_push="false"
-
-          if [[ "${{ github.event_name }}" == "push" ]]; 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}" >> $GITHUB_OUTPUT
+          # can-push: Can we push to GHCR?
+          # True for: pushes, or PRs from the same repo (not forks)
+          can_push=${{ github.event_name == 'push' || github.event.pull_request.head.repo.full_name == github.repository }}
+          echo "can-push=${can_push}"
+          echo "can-push=${can_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
+          if [[ "${can_push}" == "true" && "${{ github.repository_owner }}" == "paperless-ngx" ]]; then
             case "${REF_NAME}" in
               dev|beta)
                 push_external="true"
@@ -110,12 +98,6 @@ jobs:
           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
@@ -137,20 +119,20 @@ jobs:
           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=${{ steps.check-push.outputs.should-push }}
+          outputs: type=image,name=${{ env.REGISTRY }}/${{ steps.repo.outputs.name }},push-by-digest=true,name-canonical=true,push=${{ steps.check-push.outputs.can-push }}
           cache-from: |
             type=registry,ref=${{ env.REGISTRY }}/${{ steps.repo.outputs.name }}/cache/app:${{ steps.ref.outputs.cache-ref }}-${{ 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.cache-ref, matrix.arch) || '' }}
+          cache-to: ${{ steps.check-push.outputs.can-push == 'true' && format('type=registry,mode=max,ref={0}/{1}/cache/app:{2}-{3}', env.REGISTRY, steps.repo.outputs.name, steps.ref.outputs.cache-ref, matrix.arch) || '' }}
       - name: Export digest
-        if: steps.check-push.outputs.should-push == 'true'
+        if: steps.check-push.outputs.can-push == 'true'
         run: |
           mkdir -p /tmp/digests
           digest="${{ steps.build.outputs.digest }}"
           echo "digest=${digest}"
           touch "/tmp/digests/${digest#sha256:}"
       - name: Upload digest
-        if: steps.check-push.outputs.should-push == 'true'
+        if: steps.check-push.outputs.can-push == 'true'
         uses: actions/upload-artifact@v6.0.0
         with:
           name: digests-${{ matrix.arch }}
@@ -161,7 +143,7 @@ jobs:
     name: Merge and Push Manifest
     runs-on: ubuntu-24.04
     needs: build-arch
-    if: needs.build-arch.outputs.should-push == 'true'
+    if: needs.build-arch.outputs.can-push == 'true'
     permissions:
       contents: read
       packages: write

.github/workflows/ci-frontend.yml

@@ -109,13 +109,13 @@ jobs:
         if: always()
         uses: codecov/codecov-action@v5
         with:
-          flags: frontend-node-${{ matrix.node-version }}
+          flags: frontend,frontend-node-${{ matrix.node-version }}
           directory: src-ui/
           report_type: test_results
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         with:
-          flags: frontend-node-${{ matrix.node-version }}
+          flags: frontend,frontend-node-${{ matrix.node-version }}
           directory: src-ui/coverage/
   e2e-tests:
     name: "E2E Tests (${{ matrix.shard-index }}/${{ matrix.shard-count }})"

Dockerfile

@@ -30,7 +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:0.9.26-python3.12-trixie-slim AS s6-overlay-base
+FROM ghcr.io/astral-sh/uv:0.9.15-python3.12-trixie-slim AS s6-overlay-base
 
 WORKDIR /usr/src/s6
 
@@ -196,11 +196,7 @@ RUN set -eux \
     && 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 --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 \
+    && uv pip install --no-cache --system --no-python-downloads --python-preference system --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 \

docker/install_management_commands.sh

@@ -11,7 +11,6 @@ for command in decrypt_documents \
 	mail_fetcher \
 	document_create_classifier \
 	document_index \
-	document_llmindex \
 	document_renamer \
 	document_retagger \
 	document_thumbnails \

docker/rootfs/usr/local/bin/document_llmindex

@@ -1,14 +0,0 @@
-#!/command/with-contenv /usr/bin/bash
-# shellcheck shell=bash
-
-set -e
-
-cd "${PAPERLESS_SRC_DIR}"
-
-if [[ $(id -u) == 0 ]]; then
-	s6-setuidgid paperless python3 manage.py document_llmindex "$@"
-elif [[ $(id -un) == "paperless" ]]; then
-	python3 manage.py document_llmindex "$@"
-else
-	echo "Unknown user."
-fi

docs/advanced_usage.md

@@ -501,7 +501,7 @@ The `datetime` filter formats a datetime string or datetime object using Python'
 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}
+##### 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,
@@ -851,8 +851,8 @@ 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, make sure that
-`CONSUMER_POLLING_INTERVAL` is set to a value lower than it takes for the second scan to appear,
+the directory; and if you're using [polling](configuration.md#polling), make sure that
+`CONSUMER_POLLING` 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/changelog.md

@@ -1,60 +1,9 @@
 # Changelog
 
-## paperless-ngx 2.20.5
-
-### Bug Fixes
-
--   Fix: ensure horizontal scroll for long tag names in list, wrap tags without parent [@shamoon](https://github.com/shamoon) ([#11811](https://github.com/paperless-ngx/paperless-ngx/pull/11811))
--   Fix: use explicit order field for workflow actions [@shamoon](https://github.com/shamoon) [@stumpylog](https://github.com/stumpylog) ([#11781](https://github.com/paperless-ngx/paperless-ngx/pull/11781))
-
-### All App Changes
-
-<details>
-<summary>2 changes</summary>
-
--   Fix: ensure horizontal scroll for long tag names in list, wrap tags without parent [@shamoon](https://github.com/shamoon) ([#11811](https://github.com/paperless-ngx/paperless-ngx/pull/11811))
--   Fix: use explicit order field for workflow actions [@shamoon](https://github.com/shamoon) [@stumpylog](https://github.com/stumpylog) ([#11781](https://github.com/paperless-ngx/paperless-ngx/pull/11781))
-</details>
-
-## paperless-ngx 2.20.4
-
-### Security
-
--   Resolve [GHSA-28cf-xvcf-hw6m](https://github.com/paperless-ngx/paperless-ngx/security/advisories/GHSA-28cf-xvcf-hw6m)
-
-### Bug Fixes
-
--   Fix: propagate metadata override created value [@shamoon](https://github.com/shamoon) ([#11659](https://github.com/paperless-ngx/paperless-ngx/pull/11659))
--   Fix: support ordering by storage path name [@shamoon](https://github.com/shamoon) ([#11661](https://github.com/paperless-ngx/paperless-ngx/pull/11661))
--   Fix: validate cf integer values within PostgreSQL range [@shamoon](https://github.com/shamoon) ([#11666](https://github.com/paperless-ngx/paperless-ngx/pull/11666))
--   Fixhancement: add error handling and retry when opening index [@shamoon](https://github.com/shamoon) ([#11731](https://github.com/paperless-ngx/paperless-ngx/pull/11731))
--   Fix: fix recurring workflow to respect latest run time [@shamoon](https://github.com/shamoon) ([#11735](https://github.com/paperless-ngx/paperless-ngx/pull/11735))
-
-### All App Changes
-
-<details>
-<summary>5 changes</summary>
-
--   Fix: propagate metadata override created value [@shamoon](https://github.com/shamoon) ([#11659](https://github.com/paperless-ngx/paperless-ngx/pull/11659))
--   Fix: support ordering by storage path name [@shamoon](https://github.com/shamoon) ([#11661](https://github.com/paperless-ngx/paperless-ngx/pull/11661))
--   Fix: validate cf integer values within PostgreSQL range [@shamoon](https://github.com/shamoon) ([#11666](https://github.com/paperless-ngx/paperless-ngx/pull/11666))
--   Fixhancement: add error handling and retry when opening index [@shamoon](https://github.com/shamoon) ([#11731](https://github.com/paperless-ngx/paperless-ngx/pull/11731))
--   Fix: fix recurring workflow to respect latest run time [@shamoon](https://github.com/shamoon) ([#11735](https://github.com/paperless-ngx/paperless-ngx/pull/11735))
-</details>
-
 ## paperless-ngx 2.20.3
 
-### Security
-
--   Resolve [GHSA-7cq3-mhxq-w946](https://github.com/paperless-ngx/paperless-ngx/security/advisories/GHSA-7cq3-mhxq-w946)
-
 ## paperless-ngx 2.20.2
 
-### Security
-
--   Resolve [GHSA-6653-vcx4-69mc](https://github.com/paperless-ngx/paperless-ngx/security/advisories/GHSA-6653-vcx4-69mc)
--   Resolve [GHSA-24x5-wp64-9fcc](https://github.com/paperless-ngx/paperless-ngx/security/advisories/GHSA-24x5-wp64-9fcc)
-
 ### Features / Enhancements
 
 -   Tweakhancement: dim inactive users in users-groups list [@shamoon](https://github.com/shamoon) ([#11537](https://github.com/paperless-ngx/paperless-ngx/pull/11537))

docs/configuration.md

@@ -170,18 +170,11 @@ Available options are `postgresql` and `mariadb`.
 
     !!! note
 
-        A pool of 8-10 connections per worker is typically sufficient.
-        If you encounter error messages such as `couldn't get a connection`
-        or database connection timeouts, you probably need to increase the pool size.
-
-    !!! warning
-        Make sure your PostgreSQL `max_connections` setting is large enough to handle the connection pools:
-        `(NB_PAPERLESS_WORKERS + NB_CELERY_WORKERS) × POOL_SIZE + SAFETY_MARGIN`. For example, with
-        4 Paperless workers and 2 Celery workers, and a pool size of 8:``(4 + 2) × 8 + 10 = 58`,
-        so `max_connections = 60` (or even more) is appropriate.
-
-        This assumes only Paperless-ngx connects to your PostgreSQL instance. If you have other applications,
-        you should increase `max_connections` accordingly.
+        A small pool is typically sufficient — for example, a size of 4.
+        Make sure your PostgreSQL server's max_connections setting is large enough to handle:
+        ```(Paperless workers + Celery workers) × pool size + safety margin```
+        For example, with 4 Paperless workers and 2 Celery workers, and a pool size of 4:
+        (4 + 2) × 4 + 10 = 34 connections required.
 
 #### [`PAPERLESS_DB_READ_CACHE_ENABLED=<bool>`](#PAPERLESS_DB_READ_CACHE_ENABLED) {#PAPERLESS_DB_READ_CACHE_ENABLED}
 
@@ -1175,45 +1168,21 @@ don't exist yet.
 
 #### [`PAPERLESS_CONSUMER_IGNORE_PATTERNS=<json>`](#PAPERLESS_CONSUMER_IGNORE_PATTERNS) {#PAPERLESS_CONSUMER_IGNORE_PATTERNS}
 
-: Additional regex patterns for files to ignore in the consumption directory. Patterns are matched against filenames only (not full paths)
-using Python's `re.match()`, which anchors at the start of the filename.
+: By default, paperless ignores certain files and folders in the
+consumption directory, such as system files created by the Mac OS
+or hidden folders some tools use to store data.
 
-    See the [watchfiles documentation](https://watchfiles.helpmanual.io/api/filters/#watchfiles.BaseFilter.ignore_entity_patterns)
+    This can be adjusted by configuring a custom json array with
+    patterns to exclude.
 
-    This setting is for additional patterns beyond the built-in defaults. Common system files and directories are already ignored automatically.
-    The patterns will be compiled via Python's standard `re` module.
+    For example, `.DS_STORE/*` will ignore any files found in a folder
+    named `.DS_STORE`, including `.DS_STORE/bar.pdf` and `foo/.DS_STORE/bar.pdf`
 
-    Example custom patterns:
+    A pattern like `._*` will ignore anything starting with `._`, including:
+    `._foo.pdf` and `._bar/foo.pdf`
 
-    ```json
-    ["^temp_", "\\.bak$", "^~"]
-    ```
-
-    This would ignore:
-
-    - Files starting with `temp_` (e.g., `temp_scan.pdf`)
-    - Files ending with `.bak` (e.g., `document.pdf.bak`)
-    - Files starting with `~` (e.g., `~$document.docx`)
-
-    Defaults to `[]` (empty list, uses only built-in defaults).
-
-    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.
+    Defaults to
+    `[".DS_Store", ".DS_STORE", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini", "@eaDir/*", "Thumbs.db"]`.
 
 #### [`PAPERLESS_CONSUMER_BARCODE_SCANNER=<string>`](#PAPERLESS_CONSUMER_BARCODE_SCANNER) {#PAPERLESS_CONSUMER_BARCODE_SCANNER}
 
@@ -1312,24 +1281,48 @@ within your documents.
 
     Defaults to false.
 
-#### [`PAPERLESS_CONSUMER_POLLING_INTERVAL=<num>`](#PAPERLESS_CONSUMER_POLLING_INTERVAL) {#PAPERLESS_CONSUMER_POLLING_INTERVAL}
+### Polling {#polling}
 
-: Configures how the consumer detects new files in the consumption directory.
+#### [`PAPERLESS_CONSUMER_POLLING=<num>`](#PAPERLESS_CONSUMER_POLLING) {#PAPERLESS_CONSUMER_POLLING}
 
-    When set to `0` (default), paperless uses native filesystem notifications for efficient, immediate detection of new files.
+: If paperless won't find documents added to your consume folder, it
+might not be able to automatically detect filesystem changes. In
+that case, specify a polling interval in seconds 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`.
 
-    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.
+    Defaults to 0, which disables polling and uses filesystem
+    notifications.
 
-    Defaults to 0.
+#### [`PAPERLESS_CONSUMER_POLLING_RETRY_COUNT=<num>`](#PAPERLESS_CONSUMER_POLLING_RETRY_COUNT) {#PAPERLESS_CONSUMER_POLLING_RETRY_COUNT}
 
-#### [`PAPERLESS_CONSUMER_STABILITY_DELAY=<num>`](#PAPERLESS_CONSUMER_STABILITY_DELAY) {#PAPERLESS_CONSUMER_STABILITY_DELAY}
+: If consumer polling is enabled, sets the maximum number of times
+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.
 
-: Sets the time in seconds that a file must remain unchanged (same size and modification time) before paperless will begin consuming it.
+    Defaults to 5.
 
-    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
+#### [`PAPERLESS_CONSUMER_POLLING_DELAY=<num>`](#PAPERLESS_CONSUMER_POLLING_DELAY) {#PAPERLESS_CONSUMER_POLLING_DELAY}
 
-    Defaults to 5.0 seconds.
+: If consumer polling is enabled, sets the delay in seconds between
+each check (above) paperless will do while waiting for a file to
+remain unmodified.
+
+    Defaults to 5.
+
+### iNotify {#inotify}
+
+#### [`PAPERLESS_CONSUMER_INOTIFY_DELAY=<num>`](#PAPERLESS_CONSUMER_INOTIFY_DELAY) {#PAPERLESS_CONSUMER_INOTIFY_DELAY}
+
+: Sets the time in seconds the consumer will wait for additional
+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.
 
 ## Workflow webhooks
 
@@ -1831,67 +1824,3 @@ password. All of these options come from their similarly-named [Django settings]
 : 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/index.md

@@ -31,7 +31,6 @@ physical documents into a searchable online archive so you can keep, well, _less
     -   _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.
--   **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:

docs/migration.md

@@ -1,19 +0,0 @@
-# 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 |

docs/setup.md

@@ -124,7 +124,8 @@ account. The script essentially automatically performs the steps described in [D
         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_INTERVAL`](configuration.md#PAPERLESS_CONSUMER_POLLING_INTERVAL), which will disable inotify.
+        [`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`

docs/troubleshooting.md

@@ -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_INTERVAL`](configuration.md#PAPERLESS_CONSUMER_POLLING_INTERVAL).
+option [`PAPERLESS_CONSUMER_POLLING`](configuration.md#PAPERLESS_CONSUMER_POLLING).
 
-This will disable automatic listening for filesystem changes and
+This will disable listening to filesystem changes with inotify and
 paperless will manually check the consumption directory for changes
 instead.
 
@@ -234,9 +234,47 @@ 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, such as how a scanner may modify a file multiple times as it scans.
-Try adjusting the
-[file stability delay](configuration.md#PAPERLESS_CONSUMER_STABILITY_DELAY) to a larger value.
+placed into the consume folder. 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).
+
+## 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".
 

docs/usage.md

@@ -278,28 +278,6 @@ 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)
@@ -565,7 +543,7 @@ This allows for complex logic to be used to generate the title, including [logic
 and [filters](https://jinja.palletsprojects.com/en/3.1.x/templates/#id11).
 The template is provided as a string.
 
-Using Jinja2 Templates is also useful for [Date localization](advanced_usage.md#date-localization) in the title.
+Using Jinja2 Templates is also useful for [Date localization](advanced_usage.md#Date-Localization) in the title.
 
 The available inputs differ depending on the type of workflow trigger.
 This is because at the time of consumption (when the text is to be set), no automatic tags etc. have been
@@ -597,7 +575,6 @@ The following placeholders are only available for "added" or "updated" triggers
 -   `{{created_day}}`: created day
 -   `{{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_id}}`: Document ID
 
 ##### Examples
 

mkdocs.yml

@@ -69,9 +69,8 @@ nav:
   - development.md
   - 'FAQs': faq.md
   - troubleshooting.md
-  - 'Migration to v3': migration.md
   - changelog.md
-copyright: Copyright © 2016 - 2026 Daniel Quinn, Jonas Winkler, and the Paperless-ngx team
+copyright: Copyright © 2016 - 2023 Daniel Quinn, Jonas Winkler, and the Paperless-ngx team
 extra:
   social:
     - icon: fontawesome/brands/github

paperless.conf.example

@@ -55,10 +55,10 @@
 #PAPERLESS_TASK_WORKERS=1
 #PAPERLESS_THREADS_PER_WORKER=1
 #PAPERLESS_TIME_ZONE=UTC
-#PAPERLESS_CONSUMER_POLLING_INTERVAL=10
+#PAPERLESS_CONSUMER_POLLING=10
 #PAPERLESS_CONSUMER_DELETE_DUPLICATES=false
 #PAPERLESS_CONSUMER_RECURSIVE=false
-#PAPERLESS_CONSUMER_IGNORE_PATTERNS=[]  # Defaults are built in; add filename regexes, e.g. ["^\\.DS_Store$", "^desktop\\.ini$"]
+#PAPERLESS_CONSUMER_IGNORE_PATTERNS=[".DS_STORE/*", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini"]
 #PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=false
 #PAPERLESS_CONSUMER_ENABLE_BARCODES=false
 #PAPERLESS_CONSUMER_BARCODE_STRING=PATCHT

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "paperless-ngx"
-version = "2.20.5"
+version = "2.20.3"
 description = "A community-supported supercharged document management system: scan, index and archive all your physical documents"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -28,7 +28,7 @@ dependencies = [
   #          Only patch versions are guaranteed to not introduce breaking changes.
   "django~=5.2.5",
   "django-allauth[mfa,socialaccount]~=65.12.1",
-  "django-auditlog~=3.4.1",
+  "django-auditlog~=3.3.0",
   "django-cachalot~=2.8.0",
   "django-celery-results~=2.6.0",
   "django-compression-middleware~=0.5.0",
@@ -44,23 +44,16 @@ dependencies = [
   "drf-spectacular~=0.28",
   "drf-spectacular-sidecar~=2025.10.1",
   "drf-writable-nested~=0.7.1",
-  "faiss-cpu>=1.10",
   "filelock~=3.20.0",
   "flower~=2.0.1",
-  "gotenberg-client~=0.13.1",
+  "gotenberg-client~=0.12.0",
   "httpx-oauth~=0.16",
   "imap-tools~=1.11.0",
+  "inotifyrecursive~=0.3",
   "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~=16.13.0",
-  "openai>=1.76",
+  "ocrmypdf~=16.12.0",
   "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",
   "python-dateutil~=2.9.0",
@@ -73,12 +66,10 @@ dependencies = [
   "redis[hiredis]~=5.2.1",
   "regex>=2025.9.18",
   "scikit-learn~=1.7.0",
-  "sentence-transformers>=4.1",
   "setproctitle~=1.3.4",
   "tika-client~=0.10.0",
-  "torch~=2.9.1",
   "tqdm~=4.67.1",
-  "watchfiles>=1.1.1",
+  "watchdog~=6.0",
   "whitenoise~=6.9",
   "whoosh-reloaded>=2.7.5",
   "zxing-cpp~=2.3.0",
@@ -91,7 +82,7 @@ optional-dependencies.postgres = [
   "psycopg[c,pool]==3.2.12",
   # Direct dependency for proper resolution of the pre-built wheels
   "psycopg-c==3.2.12",
-  "psycopg-pool==3.3",
+  "psycopg-pool==3.2.7",
 ]
 optional-dependencies.webserver = [
   "granian[uvloop]~=2.5.1",
@@ -126,7 +117,7 @@ testing = [
 ]
 
 lint = [
-  "pre-commit~=4.5.1",
+  "pre-commit~=4.4.0",
   "pre-commit-uv~=4.2.0",
   "ruff~=0.14.0",
 ]
@@ -169,15 +160,6 @@ zxing-cpp = [
   { 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'" },
 ]
 
-torch = [
-  { index = "pytorch-cpu" },
-]
-
-[[tool.uv.index]]
-name = "pytorch-cpu"
-url = "https://download.pytorch.org/whl/cpu"
-explicit = true
-
 [tool.ruff]
 target-version = "py310"
 line-length = 88
@@ -273,7 +255,6 @@ testpaths = [
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
   "src/paperless_remote/tests/",
-  "src/paperless_ai/tests",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "paperless-ngx-ui",
-  "version": "2.20.5",
+  "version": "2.20.3",
   "scripts": {
     "preinstall": "npx only-allow pnpm",
     "ng": "ng",

src-ui/src/app/components/admin/config/config.component.html

@@ -35,12 +35,8 @@
                                                     @case (ConfigOptionType.String) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
                                                     @case (ConfigOptionType.JSON) { <pngx-input-text [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-text> }
                                                     @case (ConfigOptionType.File) { <pngx-input-file [formControlName]="option.key" (upload)="uploadFile($event, option.key)" [error]="errors[option.key]"></pngx-input-file> }
-                                                    @case (ConfigOptionType.Password) { <pngx-input-password [formControlName]="option.key" [error]="errors[option.key]"></pngx-input-password> }
                                                 }
                                             </div>
-                                            @if (option.note) {
-                                                <div class="form-text fst-italic">{{option.note}}</div>
-                                            }
                                         </div>
                                     </div>
                                 </div>

src-ui/src/app/components/admin/config/config.component.ts

@@ -29,7 +29,6 @@ import { SettingsService } from 'src/app/services/settings.service'
 import { ToastService } from 'src/app/services/toast.service'
 import { FileComponent } from '../../common/input/file/file.component'
 import { NumberComponent } from '../../common/input/number/number.component'
-import { PasswordComponent } from '../../common/input/password/password.component'
 import { SelectComponent } from '../../common/input/select/select.component'
 import { SwitchComponent } from '../../common/input/switch/switch.component'
 import { TextComponent } from '../../common/input/text/text.component'
@@ -47,7 +46,6 @@ import { LoadingComponentWithPermissions } from '../../loading-component/loading
     TextComponent,
     NumberComponent,
     FileComponent,
-    PasswordComponent,
     AsyncPipe,
     NgbNavModule,
     FormsModule,

src-ui/src/app/components/admin/settings/settings.component.spec.ts

@@ -91,9 +91,6 @@ const status: SystemStatus = {
     sanity_check_status: SystemStatusItemStatus.ERROR,
     sanity_check_last_run: new Date().toISOString(),
     sanity_check_error: 'Error running sanity check.',
-    llmindex_status: SystemStatusItemStatus.DISABLED,
-    llmindex_last_modified: new Date().toISOString(),
-    llmindex_error: null,
   },
 }
 

src-ui/src/app/components/app-frame/app-frame.component.html

@@ -30,9 +30,6 @@
     </div>
   </div>
   <ul ngbNav class="order-sm-3">
-    @if (aiEnabled) {
-      <pngx-chat></pngx-chat>
-    }
     <pngx-toasts-dropdown></pngx-toasts-dropdown>
     <li ngbDropdown class="nav-item dropdown">
       <button class="btn ps-1 border-0" id="userDropdown" ngbDropdownToggle>

src-ui/src/app/components/app-frame/app-frame.component.ts

@@ -44,7 +44,6 @@ import { SettingsService } from 'src/app/services/settings.service'
 import { TasksService } from 'src/app/services/tasks.service'
 import { ToastService } from 'src/app/services/toast.service'
 import { environment } from 'src/environments/environment'
-import { ChatComponent } from '../chat/chat/chat.component'
 import { ProfileEditDialogComponent } from '../common/profile-edit-dialog/profile-edit-dialog.component'
 import { DocumentDetailComponent } from '../document-detail/document-detail.component'
 import { ComponentWithPermissions } from '../with-permissions/with-permissions.component'
@@ -60,7 +59,6 @@ import { ToastsDropdownComponent } from './toasts-dropdown/toasts-dropdown.compo
     DocumentTitlePipe,
     IfPermissionsDirective,
     ToastsDropdownComponent,
-    ChatComponent,
     RouterModule,
     NgClass,
     NgbDropdownModule,
@@ -186,10 +184,6 @@ export class AppFrameComponent
       })
   }
 
-  get aiEnabled(): boolean {
-    return this.settingsService.get(SETTINGS_KEYS.AI_ENABLED)
-  }
-
   closeMenu() {
     this.isMenuCollapsed = true
   }

src-ui/src/app/components/app-frame/toasts-dropdown/toasts-dropdown.component.html

@@ -1,5 +1,5 @@
 
-<li ngbDropdown class="nav-item mx-1" (openChange)="onOpenChange($event)">
+<li ngbDropdown class="nav-item" (openChange)="onOpenChange($event)">
   @if (toasts.length) {
     <span class="badge rounded-pill z-3 pe-none bg-secondary me-2 position-absolute top-0 left-0">{{ toasts.length }}</span>
   }

src-ui/src/app/components/chat/chat/chat.component.html

@@ -1,35 +0,0 @@
-
-<li ngbDropdown class="nav-item me-n2" (openChange)="onOpenChange($event)">
-  <button class="btn border-0" id="chatDropdown" ngbDropdownToggle>
-    <i-bs width="1.3em" height="1.3em" name="chatSquareDots"></i-bs>
-  </button>
-  <div ngbDropdownMenu class="dropdown-menu-end shadow p-3" aria-labelledby="chatDropdown">
-    <div class="chat-container bg-light p-2">
-      <div class="chat-messages font-monospace small">
-        @for (message of messages; track message) {
-          <div class="message d-flex flex-row small" [class.justify-content-end]="message.role === 'user'">
-            <span class="p-2 m-2" [class.bg-dark]="message.role === 'user'">
-              {{ message.content }}
-              @if (message.isStreaming) { <span class="blinking-cursor">|</span> }
-            </span>
-          </div>
-        }
-        <div #scrollAnchor></div>
-      </div>
-
-      <form class="chat-input">
-        <div class="input-group">
-          <input
-            #chatInput
-            class="form-control form-control-sm" name="chatInput" type="text"
-            [placeholder]="placeholder"
-            [disabled]="loading"
-            [(ngModel)]="input"
-            (keydown)="searchInputKeyDown($event)"
-            />
-          <button class="btn btn-sm btn-secondary" type="button" (click)="sendMessage()" [disabled]="loading">Send</button>
-        </div>
-      </form>
-    </div>
-  </div>
-</li>

src-ui/src/app/components/chat/chat/chat.component.scss

@@ -1,37 +0,0 @@
-.dropdown-menu {
-  width: var(--pngx-toast-max-width);
-}
-
-.chat-messages {
-  max-height: 350px;
-  overflow-y: auto;
-}
-
-.dropdown-toggle::after {
-  display: none;
-}
-
-.dropdown-item {
-  white-space: initial;
-}
-
-@media screen and (max-width: 400px) {
-  :host ::ng-deep .dropdown-menu-end {
-    right: -3rem;
-  }
-}
-
-.blinking-cursor {
-  font-weight: bold;
-  font-size: 1.2em;
-  animation: blink 1s step-end infinite;
-}
-
-@keyframes blink {
-  from, to {
-    opacity: 0;
-  }
-  50% {
-    opacity: 1;
-  }
-}

src-ui/src/app/components/chat/chat/chat.component.spec.ts

@@ -1,132 +0,0 @@
-import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
-import { provideHttpClientTesting } from '@angular/common/http/testing'
-import { ElementRef } from '@angular/core'
-import { ComponentFixture, TestBed } from '@angular/core/testing'
-import { NavigationEnd, Router } from '@angular/router'
-import { allIcons, NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
-import { Subject } from 'rxjs'
-import { ChatService } from 'src/app/services/chat.service'
-import { ChatComponent } from './chat.component'
-
-describe('ChatComponent', () => {
-  let component: ChatComponent
-  let fixture: ComponentFixture<ChatComponent>
-  let chatService: ChatService
-  let router: Router
-  let routerEvents$: Subject<NavigationEnd>
-  let mockStream$: Subject<string>
-
-  beforeEach(async () => {
-    TestBed.configureTestingModule({
-      imports: [NgxBootstrapIconsModule.pick(allIcons), ChatComponent],
-      providers: [
-        provideHttpClient(withInterceptorsFromDi()),
-        provideHttpClientTesting(),
-      ],
-    }).compileComponents()
-
-    fixture = TestBed.createComponent(ChatComponent)
-    router = TestBed.inject(Router)
-    routerEvents$ = new Subject<any>()
-    jest
-      .spyOn(router, 'events', 'get')
-      .mockReturnValue(routerEvents$.asObservable())
-    chatService = TestBed.inject(ChatService)
-    mockStream$ = new Subject<string>()
-    jest
-      .spyOn(chatService, 'streamChat')
-      .mockReturnValue(mockStream$.asObservable())
-    component = fixture.componentInstance
-
-    jest.useFakeTimers()
-
-    fixture.detectChanges()
-
-    component.scrollAnchor.nativeElement.scrollIntoView = jest.fn()
-  })
-
-  it('should update documentId on initialization', () => {
-    jest.spyOn(router, 'url', 'get').mockReturnValue('/documents/123')
-    component.ngOnInit()
-    expect(component.documentId).toBe(123)
-  })
-
-  it('should update documentId on navigation', () => {
-    component.ngOnInit()
-    routerEvents$.next(new NavigationEnd(1, '/documents/456', '/documents/456'))
-    expect(component.documentId).toBe(456)
-  })
-
-  it('should return correct placeholder based on documentId', () => {
-    component.documentId = 123
-    expect(component.placeholder).toBe('Ask a question about this document...')
-    component.documentId = undefined
-    expect(component.placeholder).toBe('Ask a question about a document...')
-  })
-
-  it('should send a message and handle streaming response', () => {
-    component.input = 'Hello'
-    component.sendMessage()
-
-    expect(component.messages.length).toBe(2)
-    expect(component.messages[0].content).toBe('Hello')
-    expect(component.loading).toBe(true)
-
-    mockStream$.next('Hi')
-    expect(component.messages[1].content).toBe('H')
-    mockStream$.next('Hi there')
-    // advance time to process the typewriter effect
-    jest.advanceTimersByTime(1000)
-    expect(component.messages[1].content).toBe('Hi there')
-
-    mockStream$.complete()
-    expect(component.loading).toBe(false)
-    expect(component.messages[1].isStreaming).toBe(false)
-  })
-
-  it('should handle errors during streaming', () => {
-    component.input = 'Hello'
-    component.sendMessage()
-
-    mockStream$.error('Error')
-    expect(component.messages[1].content).toContain(
-      '⚠️ Error receiving response.'
-    )
-    expect(component.loading).toBe(false)
-  })
-
-  it('should enqueue typewriter chunks correctly', () => {
-    const message = { content: '', role: 'assistant', isStreaming: true }
-    component.enqueueTypewriter(null, message as any) // coverage for null
-    component.enqueueTypewriter('Hello', message as any)
-    expect(component['typewriterBuffer'].length).toBe(4)
-  })
-
-  it('should scroll to bottom after sending a message', () => {
-    const scrollSpy = jest.spyOn(
-      ChatComponent.prototype as any,
-      'scrollToBottom'
-    )
-    component.input = 'Test'
-    component.sendMessage()
-    expect(scrollSpy).toHaveBeenCalled()
-  })
-
-  it('should focus chat input when dropdown is opened', () => {
-    const focus = jest.fn()
-    component.chatInput = {
-      nativeElement: { focus: focus },
-    } as unknown as ElementRef<HTMLInputElement>
-
-    component.onOpenChange(true)
-    jest.advanceTimersByTime(15)
-    expect(focus).toHaveBeenCalled()
-  })
-
-  it('should send message on Enter key press', () => {
-    jest.spyOn(component, 'sendMessage')
-    const event = new KeyboardEvent('keydown', { key: 'Enter' })
-    component.searchInputKeyDown(event)
-    expect(component.sendMessage).toHaveBeenCalled()
-  })
-})

src-ui/src/app/components/chat/chat/chat.component.ts

@@ -1,140 +0,0 @@
-import { Component, ElementRef, inject, OnInit, ViewChild } from '@angular/core'
-import { FormsModule, ReactiveFormsModule } from '@angular/forms'
-import { NavigationEnd, Router } from '@angular/router'
-import { NgbDropdownModule } from '@ng-bootstrap/ng-bootstrap'
-import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
-import { filter, map } from 'rxjs'
-import { ChatMessage, ChatService } from 'src/app/services/chat.service'
-
-@Component({
-  selector: 'pngx-chat',
-  imports: [
-    FormsModule,
-    ReactiveFormsModule,
-    NgxBootstrapIconsModule,
-    NgbDropdownModule,
-  ],
-  templateUrl: './chat.component.html',
-  styleUrl: './chat.component.scss',
-})
-export class ChatComponent implements OnInit {
-  public messages: ChatMessage[] = []
-  public loading = false
-  public input: string = ''
-  public documentId!: number
-
-  private chatService: ChatService = inject(ChatService)
-  private router: Router = inject(Router)
-
-  @ViewChild('scrollAnchor') scrollAnchor!: ElementRef<HTMLDivElement>
-  @ViewChild('chatInput') chatInput!: ElementRef<HTMLInputElement>
-
-  private typewriterBuffer: string[] = []
-  private typewriterActive = false
-
-  public get placeholder(): string {
-    return this.documentId
-      ? $localize`Ask a question about this document...`
-      : $localize`Ask a question about a document...`
-  }
-
-  ngOnInit(): void {
-    this.updateDocumentId(this.router.url)
-    this.router.events
-      .pipe(
-        filter((event) => event instanceof NavigationEnd),
-        map((event) => (event as NavigationEnd).url)
-      )
-      .subscribe((url) => {
-        this.updateDocumentId(url)
-      })
-  }
-
-  private updateDocumentId(url: string): void {
-    const docIdRe = url.match(/^\/documents\/(\d+)/)
-    this.documentId = docIdRe ? +docIdRe[1] : undefined
-  }
-
-  sendMessage(): void {
-    if (!this.input.trim()) return
-
-    const userMessage: ChatMessage = { role: 'user', content: this.input }
-    this.messages.push(userMessage)
-    this.scrollToBottom()
-
-    const assistantMessage: ChatMessage = {
-      role: 'assistant',
-      content: '',
-      isStreaming: true,
-    }
-    this.messages.push(assistantMessage)
-    this.loading = true
-
-    let lastPartialLength = 0
-
-    this.chatService.streamChat(this.documentId, this.input).subscribe({
-      next: (chunk) => {
-        const delta = chunk.substring(lastPartialLength)
-        lastPartialLength = chunk.length
-        this.enqueueTypewriter(delta, assistantMessage)
-      },
-      error: () => {
-        assistantMessage.content += '\n\n⚠️ Error receiving response.'
-        assistantMessage.isStreaming = false
-        this.loading = false
-      },
-      complete: () => {
-        assistantMessage.isStreaming = false
-        this.loading = false
-        this.scrollToBottom()
-      },
-    })
-
-    this.input = ''
-  }
-
-  enqueueTypewriter(chunk: string, message: ChatMessage): void {
-    if (!chunk) return
-
-    this.typewriterBuffer.push(...chunk.split(''))
-
-    if (!this.typewriterActive) {
-      this.typewriterActive = true
-      this.playTypewriter(message)
-    }
-  }
-
-  playTypewriter(message: ChatMessage): void {
-    if (this.typewriterBuffer.length === 0) {
-      this.typewriterActive = false
-      return
-    }
-
-    const nextChar = this.typewriterBuffer.shift()
-    message.content += nextChar
-    this.scrollToBottom()
-
-    setTimeout(() => this.playTypewriter(message), 10) // 10ms per character
-  }
-
-  private scrollToBottom(): void {
-    setTimeout(() => {
-      this.scrollAnchor?.nativeElement?.scrollIntoView({ behavior: 'smooth' })
-    }, 50)
-  }
-
-  public onOpenChange(open: boolean): void {
-    if (open) {
-      setTimeout(() => {
-        this.chatInput.nativeElement.focus()
-      }, 10)
-    }
-  }
-
-  public searchInputKeyDown(event: KeyboardEvent) {
-    if (event.key === 'Enter') {
-      event.preventDefault()
-      this.sendMessage()
-    }
-  }
-}

src-ui/src/app/components/common/custom-fields-dropdown/custom-fields-dropdown.component.html

@@ -1,7 +1,7 @@
-<div ngbDropdown #fieldDropdown="ngbDropdown" (openChange)="onOpenClose($event)" [popperOptions]="popperOptions">
-    <button type="button" class="btn btn-sm btn-outline-primary" id="customFieldsDropdown" [disabled]="disabled" ngbDropdownToggle>
+<div ngbDropdown #fieldDropdown="ngbDropdown" (openChange)="onOpenClose($event)" [popperOptions]="popperOptions" placement="bottom-end">
+    <button class="btn btn-sm btn-outline-primary" id="customFieldsDropdown" [disabled]="disabled" ngbDropdownToggle>
       <i-bs name="ui-radios"></i-bs>
-      <div class="d-none d-lg-inline">&nbsp;<ng-container i18n>Custom Fields</ng-container></div>
+      <div class="d-none d-sm-inline">&nbsp;<ng-container i18n>Custom Fields</ng-container></div>
     </button>
     <div ngbDropdownMenu aria-labelledby="customFieldsDropdown" class="shadow custom-fields-dropdown">
         <div class="list-group list-group-flush" (keydown)="listKeyDown($event)">

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.html

@@ -430,6 +430,24 @@
           </div>
         </div>
       }
+      @case (WorkflowActionType.PasswordRemoval) {
+        <div class="row">
+          <div class="col">
+            <p class="small" i18n>
+              One or more passwords separated by commas or new lines. The workflow will try them in order until one succeeds.
+            </p>
+            <pngx-input-textarea
+              i18n-title
+              title="Passwords"
+              formControlName="passwords"
+              rows="4"
+              [error]="error?.actions?.[i]?.passwords"
+              hint="Passwords are stored in plain text. Use with caution."
+              i18n-hint
+            ></pngx-input-textarea>
+          </div>
+        </div>
+      }
     }
   </div>
 </ng-template>

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.spec.ts

@@ -252,7 +252,7 @@ describe('WorkflowEditDialogComponent', () => {
     expect(component.object.actions.length).toEqual(2)
   })
 
-  it('should update order on drag n drop', () => {
+  it('should update order and remove ids from actions on drag n drop', () => {
     const action1 = workflow.actions[0]
     const action2 = workflow.actions[1]
     component.object = workflow
@@ -261,6 +261,8 @@ describe('WorkflowEditDialogComponent', () => {
       WorkflowAction[]
     >)
     expect(component.object.actions).toEqual([action2, action1])
+    expect(action1.id).toBeNull()
+    expect(action2.id).toBeNull()
   })
 
   it('should not include auto matching in algorithms', () => {

src-ui/src/app/components/common/edit-dialog/workflow-edit-dialog/workflow-edit-dialog.component.ts

@@ -139,6 +139,10 @@ export const WORKFLOW_ACTION_OPTIONS = [
     id: WorkflowActionType.Webhook,
     name: $localize`Webhook`,
   },
+  {
+    id: WorkflowActionType.PasswordRemoval,
+    name: $localize`Password removal`,
+  },
 ]
 
 export enum TriggerFilterType {
@@ -1133,6 +1137,7 @@ export class WorkflowEditDialogComponent
           headers: new FormControl(action.webhook?.headers),
           include_document: new FormControl(!!action.webhook?.include_document),
         }),
+        passwords: new FormControl(action.passwords),
       }),
       { emitEvent }
     )
@@ -1283,6 +1288,11 @@ export class WorkflowEditDialogComponent
     const actionField = this.actionFields.at(event.previousIndex)
     this.actionFields.removeAt(event.previousIndex)
     this.actionFields.insert(event.currentIndex, actionField)
+    // removing id will effectively re-create the actions in this order
+    this.object.actions.forEach((a) => (a.id = null))
+    this.actionFields.controls.forEach((c) =>
+      c.get('id').setValue(null, { emitEvent: false })
+    )
   }
 
   save(): void {

src-ui/src/app/components/common/input/password/password.component.html

@@ -1,24 +1,17 @@
-<div class="mb-3" [class.pb-3]="error">
-  <div class="row">
-    <div class="d-flex align-items-center position-relative hidden-button-container" [class.col-md-3]="horizontal">
-      @if (title) {
-        <label class="form-label" [class.mb-md-0]="horizontal" [for]="inputId">{{title}}</label>
-      }
-    </div>
-  <div class="position-relative" [class.col-md-9]="horizontal">
-    <div class="input-group" [class.is-invalid]="error">
-      <input #inputField [type]="showReveal && textVisible ? 'text' : 'password'" class="form-control" [class.is-invalid]="error" [id]="inputId" [(ngModel)]="value" (focus)="onFocus()" (focusout)="onFocusOut()" (change)="onChange(value)" [disabled]="disabled" [autocomplete]="autocomplete">
-      @if (showReveal) {
-        <button type="button" class="btn btn-outline-secondary" (click)="toggleVisibility()" i18n-title title="Show password" [disabled]="disabled || disableRevealToggle">
-          <i-bs name="eye"></i-bs>
-        </button>
-      }
-    </div>
-    <div class="invalid-feedback">
-      {{error}}
-    </div>
-    @if (hint) {
-      <small class="form-text text-muted" [innerHTML]="hint"></small>
+<div class="mb-3">
+  <label class="form-label" [for]="inputId">{{title}}</label>
+  <div class="input-group" [class.is-invalid]="error">
+    <input #inputField [type]="showReveal && textVisible ? 'text' : 'password'" class="form-control" [class.is-invalid]="error" [id]="inputId" [(ngModel)]="value" (focus)="onFocus()" (focusout)="onFocusOut()" (change)="onChange(value)" [disabled]="disabled" [autocomplete]="autocomplete">
+    @if (showReveal) {
+      <button type="button" class="btn btn-outline-secondary" (click)="toggleVisibility()" i18n-title title="Show password" [disabled]="disabled || disableRevealToggle">
+        <i-bs name="eye"></i-bs>
+      </button>
     }
   </div>
+  <div class="invalid-feedback">
+    {{error}}
+  </div>
+  @if (hint) {
+    <small class="form-text text-muted" [innerHTML]="hint"></small>
+  }
 </div>

src-ui/src/app/components/common/input/tags/tags.component.html

@@ -28,7 +28,7 @@
             </button>
           </ng-template>
           <ng-template ng-option-tmp let-item="item" let-index="index" let-search="searchTerm">
-            <div class="tag-option-row d-flex align-items-center" [class.w-auto]="!getTag(item.id)?.parent">
+            <div class="tag-option-row d-flex align-items-center">
               @if (item.id && tags) {
                 @if (getTag(item.id)?.parent) {
                   <i-bs name="list-nested" class="me-1"></i-bs>

src-ui/src/app/components/common/input/tags/tags.component.scss

@@ -22,8 +22,8 @@
 }
 
 // Dropdown hierarchy reveal for ng-select options
-:host ::ng-deep .ng-dropdown-panel .ng-option {
-  overflow-x: auto !important;
+::ng-deep .ng-dropdown-panel .ng-option {
+  overflow-x: scroll;
 
   .tag-option-row {
     font-size: 1rem;
@@ -41,12 +41,12 @@
   }
 }
 
-:host ::ng-deep .ng-dropdown-panel .ng-option:hover .hierarchy-reveal,
-:host ::ng-deep .ng-dropdown-panel .ng-option.ng-option-marked .hierarchy-reveal {
+::ng-deep .ng-dropdown-panel .ng-option:hover .hierarchy-reveal,
+::ng-deep .ng-dropdown-panel .ng-option.ng-option-marked .hierarchy-reveal {
   max-width: 1000px;
 }
 
 ::ng-deep .ng-dropdown-panel .ng-option:hover .hierarchy-indicator,
-:host ::ng-deep .ng-dropdown-panel .ng-option.ng-option-marked .hierarchy-indicator {
+::ng-deep .ng-dropdown-panel .ng-option.ng-option-marked .hierarchy-indicator {
   background: transparent;
 }

src-ui/src/app/components/common/input/text/text.component.html

@@ -15,12 +15,6 @@
         @if (hint) {
           <small class="form-text text-muted" [innerHTML]="hint"></small>
         }
-        @if (getSuggestion()?.length > 0) {
-          <small>
-            <span i18n>Suggestion:</span>&nbsp;
-            <a (click)="applySuggestion(s)" [routerLink]="[]">{{getSuggestion()}}</a>&nbsp;
-          </small>
-        }
         <div class="invalid-feedback position-absolute top-100">
           {{error}}
         </div>

src-ui/src/app/components/common/input/text/text.component.spec.ts

@@ -26,20 +26,10 @@ describe('TextComponent', () => {
 
   it('should support use of input field', () => {
     expect(component.value).toBeUndefined()
-    input.value = 'foo'
-    input.dispatchEvent(new Event('input'))
-    fixture.detectChanges()
-    expect(component.value).toBe('foo')
-  })
-
-  it('should support suggestion', () => {
-    component.value = 'foo'
-    component.suggestion = 'foo'
-    expect(component.getSuggestion()).toBe('')
-    component.value = 'bar'
-    expect(component.getSuggestion()).toBe('foo')
-    component.applySuggestion()
-    fixture.detectChanges()
-    expect(component.value).toBe('foo')
+    // TODO: why doesn't this work?
+    // input.value = 'foo'
+    // input.dispatchEvent(new Event('change'))
+    // fixture.detectChanges()
+    // expect(component.value).toEqual('foo')
   })
 })

src-ui/src/app/components/common/input/text/text.component.ts

@@ -4,7 +4,6 @@ import {
   NG_VALUE_ACCESSOR,
   ReactiveFormsModule,
 } from '@angular/forms'
-import { RouterLink } from '@angular/router'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
 import { AbstractInputComponent } from '../abstract-input'
 
@@ -19,12 +18,7 @@ import { AbstractInputComponent } from '../abstract-input'
   selector: 'pngx-input-text',
   templateUrl: './text.component.html',
   styleUrls: ['./text.component.scss'],
-  imports: [
-    FormsModule,
-    ReactiveFormsModule,
-    NgxBootstrapIconsModule,
-    RouterLink,
-  ],
+  imports: [FormsModule, ReactiveFormsModule, NgxBootstrapIconsModule],
 })
 export class TextComponent extends AbstractInputComponent<string> {
   @Input()
@@ -33,19 +27,7 @@ export class TextComponent extends AbstractInputComponent<string> {
   @Input()
   placeholder: string = ''
 
-  @Input()
-  suggestion: string = ''
-
   constructor() {
     super()
   }
-
-  getSuggestion() {
-    return this.value !== this.suggestion ? this.suggestion : ''
-  }
-
-  applySuggestion() {
-    this.value = this.suggestion
-    this.onChange(this.value)
-  }
 }

src-ui/src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.html

@@ -1,49 +0,0 @@
-<div class="btn-group">
-  <button type="button" class="btn btn-sm btn-outline-primary" (click)="clickSuggest()" [disabled]="loading || (suggestions && !aiEnabled)">
-    @if (loading) {
-      <div class="spinner-border spinner-border-sm" role="status"></div>
-    } @else {
-      <i-bs width="1.2em" height="1.2em" name="stars"></i-bs>
-    }
-    <span class="d-none d-lg-inline ps-1" i18n>Suggest</span>
-    @if (totalSuggestions > 0) {
-      <span class="badge bg-primary ms-2">{{ totalSuggestions }}</span>
-    }
-  </button>
-
-  @if (aiEnabled) {
-    <div class="btn-group" ngbDropdown #dropdown="ngbDropdown" [popperOptions]="popperOptions">
-      <button type="button" class="btn btn-sm btn-outline-primary" ngbDropdownToggle [disabled]="loading || !suggestions" aria-expanded="false" aria-controls="suggestionsDropdown" aria-label="Suggestions dropdown">
-        <span class="visually-hidden" i18n>Show suggestions</span>
-      </button>
-
-      <div ngbDropdownMenu aria-labelledby="suggestionsDropdown" class="shadow suggestions-dropdown">
-        <div class="list-group list-group-flush small pb-0">
-          @if (!suggestions?.suggested_tags && !suggestions?.suggested_document_types && !suggestions?.suggested_correspondents) {
-            <div class="list-group-item text-muted fst-italic">
-              <small class="text-muted small fst-italic" i18n>No novel suggestions</small>
-            </div>
-          }
-          @if (suggestions?.suggested_tags.length > 0) {
-            <small class="list-group-item text-uppercase text-muted small">Tags</small>
-            @for (tag of suggestions.suggested_tags; track tag) {
-              <button type="button" class="list-group-item list-group-item-action bg-light" (click)="addTag.emit(tag)" i18n>{{ tag }}</button>
-            }
-          }
-          @if (suggestions?.suggested_document_types.length > 0) {
-            <div class="list-group-item text-uppercase text-muted small">Document Types</div>
-            @for (type of suggestions.suggested_document_types; track type) {
-              <button type="button" class="list-group-item list-group-item-action bg-light" (click)="addDocumentType.emit(type)" i18n>{{ type }}</button>
-            }
-          }
-          @if (suggestions?.suggested_correspondents.length > 0) {
-            <div class="list-group-item text-uppercase text-muted small">Correspondents</div>
-            @for (correspondent of suggestions.suggested_correspondents; track correspondent) {
-              <button type="button" class="list-group-item list-group-item-action bg-light" (click)="addCorrespondent.emit(correspondent)" i18n>{{ correspondent }}</button>
-            }
-          }
-        </div>
-      </div>
-    </div>
-  }
-</div>

src-ui/src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.scss

@@ -1,3 +0,0 @@
-.suggestions-dropdown {
-  min-width: 250px;
-}

src-ui/src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.spec.ts

@@ -1,51 +0,0 @@
-import { ComponentFixture, TestBed } from '@angular/core/testing'
-import { NgbDropdownModule } from '@ng-bootstrap/ng-bootstrap'
-import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
-import { SuggestionsDropdownComponent } from './suggestions-dropdown.component'
-
-describe('SuggestionsDropdownComponent', () => {
-  let component: SuggestionsDropdownComponent
-  let fixture: ComponentFixture<SuggestionsDropdownComponent>
-
-  beforeEach(() => {
-    TestBed.configureTestingModule({
-      imports: [
-        NgbDropdownModule,
-        NgxBootstrapIconsModule.pick(allIcons),
-        SuggestionsDropdownComponent,
-      ],
-      providers: [],
-    })
-    fixture = TestBed.createComponent(SuggestionsDropdownComponent)
-    component = fixture.componentInstance
-    fixture.detectChanges()
-  })
-
-  it('should calculate totalSuggestions', () => {
-    component.suggestions = {
-      suggested_correspondents: ['John Doe'],
-      suggested_tags: ['Tag1', 'Tag2'],
-      suggested_document_types: ['Type1'],
-    }
-    expect(component.totalSuggestions).toBe(4)
-  })
-
-  it('should emit getSuggestions when clickSuggest is called and suggestions are null', () => {
-    jest.spyOn(component.getSuggestions, 'emit')
-    component.suggestions = null
-    component.clickSuggest()
-    expect(component.getSuggestions.emit).toHaveBeenCalled()
-  })
-
-  it('should toggle dropdown when clickSuggest is called and suggestions are not null', () => {
-    component.aiEnabled = true
-    fixture.detectChanges()
-    component.suggestions = {
-      suggested_correspondents: [],
-      suggested_tags: [],
-      suggested_document_types: [],
-    }
-    component.clickSuggest()
-    expect(component.dropdown.open).toBeTruthy()
-  })
-})

src-ui/src/app/components/common/suggestions-dropdown/suggestions-dropdown.component.ts

@@ -1,64 +0,0 @@
-import {
-  Component,
-  EventEmitter,
-  Input,
-  Output,
-  ViewChild,
-} from '@angular/core'
-import { NgbDropdown, NgbDropdownModule } from '@ng-bootstrap/ng-bootstrap'
-import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
-import { DocumentSuggestions } from 'src/app/data/document-suggestions'
-import { pngxPopperOptions } from 'src/app/utils/popper-options'
-
-@Component({
-  selector: 'pngx-suggestions-dropdown',
-  imports: [NgbDropdownModule, NgxBootstrapIconsModule],
-  templateUrl: './suggestions-dropdown.component.html',
-  styleUrl: './suggestions-dropdown.component.scss',
-})
-export class SuggestionsDropdownComponent {
-  public popperOptions = pngxPopperOptions
-
-  @ViewChild('dropdown') dropdown: NgbDropdown
-
-  @Input()
-  suggestions: DocumentSuggestions = null
-
-  @Input()
-  aiEnabled: boolean = false
-
-  @Input()
-  loading: boolean = false
-
-  @Input()
-  disabled: boolean = false
-
-  @Output()
-  getSuggestions: EventEmitter<SuggestionsDropdownComponent> =
-    new EventEmitter()
-
-  @Output()
-  addTag: EventEmitter<string> = new EventEmitter()
-
-  @Output()
-  addDocumentType: EventEmitter<string> = new EventEmitter()
-
-  @Output()
-  addCorrespondent: EventEmitter<string> = new EventEmitter()
-
-  public clickSuggest(): void {
-    if (!this.suggestions) {
-      this.getSuggestions.emit(this)
-    } else {
-      this.dropdown?.toggle()
-    }
-  }
-
-  get totalSuggestions(): number {
-    return (
-      this.suggestions?.suggested_correspondents?.length +
-        this.suggestions?.suggested_tags?.length +
-        this.suggestions?.suggested_document_types?.length || 0
-    )
-  }
-}

src-ui/src/app/components/common/system-status-dialog/system-status-dialog.component.html

@@ -266,43 +266,6 @@
                   }
                 </span>
               </dd>
-              @if (aiEnabled) {
-                <dt i18n>AI Index</dt>
-                <dd class="d-flex align-items-center">
-                  <button class="btn btn-sm d-flex align-items-center btn-dark text-uppercase small" [ngbPopover]="llmIndexStatus" triggers="click mouseenter:mouseleave">
-                    {{status.tasks.llmindex_status}}
-                    @if (status.tasks.llmindex_status === 'OK') {
-                      @if (isStale(status.tasks.llmindex_last_modified)) {
-                        <i-bs name="exclamation-triangle-fill" class="text-warning ms-2 lh-1"></i-bs>
-                      } @else {
-                        <i-bs name="check-circle-fill" class="text-primary ms-2 lh-1"></i-bs>
-                      }
-                    } @else {
-                      <i-bs name="exclamation-triangle-fill" class="ms-2 lh-1"
-                      [class.text-danger]="status.tasks.llmindex_status === SystemStatusItemStatus.ERROR"
-                      [class.text-warning]="status.tasks.llmindex_status === SystemStatusItemStatus.WARNING"
-                      [class.text-muted]="status.tasks.llmindex_status === SystemStatusItemStatus.DISABLED"></i-bs>
-                    }
-                  </button>
-                  @if (currentUserIsSuperUser) {
-                    @if (isRunning(PaperlessTaskName.LLMIndexUpdate)) {
-                      <div class="spinner-border spinner-border-sm ms-2" role="status"></div>
-                    } @else {
-                      <button class="btn btn-sm d-flex align-items-center btn-dark small ms-2" (click)="runTask(PaperlessTaskName.LLMIndexUpdate)">
-                        <i-bs name="play-fill"></i-bs>&nbsp;
-                        <ng-container i18n>Run Task</ng-container>
-                      </button>
-                    }
-                  }
-                </dd>
-                <ng-template #llmIndexStatus>
-                  @if (status.tasks.llmindex_status === 'OK') {
-                    <h6><ng-container i18n>Last Run</ng-container>:</h6> <span class="font-monospace small">{{status.tasks.llmindex_last_modified | customDate:'medium'}}</span>
-                  } @else {
-                    <h6><ng-container i18n>Error</ng-container>:</h6> <span class="font-monospace small">{{status.tasks.llmindex_error}}</span>
-                  }
-                </ng-template>
-              }
             </dl>
           </div>
         </div>

src-ui/src/app/components/common/system-status-dialog/system-status-dialog.component.spec.ts

@@ -68,9 +68,6 @@ const status: SystemStatus = {
     sanity_check_status: SystemStatusItemStatus.OK,
     sanity_check_last_run: new Date().toISOString(),
     sanity_check_error: null,
-    llmindex_status: SystemStatusItemStatus.OK,
-    llmindex_last_modified: new Date().toISOString(),
-    llmindex_error: null,
   },
 }
 

src-ui/src/app/components/common/system-status-dialog/system-status-dialog.component.ts

@@ -13,11 +13,9 @@ import {
   SystemStatus,
   SystemStatusItemStatus,
 } from 'src/app/data/system-status'
-import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
 import { FileSizePipe } from 'src/app/pipes/file-size.pipe'
 import { PermissionsService } from 'src/app/services/permissions.service'
-import { SettingsService } from 'src/app/services/settings.service'
 import { SystemStatusService } from 'src/app/services/system-status.service'
 import { TasksService } from 'src/app/services/tasks.service'
 import { ToastService } from 'src/app/services/toast.service'
@@ -46,7 +44,6 @@ export class SystemStatusDialogComponent implements OnInit, OnDestroy {
   private toastService = inject(ToastService)
   private permissionsService = inject(PermissionsService)
   private websocketStatusService = inject(WebsocketStatusService)
-  private settingsService = inject(SettingsService)
 
   public SystemStatusItemStatus = SystemStatusItemStatus
   public PaperlessTaskName = PaperlessTaskName
@@ -63,10 +60,6 @@ export class SystemStatusDialogComponent implements OnInit, OnDestroy {
     return this.permissionsService.isSuperUser()
   }
 
-  get aiEnabled(): boolean {
-    return this.settingsService.get(SETTINGS_KEYS.AI_ENABLED)
-  }
-
   public ngOnInit() {
     this.versionMismatch =
       environment.production &&

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -74,6 +74,16 @@
     </div>
   </div>
 
+  <pngx-custom-fields-dropdown
+    *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.CustomField }"
+    [documentId]="documentId"
+    [disabled]="!userCanEdit"
+    [existingFields]="document?.custom_fields"
+    (created)="refreshCustomFields()"
+    (added)="addField($event)">
+  </pngx-custom-fields-dropdown>
+
+
   <div class="ms-auto" ngbDropdown>
     <button class="btn btn-sm btn-outline-primary" id="sendDropdown" ngbDropdownToggle>
       <i-bs name="send"></i-bs>
@@ -94,7 +104,7 @@
 </pngx-page-header>
 
 <div class="row">
-  <div class="col-md-6 col-xl-5 mb-4">
+  <div class="col-md-6 col-xl-4 mb-4">
 
     <form [formGroup]='documentForm' (ngSubmit)="save()">
 
@@ -111,32 +121,6 @@
           </button>
         </div>
 
-        <ng-container *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }">
-          <div class="btn-group pb-3 ms-auto">
-            <pngx-suggestions-dropdown *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }"
-              [disabled]="!userCanEdit || suggestionsLoading"
-              [loading]="suggestionsLoading"
-              [suggestions]="suggestions"
-              [aiEnabled]="aiEnabled"
-              (getSuggestions)="getSuggestions()"
-              (addTag)="createTag($event)"
-              (addDocumentType)="createDocumentType($event)"
-              (addCorrespondent)="createCorrespondent($event)">
-            </pngx-suggestions-dropdown>
-          </div>
-
-          <div class="btn-group pb-3 ms-2">
-            <pngx-custom-fields-dropdown
-              *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.CustomField }"
-              [documentId]="documentId"
-              [disabled]="!userCanEdit"
-              [existingFields]="document?.custom_fields"
-              (created)="refreshCustomFields()"
-              (added)="addField($event)">
-            </pngx-custom-fields-dropdown>
-          </div>
-        </ng-container>
-
         <ng-container *ngTemplateOutlet="saveButtons"></ng-container>
       </div>
 
@@ -145,7 +129,7 @@
           <a ngbNavLink i18n>Details</a>
           <ng-template ngbNavContent>
             <div>
-              <pngx-input-text #inputTitle i18n-title title="Title" formControlName="title" [horizontal]="true" [suggestion]="suggestions?.title" (keyup)="titleKeyUp($event)" [error]="error?.title"></pngx-input-text>
+              <pngx-input-text #inputTitle i18n-title title="Title" formControlName="title" [horizontal]="true" (keyup)="titleKeyUp($event)" [error]="error?.title"></pngx-input-text>
               <pngx-input-number i18n-title title="Archive serial number" [error]="error?.archive_serial_number" [horizontal]="true" formControlName='archive_serial_number'></pngx-input-number>
               <pngx-input-date i18n-title title="Date created" formControlName="created" [suggestions]="suggestions?.dates" [showFilter]="true" [horizontal]="true" (filterDocuments)="filterDocuments($event)"
               [error]="error?.created"></pngx-input-date>
@@ -155,7 +139,7 @@
               (createNew)="createDocumentType($event)" [hideAddButton]="createDisabled(DataType.DocumentType)" [suggestions]="suggestions?.document_types" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.DocumentType }"></pngx-input-select>
               <pngx-input-select [items]="storagePaths" i18n-title title="Storage path" formControlName="storage_path" [allowNull]="true" [showFilter]="true" [horizontal]="true" (filterDocuments)="filterDocuments($event, DataType.StoragePath)"
               (createNew)="createStoragePath($event)" [hideAddButton]="createDisabled(DataType.StoragePath)" [suggestions]="suggestions?.storage_paths" i18n-placeholder placeholder="Default" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.StoragePath }"></pngx-input-select>
-              <pngx-input-tags #tagsInput formControlName="tags" [suggestions]="suggestions?.tags" [showFilter]="true" [horizontal]="true" (filterDocuments)="filterDocuments($event, DataType.Tag)" [hideAddButton]="createDisabled(DataType.Tag)" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Tag }"></pngx-input-tags>
+              <pngx-input-tags formControlName="tags" [suggestions]="suggestions?.tags" [showFilter]="true" [horizontal]="true" (filterDocuments)="filterDocuments($event, DataType.Tag)" [hideAddButton]="createDisabled(DataType.Tag)" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Tag }"></pngx-input-tags>
               @for (fieldInstance of document?.custom_fields; track fieldInstance.field; let i = $index) {
                 <div [formGroup]="customFieldFormFields.controls[i]">
                   @switch (getCustomFieldFromInstance(fieldInstance)?.data_type) {
@@ -377,14 +361,14 @@
     </form>
   </div>
 
-  <div class="col-md-6 col-xl-7 mb-3 d-none d-md-block position-relative" #pdfPreview>
+  <div class="col-md-6 col-xl-8 mb-3 d-none d-md-block position-relative" #pdfPreview>
     <ng-container *ngTemplateOutlet="previewContent"></ng-container>
   </div>
 
 </div>
 
 <ng-template #saveButtons>
-  <div class="btn-group pb-3 ms-4">
+  <div class="btn-group pb-3 ms-auto">
     <ng-container *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.Document }">
       <button type="submit" class="order-3 btn btn-sm btn-primary" i18n [disabled]="!userCanEdit || networkActive || (isDirty$ | async) !== true">Save</button>
       @if (hasNext()) {

src-ui/src/app/components/document-detail/document-detail.component.spec.ts

@@ -157,16 +157,6 @@ describe('DocumentDetailComponent', () => {
         {
           provide: TagService,
           useValue: {
-            getCachedMany: (ids: number[]) =>
-              of(
-                ids.map((id) => ({
-                  id,
-                  name: `Tag${id}`,
-                  is_inbox_tag: true,
-                  color: '#ff0000',
-                  text_color: '#000000',
-                }))
-              ),
             listAll: () =>
               of({
                 count: 3,
@@ -393,32 +383,8 @@ describe('DocumentDetailComponent', () => {
     currentUserCan = true
   })
 
-  it('should support creating tag, remove from suggestions', () => {
+  it('should support creating document type', () => {
     initNormally()
-    component.suggestions = {
-      suggested_tags: ['Tag1', 'NewTag12'],
-    }
-    let openModal: NgbModalRef
-    modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
-    const modalSpy = jest.spyOn(modalService, 'open')
-    component.createTag('NewTag12')
-    expect(modalSpy).toHaveBeenCalled()
-    openModal.componentInstance.succeeded.next({
-      id: 12,
-      name: 'NewTag12',
-      is_inbox_tag: true,
-      color: '#ff0000',
-      text_color: '#000000',
-    })
-    expect(component.tagsInput.value).toContain(12)
-    expect(component.suggestions.suggested_tags).not.toContain('NewTag12')
-  })
-
-  it('should support creating document type, remove from suggestions', () => {
-    initNormally()
-    component.suggestions = {
-      suggested_document_types: ['DocumentType1', 'NewDocType2'],
-    }
     let openModal: NgbModalRef
     modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
     const modalSpy = jest.spyOn(modalService, 'open')
@@ -426,16 +392,10 @@ describe('DocumentDetailComponent', () => {
     expect(modalSpy).toHaveBeenCalled()
     openModal.componentInstance.succeeded.next({ id: 12, name: 'NewDocType12' })
     expect(component.documentForm.get('document_type').value).toEqual(12)
-    expect(component.suggestions.suggested_document_types).not.toContain(
-      'NewDocType2'
-    )
   })
 
-  it('should support creating correspondent, remove from suggestions', () => {
+  it('should support creating correspondent', () => {
     initNormally()
-    component.suggestions = {
-      suggested_correspondents: ['Correspondent1', 'NewCorrrespondent12'],
-    }
     let openModal: NgbModalRef
     modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
     const modalSpy = jest.spyOn(modalService, 'open')
@@ -446,9 +406,6 @@ describe('DocumentDetailComponent', () => {
       name: 'NewCorrrespondent12',
     })
     expect(component.documentForm.get('correspondent').value).toEqual(12)
-    expect(component.suggestions.suggested_correspondents).not.toContain(
-      'NewCorrrespondent12'
-    )
   })
 
   it('should support creating storage path', () => {
@@ -1039,7 +996,7 @@ describe('DocumentDetailComponent', () => {
     expect(component.document.custom_fields).toHaveLength(initialLength - 1)
     expect(component.customFieldFormFields).toHaveLength(initialLength - 1)
     expect(
-      fixture.debugElement.query(By.css('form ul')).nativeElement.textContent
+      fixture.debugElement.query(By.css('form')).nativeElement.textContent
     ).not.toContain('Field 1')
     const patchSpy = jest.spyOn(documentService, 'patch')
     component.save(true)
@@ -1130,22 +1087,10 @@ describe('DocumentDetailComponent', () => {
 
   it('should get suggestions', () => {
     const suggestionsSpy = jest.spyOn(documentService, 'getSuggestions')
-    suggestionsSpy.mockReturnValue(
-      of({
-        tags: [42, 43],
-        suggested_tags: [],
-        suggested_document_types: [],
-        suggested_correspondents: [],
-      })
-    )
+    suggestionsSpy.mockReturnValue(of({ tags: [42, 43] }))
     initNormally()
     expect(suggestionsSpy).toHaveBeenCalled()
-    expect(component.suggestions).toEqual({
-      tags: [42, 43],
-      suggested_tags: [],
-      suggested_document_types: [],
-      suggested_correspondents: [],
-    })
+    expect(component.suggestions).toEqual({ tags: [42, 43] })
   })
 
   it('should show error if needed for get suggestions', () => {

src-ui/src/app/components/document-detail/document-detail.component.ts

@@ -31,7 +31,6 @@ import {
   map,
   switchMap,
   takeUntil,
-  tap,
 } from 'rxjs/operators'
 import { Correspondent } from 'src/app/data/correspondent'
 import { CustomField, CustomFieldDataType } from 'src/app/data/custom-field'
@@ -77,7 +76,6 @@ import { DocumentTypeService } from 'src/app/services/rest/document-type.service
 import { DocumentService } from 'src/app/services/rest/document.service'
 import { SavedViewService } from 'src/app/services/rest/saved-view.service'
 import { StoragePathService } from 'src/app/services/rest/storage-path.service'
-import { TagService } from 'src/app/services/rest/tag.service'
 import { UserService } from 'src/app/services/rest/user.service'
 import { SettingsService } from 'src/app/services/settings.service'
 import { ToastService } from 'src/app/services/toast.service'
@@ -91,7 +89,6 @@ import { CorrespondentEditDialogComponent } from '../common/edit-dialog/correspo
 import { DocumentTypeEditDialogComponent } from '../common/edit-dialog/document-type-edit-dialog/document-type-edit-dialog.component'
 import { EditDialogMode } from '../common/edit-dialog/edit-dialog.component'
 import { StoragePathEditDialogComponent } from '../common/edit-dialog/storage-path-edit-dialog/storage-path-edit-dialog.component'
-import { TagEditDialogComponent } from '../common/edit-dialog/tag-edit-dialog/tag-edit-dialog.component'
 import { EmailDocumentDialogComponent } from '../common/email-document-dialog/email-document-dialog.component'
 import { CheckComponent } from '../common/input/check/check.component'
 import { DateComponent } from '../common/input/date/date.component'
@@ -110,7 +107,6 @@ import {
   PdfEditorEditMode,
 } from '../common/pdf-editor/pdf-editor.component'
 import { ShareLinksDialogComponent } from '../common/share-links-dialog/share-links-dialog.component'
-import { SuggestionsDropdownComponent } from '../common/suggestions-dropdown/suggestions-dropdown.component'
 import { DocumentHistoryComponent } from '../document-history/document-history.component'
 import { DocumentNotesComponent } from '../document-notes/document-notes.component'
 import { ComponentWithPermissions } from '../with-permissions/with-permissions.component'
@@ -167,7 +163,6 @@ export enum ZoomSetting {
     NumberComponent,
     MonetaryComponent,
     UrlComponent,
-    SuggestionsDropdownComponent,
     CustomDatePipe,
     FileSizePipe,
     IfPermissionsDirective,
@@ -181,6 +176,7 @@ export enum ZoomSetting {
     NgxBootstrapIconsModule,
     PdfViewerModule,
     TextAreaComponent,
+    PasswordRemovalConfirmDialogComponent,
   ],
 })
 export class DocumentDetailComponent
@@ -189,7 +185,6 @@ export class DocumentDetailComponent
 {
   private documentsService = inject(DocumentService)
   private route = inject(ActivatedRoute)
-  private tagService = inject(TagService)
   private correspondentService = inject(CorrespondentService)
   private documentTypeService = inject(DocumentTypeService)
   private router = inject(Router)
@@ -212,8 +207,6 @@ export class DocumentDetailComponent
   @ViewChild('inputTitle')
   titleInput: TextComponent
 
-  @ViewChild('tagsInput') tagsInput: TagsComponent
-
   expandOriginalMetadata = false
   expandArchivedMetadata = false
 
@@ -225,7 +218,6 @@ export class DocumentDetailComponent
   document: Document
   metadata: DocumentMetadata
   suggestions: DocumentSuggestions
-  suggestionsLoading: boolean = false
   users: User[]
 
   title: string
@@ -285,10 +277,10 @@ export class DocumentDetailComponent
     if (
       element &&
       element.nativeElement.offsetParent !== null &&
-      this.nav?.activeId == DocumentDetailNavIDs.Preview
+      this.nav?.activeId == 4
     ) {
       // its visible
-      setTimeout(() => this.nav?.select(DocumentDetailNavIDs.Details))
+      setTimeout(() => this.nav?.select(1))
     }
   }
 
@@ -307,10 +299,6 @@ export class DocumentDetailComponent
     return this.deviceDetectorService.isMobile()
   }
 
-  get aiEnabled(): boolean {
-    return this.settings.get(SETTINGS_KEYS.AI_ENABLED)
-  }
-
   get archiveContentRenderType(): ContentRenderType {
     return this.document?.archived_file_name
       ? this.getRenderType('application/pdf')
@@ -695,12 +683,25 @@ export class DocumentDetailComponent
         PermissionType.Document
       )
     ) {
-      this.tagService.getCachedMany(doc.tags).subscribe((tags) => {
-        // only show suggestions if document has inbox tags
-        if (tags.some((tag) => tag.is_inbox_tag)) {
-          this.getSuggestions()
-        }
-      })
+      this.documentsService
+        .getSuggestions(doc.id)
+        .pipe(
+          first(),
+          takeUntil(this.unsubscribeNotifier),
+          takeUntil(this.docChangeNotifier)
+        )
+        .subscribe({
+          next: (result) => {
+            this.suggestions = result
+          },
+          error: (error) => {
+            this.suggestions = null
+            this.toastService.showError(
+              $localize`Error retrieving suggestions.`,
+              error
+            )
+          },
+        })
     }
     this.title = this.documentTitlePipe.transform(doc.title)
     this.prepareForm(doc)
@@ -710,63 +711,6 @@ export class DocumentDetailComponent
     return this.documentForm.get('custom_fields') as FormArray
   }
 
-  getSuggestions() {
-    this.suggestionsLoading = true
-    this.documentsService
-      .getSuggestions(this.documentId)
-      .pipe(
-        first(),
-        takeUntil(this.unsubscribeNotifier),
-        takeUntil(this.docChangeNotifier)
-      )
-      .subscribe({
-        next: (result) => {
-          this.suggestions = result
-          this.suggestionsLoading = false
-        },
-        error: (error) => {
-          this.suggestions = null
-          this.suggestionsLoading = false
-          this.toastService.showError(
-            $localize`Error retrieving suggestions.`,
-            error
-          )
-        },
-      })
-  }
-
-  createTag(newName: string) {
-    var modal = this.modalService.open(TagEditDialogComponent, {
-      backdrop: 'static',
-    })
-    modal.componentInstance.dialogMode = EditDialogMode.CREATE
-    if (newName) modal.componentInstance.object = { name: newName }
-    modal.componentInstance.succeeded
-      .pipe(
-        tap((newTag: Tag) => {
-          // remove from suggestions if present
-          if (this.suggestions) {
-            this.suggestions = {
-              ...this.suggestions,
-              suggested_tags: this.suggestions.suggested_tags.filter(
-                (tag) => tag !== newTag.name
-              ),
-            }
-          }
-        }),
-        switchMap((newTag: Tag) => {
-          return this.tagService
-            .listAll()
-            .pipe(map((tags) => ({ newTag, tags })))
-        }),
-        takeUntil(this.unsubscribeNotifier)
-      )
-      .subscribe(({ newTag, tags }) => {
-        this.tagsInput.tags = tags.results
-        this.tagsInput.addTag(newTag.id)
-      })
-  }
-
   createDocumentType(newName: string) {
     var modal = this.modalService.open(DocumentTypeEditDialogComponent, {
       backdrop: 'static',
@@ -786,12 +730,6 @@ export class DocumentDetailComponent
         this.documentTypes = documentTypes.results
         this.documentForm.get('document_type').setValue(newDocumentType.id)
         this.documentForm.get('document_type').markAsDirty()
-        if (this.suggestions) {
-          this.suggestions.suggested_document_types =
-            this.suggestions.suggested_document_types.filter(
-              (dt) => dt !== newName
-            )
-        }
       })
   }
 
@@ -816,12 +754,6 @@ export class DocumentDetailComponent
         this.correspondents = correspondents.results
         this.documentForm.get('correspondent').setValue(newCorrespondent.id)
         this.documentForm.get('correspondent').markAsDirty()
-        if (this.suggestions) {
-          this.suggestions.suggested_correspondents =
-            this.suggestions.suggested_correspondents.filter(
-              (c) => c !== newName
-            )
-        }
       })
   }
 

src-ui/src/app/data/document-suggestions.ts

@@ -1,17 +1,11 @@
 export interface DocumentSuggestions {
-  title?: string
-
   tags?: number[]
-  suggested_tags?: string[]
 
   correspondents?: number[]
-  suggested_correspondents?: string[]
 
   document_types?: number[]
-  suggested_document_types?: string[]
 
   storage_paths?: number[]
-  suggested_storage_paths?: string[]
 
   dates?: string[] // ISO-formatted date string e.g. 2022-11-03
 }

src-ui/src/app/data/paperless-config.ts

@@ -44,24 +44,12 @@ export enum ConfigOptionType {
   Boolean = 'boolean',
   JSON = 'json',
   File = 'file',
-  Password = 'password',
 }
 
 export const ConfigCategory = {
   General: $localize`General Settings`,
   OCR: $localize`OCR Settings`,
   Barcode: $localize`Barcode Settings`,
-  AI: $localize`AI Settings`,
-}
-
-export const LLMEmbeddingBackendConfig = {
-  OPENAI: 'openai',
-  HUGGINGFACE: 'huggingface',
-}
-
-export const LLMBackendConfig = {
-  OPENAI: 'openai',
-  OLLAMA: 'ollama',
 }
 
 export interface ConfigOption {
@@ -71,7 +59,6 @@ export interface ConfigOption {
   choices?: Array<{ id: string; name: string }>
   config_key?: string
   category: string
-  note?: string
 }
 
 function mapToItems(enumObj: Object): Array<{ id: string; name: string }> {
@@ -271,58 +258,6 @@ export const PaperlessConfigOptions: ConfigOption[] = [
     config_key: 'PAPERLESS_CONSUMER_TAG_BARCODE_MAPPING',
     category: ConfigCategory.Barcode,
   },
-  {
-    key: 'ai_enabled',
-    title: $localize`AI Enabled`,
-    type: ConfigOptionType.Boolean,
-    config_key: 'PAPERLESS_AI_ENABLED',
-    category: ConfigCategory.AI,
-    note: $localize`Consider privacy implications when enabling AI features, especially if using a remote model.`,
-  },
-  {
-    key: 'llm_embedding_backend',
-    title: $localize`LLM Embedding Backend`,
-    type: ConfigOptionType.Select,
-    choices: mapToItems(LLMEmbeddingBackendConfig),
-    config_key: 'PAPERLESS_AI_LLM_EMBEDDING_BACKEND',
-    category: ConfigCategory.AI,
-  },
-  {
-    key: 'llm_embedding_model',
-    title: $localize`LLM Embedding Model`,
-    type: ConfigOptionType.String,
-    config_key: 'PAPERLESS_AI_LLM_EMBEDDING_MODEL',
-    category: ConfigCategory.AI,
-  },
-  {
-    key: 'llm_backend',
-    title: $localize`LLM Backend`,
-    type: ConfigOptionType.Select,
-    choices: mapToItems(LLMBackendConfig),
-    config_key: 'PAPERLESS_AI_LLM_BACKEND',
-    category: ConfigCategory.AI,
-  },
-  {
-    key: 'llm_model',
-    title: $localize`LLM Model`,
-    type: ConfigOptionType.String,
-    config_key: 'PAPERLESS_AI_LLM_MODEL',
-    category: ConfigCategory.AI,
-  },
-  {
-    key: 'llm_api_key',
-    title: $localize`LLM API Key`,
-    type: ConfigOptionType.Password,
-    config_key: 'PAPERLESS_AI_LLM_API_KEY',
-    category: ConfigCategory.AI,
-  },
-  {
-    key: 'llm_endpoint',
-    title: $localize`LLM Endpoint`,
-    type: ConfigOptionType.String,
-    config_key: 'PAPERLESS_AI_LLM_ENDPOINT',
-    category: ConfigCategory.AI,
-  },
 ]
 
 export interface PaperlessConfig extends ObjectWithId {
@@ -352,11 +287,4 @@ export interface PaperlessConfig extends ObjectWithId {
   barcode_max_pages: number
   barcode_enable_tag: boolean
   barcode_tag_mapping: object
-  ai_enabled: boolean
-  llm_embedding_backend: string
-  llm_embedding_model: string
-  llm_backend: string
-  llm_model: string
-  llm_api_key: string
-  llm_endpoint: string
 }

src-ui/src/app/data/paperless-task.ts

@@ -11,7 +11,6 @@ export enum PaperlessTaskName {
   TrainClassifier = 'train_classifier',
   SanityCheck = 'check_sanity',
   IndexOptimize = 'index_optimize',
-  LLMIndexUpdate = 'llmindex_update',
 }
 
 export enum PaperlessTaskStatus {

src-ui/src/app/data/system-status.ts

@@ -7,7 +7,6 @@ export enum SystemStatusItemStatus {
   OK = 'OK',
   ERROR = 'ERROR',
   WARNING = 'WARNING',
-  DISABLED = 'DISABLED',
 }
 
 export interface SystemStatus {
@@ -44,9 +43,6 @@ export interface SystemStatus {
     sanity_check_status: SystemStatusItemStatus
     sanity_check_last_run: string // ISO date string
     sanity_check_error: string
-    llmindex_status: SystemStatusItemStatus
-    llmindex_last_modified: string // ISO date string
-    llmindex_error: string
   }
   websocket_connected?: SystemStatusItemStatus // added client-side
 }

src-ui/src/app/data/ui-settings.ts

@@ -76,7 +76,6 @@ export const SETTINGS_KEYS = {
   GMAIL_OAUTH_URL: 'gmail_oauth_url',
   OUTLOOK_OAUTH_URL: 'outlook_oauth_url',
   EMAIL_ENABLED: 'email_enabled',
-  AI_ENABLED: 'ai_enabled',
 }
 
 export const SETTINGS: UiSetting[] = [
@@ -290,9 +289,4 @@ export const SETTINGS: UiSetting[] = [
     type: 'string',
     default: 'page-width', // ZoomSetting from 'document-detail.component'
   },
-  {
-    key: SETTINGS_KEYS.AI_ENABLED,
-    type: 'boolean',
-    default: false,
-  },
 ]

src-ui/src/app/data/workflow-action.ts

@@ -5,6 +5,7 @@ export enum WorkflowActionType {
   Removal = 2,
   Email = 3,
   Webhook = 4,
+  PasswordRemoval = 5,
 }
 
 export interface WorkflowActionEmail extends ObjectWithId {
@@ -97,4 +98,6 @@ export interface WorkflowAction extends ObjectWithId {
   email?: WorkflowActionEmail
 
   webhook?: WorkflowActionWebhook
+
+  passwords?: string
 }

src-ui/src/app/interceptors/csrf.interceptor.ts

@@ -4,15 +4,15 @@ import {
   HttpInterceptor,
   HttpRequest,
 } from '@angular/common/http'
-import { inject, Injectable } from '@angular/core'
+import { Injectable, inject } from '@angular/core'
 import { Meta } from '@angular/platform-browser'
 import { CookieService } from 'ngx-cookie-service'
 import { Observable } from 'rxjs'
 
 @Injectable()
 export class CsrfInterceptor implements HttpInterceptor {
-  private cookieService: CookieService = inject(CookieService)
-  private meta: Meta = inject(Meta)
+  private cookieService = inject(CookieService)
+  private meta = inject(Meta)
 
   intercept(
     request: HttpRequest<unknown>,

src-ui/src/app/services/chat.service.spec.ts

@@ -1,58 +0,0 @@
-import {
-  HttpEventType,
-  provideHttpClient,
-  withInterceptorsFromDi,
-} from '@angular/common/http'
-import {
-  HttpTestingController,
-  provideHttpClientTesting,
-} from '@angular/common/http/testing'
-import { TestBed } from '@angular/core/testing'
-import { environment } from 'src/environments/environment'
-import { ChatService } from './chat.service'
-
-describe('ChatService', () => {
-  let service: ChatService
-  let httpMock: HttpTestingController
-
-  beforeEach(() => {
-    TestBed.configureTestingModule({
-      imports: [],
-      providers: [
-        ChatService,
-        provideHttpClient(withInterceptorsFromDi()),
-        provideHttpClientTesting(),
-      ],
-    })
-    service = TestBed.inject(ChatService)
-    httpMock = TestBed.inject(HttpTestingController)
-  })
-
-  afterEach(() => {
-    httpMock.verify()
-  })
-
-  it('should stream chat messages', (done) => {
-    const documentId = 1
-    const prompt = 'Hello, world!'
-    const mockResponse = 'Partial response text'
-    const apiUrl = `${environment.apiBaseUrl}documents/chat/`
-
-    service.streamChat(documentId, prompt).subscribe((chunk) => {
-      expect(chunk).toBe(mockResponse)
-      done()
-    })
-
-    const req = httpMock.expectOne(apiUrl)
-    expect(req.request.method).toBe('POST')
-    expect(req.request.body).toEqual({
-      document_id: documentId,
-      q: prompt,
-    })
-
-    req.event({
-      type: HttpEventType.DownloadProgress,
-      partialText: mockResponse,
-    } as any)
-  })
-})

src-ui/src/app/services/chat.service.ts

@@ -1,46 +0,0 @@
-import {
-  HttpClient,
-  HttpDownloadProgressEvent,
-  HttpEventType,
-} from '@angular/common/http'
-import { inject, Injectable } from '@angular/core'
-import { filter, map, Observable } from 'rxjs'
-import { environment } from 'src/environments/environment'
-
-export interface ChatMessage {
-  role: 'user' | 'assistant'
-  content: string
-  isStreaming?: boolean
-}
-
-@Injectable({
-  providedIn: 'root',
-})
-export class ChatService {
-  private http: HttpClient = inject(HttpClient)
-
-  streamChat(documentId: number, prompt: string): Observable<string> {
-    return this.http
-      .post(
-        `${environment.apiBaseUrl}documents/chat/`,
-        {
-          document_id: documentId,
-          q: prompt,
-        },
-        {
-          observe: 'events',
-          reportProgress: true,
-          responseType: 'text',
-          withCredentials: true,
-        }
-      )
-      .pipe(
-        map((event) => {
-          if (event.type === HttpEventType.DownloadProgress) {
-            return (event as HttpDownloadProgressEvent).partialText!
-          }
-        }),
-        filter((chunk) => !!chunk)
-      )
-  }
-}

src-ui/src/environments/environment.prod.ts

@@ -6,7 +6,7 @@ export const environment = {
   apiVersion: '9', // match src/paperless/settings.py
   appTitle: 'Paperless-ngx',
   tag: 'prod',
-  version: '2.20.5',
+  version: '2.20.3',
   webSocketHost: window.location.host,
   webSocketProtocol: window.location.protocol == 'https:' ? 'wss:' : 'ws:',
   webSocketBaseUrl: base_url.pathname + 'ws/',

src-ui/src/main.ts

@@ -10,7 +10,6 @@ import { DatePipe, registerLocaleData } from '@angular/common'
 import {
   HTTP_INTERCEPTORS,
   provideHttpClient,
-  withFetch,
   withInterceptorsFromDi,
 } from '@angular/common/http'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
@@ -50,7 +49,6 @@ import {
   caretDown,
   caretUp,
   chatLeftText,
-  chatSquareDots,
   check,
   check2All,
   checkAll,
@@ -126,7 +124,6 @@ import {
   sliders2Vertical,
   sortAlphaDown,
   sortAlphaUpAlt,
-  stars,
   tag,
   tagFill,
   tags,
@@ -269,7 +266,6 @@ const icons = {
   caretDown,
   caretUp,
   chatLeftText,
-  chatSquareDots,
   check,
   check2All,
   checkAll,
@@ -345,7 +341,6 @@ const icons = {
   sliders2Vertical,
   sortAlphaDown,
   sortAlphaUpAlt,
-  stars,
   tagFill,
   tag,
   tags,
@@ -412,6 +407,6 @@ bootstrapApplication(AppComponent, {
     CorrespondentNamePipe,
     DocumentTypeNamePipe,
     StoragePathNamePipe,
-    provideHttpClient(withInterceptorsFromDi(), withFetch()),
+    provideHttpClient(withInterceptorsFromDi()),
   ],
 }).catch((err) => console.error(err))

src/documents/apps.py

@@ -11,7 +11,6 @@ class DocumentsConfig(AppConfig):
         from documents.signals import document_consumption_finished
         from documents.signals import document_updated
         from documents.signals.handlers import add_inbox_tags
-        from documents.signals.handlers import add_or_update_document_in_llm_index
         from documents.signals.handlers import add_to_index
         from documents.signals.handlers import run_workflows_added
         from documents.signals.handlers import run_workflows_updated
@@ -27,7 +26,6 @@ class DocumentsConfig(AppConfig):
         document_consumption_finished.connect(set_storage_path)
         document_consumption_finished.connect(add_to_index)
         document_consumption_finished.connect(run_workflows_added)
-        document_consumption_finished.connect(add_or_update_document_in_llm_index)
         document_updated.connect(run_workflows_updated)
 
         import documents.schema  # noqa: F401

src/documents/caching.py

@@ -41,7 +41,6 @@ class SuggestionCacheData:
 CLASSIFIER_VERSION_KEY: Final[str] = "classifier_version"
 CLASSIFIER_HASH_KEY: Final[str] = "classifier_hash"
 CLASSIFIER_MODIFIED_KEY: Final[str] = "classifier_modified"
-LLM_CACHE_CLASSIFIER_VERSION: Final[int] = 1000  # Marker distinguishing LLM suggestions
 
 CACHE_1_MINUTE: Final[int] = 60
 CACHE_5_MINUTES: Final[int] = 5 * CACHE_1_MINUTE
@@ -197,54 +196,6 @@ def refresh_suggestions_cache(
     cache.touch(doc_key, timeout)
 
 
-def get_llm_suggestion_cache(
-    document_id: int,
-    backend: str,
-) -> SuggestionCacheData | None:
-    doc_key = get_suggestion_cache_key(document_id)
-    data: SuggestionCacheData = cache.get(doc_key)
-
-    if data and data.classifier_hash == backend:
-        return data
-
-    return None
-
-
-def set_llm_suggestions_cache(
-    document_id: int,
-    suggestions: dict,
-    *,
-    backend: str,
-    timeout: int = CACHE_50_MINUTES,
-) -> None:
-    """
-    Cache LLM-generated suggestions using a backend-specific identifier (e.g. 'openai:gpt-4').
-    """
-    doc_key = get_suggestion_cache_key(document_id)
-    cache.set(
-        doc_key,
-        SuggestionCacheData(
-            classifier_version=LLM_CACHE_CLASSIFIER_VERSION,
-            classifier_hash=backend,
-            suggestions=suggestions,
-        ),
-        timeout,
-    )
-
-
-def invalidate_llm_suggestions_cache(
-    document_id: int,
-) -> None:
-    """
-    Invalidate the LLM suggestions cache for a specific document and backend.
-    """
-    doc_key = get_suggestion_cache_key(document_id)
-    data: SuggestionCacheData = cache.get(doc_key)
-
-    if data:
-        cache.delete(doc_key)
-
-
 def get_metadata_cache_key(document_id: int) -> str:
     """
     Returns the basic key for a document's metadata

src/documents/management/commands/document_consumer.py

@@ -1,343 +1,135 @@
-"""
-Document consumer management command.
-
-Watches a consumption directory for new documents and queues them for processing.
-Uses watchfiles for efficient file system monitoring with support for both
-native OS notifications and polling fallback.
-"""
-
-from __future__ import annotations
-
 import logging
-from dataclasses import dataclass
+import os
+from concurrent.futures import ThreadPoolExecutor
+from fnmatch import filter
 from pathlib import Path
+from pathlib import PurePath
 from threading import Event
 from time import monotonic
-from typing import TYPE_CHECKING
+from time import sleep
 from typing import Final
 
 from django import db
 from django.conf import settings
 from django.core.management.base import BaseCommand
 from django.core.management.base import CommandError
-from watchfiles import Change
-from watchfiles import DefaultFilter
-from watchfiles import watch
+from watchdog.events import FileSystemEventHandler
+from watchdog.observers.polling import PollingObserver
 
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
 from documents.models import Tag
-from documents.parsers import get_supported_file_extensions
+from documents.parsers import is_file_ext_supported
 from documents.tasks import consume_file
 
-if TYPE_CHECKING:
-    from collections.abc import Iterator
-
+try:
+    from inotifyrecursive import INotify
+    from inotifyrecursive import flags
+except ImportError:  # pragma: no cover
+    INotify = flags = None
 
 logger = logging.getLogger("paperless.management.consumer")
 
 
-@dataclass
-class TrackedFile:
-    """Represents a file being tracked for stability."""
-
-    path: Path
-    last_event_time: float
-    last_mtime: float | None = None
-    last_size: int | None = None
-
-    def update_stats(self) -> bool:
-        """
-        Update file stats. Returns True if file exists and stats were updated.
-        """
-        try:
-            stat = self.path.stat()
-            self.last_mtime = stat.st_mtime
-            self.last_size = stat.st_size
-            return True
-        except OSError:
-            return False
-
-    def is_unchanged(self) -> bool:
-        """
-        Check if file stats match the previously recorded values.
-        Returns False if file doesn't exist or stats changed.
-        """
-        try:
-            stat = self.path.stat()
-            return stat.st_mtime == self.last_mtime and stat.st_size == self.last_size
-        except OSError:
-            return False
-
-
-class FileStabilityTracker:
+def _tags_from_path(filepath: Path) -> list[int]:
     """
-    Tracks file events and determines when files are stable for consumption.
-
-    A file is considered stable when:
-    1. No new events have been received for it within the stability delay
-    2. Its size and modification time haven't changed
-    3. It still exists as a regular file
-
-    This handles various edge cases:
-    - Network copies that write in chunks
-    - Scanners that open/close files multiple times
-    - Temporary files that get renamed
-    - Files that are deleted before becoming stable
-    """
-
-    def __init__(self, stability_delay: float = 1.0) -> None:
-        """
-        Initialize the tracker.
-
-        Args:
-            stability_delay: Time in seconds a file must remain unchanged
-                           before being considered stable.
-        """
-        self.stability_delay = stability_delay
-        self._tracked: dict[Path, TrackedFile] = {}
-
-    def track(self, path: Path, change: Change) -> None:
-        """
-        Register a file event.
-
-        Args:
-            path: The file path that changed.
-            change: The type of change (added, modified, deleted).
-        """
-        path = path.resolve()
-
-        match change:
-            case Change.deleted:
-                self._tracked.pop(path, None)
-                logger.debug(f"Stopped tracking deleted file: {path}")
-            case Change.added | Change.modified:
-                current_time = monotonic()
-                if path in self._tracked:
-                    tracked = self._tracked[path]
-                    tracked.last_event_time = current_time
-                    tracked.update_stats()
-                    logger.debug(f"Updated tracking for: {path}")
-                else:
-                    tracked = TrackedFile(path=path, last_event_time=current_time)
-                    if tracked.update_stats():
-                        self._tracked[path] = tracked
-                        logger.debug(f"Started tracking: {path}")
-                    else:
-                        logger.debug(f"Could not stat file, not tracking: {path}")
-
-    def get_stable_files(self) -> Iterator[Path]:
-        """
-        Yield files that have been stable for the configured delay.
-
-        Files are removed from tracking once yielded or determined to be invalid.
-        """
-        current_time = monotonic()
-        to_remove: list[Path] = []
-        to_yield: list[Path] = []
-
-        for path, tracked in self._tracked.items():
-            time_since_event = current_time - tracked.last_event_time
-
-            if time_since_event < self.stability_delay:
-                continue
-
-            # File has waited long enough, verify it's unchanged
-            if not tracked.is_unchanged():
-                # Stats changed or file gone - update and wait again
-                if tracked.update_stats():
-                    tracked.last_event_time = current_time
-                    logger.debug(f"File changed during stability check: {path}")
-                else:
-                    # File no longer exists, remove from tracking
-                    to_remove.append(path)
-                    logger.debug(f"File disappeared during stability check: {path}")
-                continue
-
-            # File is stable, we can return it
-            to_yield.append(path)
-            logger.info(f"File is stable: {path}")
-
-        # Remove files that are no longer valid
-        for path in to_remove:
-            self._tracked.pop(path, None)
-
-        # Remove and yield stable files
-        for path in to_yield:
-            self._tracked.pop(path, None)
-            yield path
-
-    def has_pending_files(self) -> bool:
-        """Check if there are files waiting for stability check."""
-        return len(self._tracked) > 0
-
-    @property
-    def pending_count(self) -> int:
-        """Number of files being tracked."""
-        return len(self._tracked)
-
-
-class ConsumerFilter(DefaultFilter):
-    """
-    Filter for watchfiles that accepts only supported document types
-    and ignores system files/directories.
-
-    Extends DefaultFilter leveraging its built-in filtering:
-    - `ignore_dirs`: Directory names to ignore (and all their contents)
-    - `ignore_entity_patterns`: Regex patterns matched against filename/dirname only
-
-    We add custom logic for file extension filtering (only accept supported
-    document types), which the library doesn't provide.
-    """
-
-    # Regex patterns for files to always ignore (matched against filename only)
-    # These are passed to DefaultFilter.ignore_entity_patterns
-    DEFAULT_IGNORE_PATTERNS: Final[tuple[str, ...]] = (
-        r"^\.DS_Store$",
-        r"^\.DS_STORE$",
-        r"^\._.*",
-        r"^desktop\.ini$",
-        r"^Thumbs\.db$",
-    )
-
-    # Directories to always ignore (passed to DefaultFilter.ignore_dirs)
-    # These are matched by directory name, not full path
-    DEFAULT_IGNORE_DIRS: Final[tuple[str, ...]] = (
-        ".stfolder",  # Syncthing
-        ".stversions",  # Syncthing
-        ".localized",  # macOS
-        "@eaDir",  # Synology NAS
-        ".Spotlight-V100",  # macOS
-        ".Trashes",  # macOS
-        "__MACOSX",  # macOS archive artifacts
-    )
-
-    def __init__(
-        self,
-        *,
-        supported_extensions: frozenset[str] | None = None,
-        ignore_patterns: list[str] | None = None,
-        ignore_dirs: list[str] | None = None,
-    ) -> None:
-        """
-        Initialize the consumer filter.
-
-        Args:
-            supported_extensions: Set of file extensions to accept (e.g., {".pdf", ".png"}).
-                If None, uses get_supported_file_extensions().
-            ignore_patterns: Additional regex patterns to ignore (matched against filename).
-            ignore_dirs: Additional directory names to ignore (merged with defaults).
-        """
-        # Get supported extensions
-        if supported_extensions is None:
-            supported_extensions = frozenset(get_supported_file_extensions())
-        self._supported_extensions = supported_extensions
-
-        # Combine default and user patterns
-        all_patterns: list[str] = list(self.DEFAULT_IGNORE_PATTERNS)
-        if ignore_patterns:
-            all_patterns.extend(ignore_patterns)
-
-        # Combine default and user ignore_dirs
-        all_ignore_dirs: list[str] = list(self.DEFAULT_IGNORE_DIRS)
-        if ignore_dirs:
-            all_ignore_dirs.extend(ignore_dirs)
-
-        # Let DefaultFilter handle all the pattern and directory filtering
-        super().__init__(
-            ignore_dirs=tuple(all_ignore_dirs),
-            ignore_entity_patterns=tuple(all_patterns),
-            ignore_paths=(),
-        )
-
-    def __call__(self, change: Change, path: str) -> bool:
-        """
-        Filter function for watchfiles.
-
-        Returns True if the path should be watched, False to ignore.
-
-        The parent DefaultFilter handles:
-        - Hidden files/directories (starting with .)
-        - Directories in ignore_dirs
-        - Files/directories matching ignore_entity_patterns
-
-        We additionally filter files by extension.
-        """
-        # Let parent filter handle directory ignoring and pattern matching
-        if not super().__call__(change, path):
-            return False
-
-        path_obj = Path(path)
-
-        # For directories, parent filter already handled everything
-        if path_obj.is_dir():
-            return True
-
-        # For files, check extension
-        return self._has_supported_extension(path_obj)
-
-    def _has_supported_extension(self, path: Path) -> bool:
-        """Check if the file has a supported extension."""
-        suffix = path.suffix.lower()
-        return suffix in self._supported_extensions
-
-
-def _tags_from_path(filepath: Path, consumption_dir: Path) -> list[int]:
-    """
-    Walk up the directory tree from filepath to consumption_dir
+    Walk up the directory tree from filepath to CONSUMPTION_DIR
     and get or create Tag IDs for every directory.
 
-    Returns list of Tag primary keys.
+    Returns set of Tag models
     """
     db.close_old_connections()
-    tag_ids: set[int] = set()
-    path_parts = filepath.relative_to(consumption_dir).parent.parts
-
+    tag_ids = set()
+    path_parts = filepath.relative_to(settings.CONSUMPTION_DIR).parent.parts
     for part in path_parts:
-        tag, _ = Tag.objects.get_or_create(
-            name__iexact=part,
-            defaults={"name": part},
+        tag_ids.add(
+            Tag.objects.get_or_create(name__iexact=part, defaults={"name": part})[0].pk,
         )
-        tag_ids.add(tag.pk)
 
     return list(tag_ids)
 
 
-def _consume_file(
-    filepath: Path,
-    consumption_dir: Path,
-    *,
-    subdirs_as_tags: bool,
-) -> None:
+def _is_ignored(filepath: Path) -> bool:
     """
-    Queue a file for consumption.
+    Checks if the given file should be ignored, based on configured
+    patterns.
 
-    Args:
-        filepath: Path to the file to consume.
-        consumption_dir: Base consumption directory.
-        subdirs_as_tags: Whether to create tags from subdirectory names.
+    Returns True if the file is ignored, False otherwise
     """
-    # Verify file still exists and is accessible
+    # Trim out the consume directory, leaving only filename and it's
+    # path relative to the consume directory
+    filepath_relative = PurePath(filepath).relative_to(settings.CONSUMPTION_DIR)
+
+    # March through the components of the path, including directories and the filename
+    # looking for anything matching
+    # foo/bar/baz/file.pdf -> (foo, bar, baz, file.pdf)
+    parts = []
+    for part in filepath_relative.parts:
+        # If the part is not the name (ie, it's a dir)
+        # Need to append the trailing slash or fnmatch doesn't match
+        # fnmatch("dir", "dir/*") == False
+        # fnmatch("dir/", "dir/*") == True
+        if part != filepath_relative.name:
+            part = part + "/"
+        parts.append(part)
+
+    for pattern in settings.CONSUMER_IGNORE_PATTERNS:
+        if len(filter(parts, pattern)):
+            return True
+
+    return False
+
+
+def _consume(filepath: Path) -> None:
+    # Check permissions early
     try:
-        if not filepath.is_file():
-            logger.debug(f"Not consuming {filepath}: not a file or doesn't exist")
-            return
-    except OSError as e:
-        logger.warning(f"Not consuming {filepath}: {e}")
+        filepath.stat()
+    except (PermissionError, OSError):
+        logger.warning(f"Not consuming file {filepath}: Permission denied.")
         return
 
-    # Get tags from path if configured
-    tag_ids: list[int] | None = None
-    if subdirs_as_tags:
-        try:
-            tag_ids = _tags_from_path(filepath, consumption_dir)
-        except Exception:
-            logger.exception(f"Error creating tags from path for {filepath}")
+    if filepath.is_dir() or _is_ignored(filepath):
+        return
 
-    # Queue for consumption
+    if not filepath.is_file():
+        logger.debug(f"Not consuming file {filepath}: File has moved.")
+        return
+
+    if not is_file_ext_supported(filepath.suffix):
+        logger.warning(f"Not consuming file {filepath}: Unknown file extension.")
+        return
+
+    # Total wait time: up to 500ms
+    os_error_retry_count: Final[int] = 50
+    os_error_retry_wait: Final[float] = 0.01
+
+    read_try_count = 0
+    file_open_ok = False
+    os_error_str = None
+
+    while (read_try_count < os_error_retry_count) and not file_open_ok:
+        try:
+            with filepath.open("rb"):
+                file_open_ok = True
+        except OSError as e:
+            read_try_count += 1
+            os_error_str = str(e)
+            sleep(os_error_retry_wait)
+
+    if read_try_count >= os_error_retry_count:
+        logger.warning(f"Not consuming file {filepath}: OS reports {os_error_str}")
+        return
+
+    tag_ids = None
     try:
-        logger.info(f"Adding {filepath} to the task queue")
+        if settings.CONSUMER_SUBDIRS_AS_TAGS:
+            tag_ids = _tags_from_path(filepath)
+    except Exception:
+        logger.exception("Error creating tags from path")
+
+    try:
+        logger.info(f"Adding {filepath} to the task queue.")
         consume_file.delay(
             ConsumableDocument(
                 source=DocumentSource.ConsumeFolder,
@@ -346,209 +138,228 @@ def _consume_file(
             DocumentMetadataOverrides(tag_ids=tag_ids),
         )
     except Exception:
-        logger.exception(f"Error while queuing document {filepath}")
+        # Catch all so that the consumer won't crash.
+        # This is also what the test case is listening for to check for
+        # errors.
+        logger.exception("Error while consuming document")
+
+
+def _consume_wait_unmodified(file: Path) -> None:
+    """
+    Waits for the given file to appear unmodified based on file size
+    and modification time.  Will wait a configured number of seconds
+    and retry a configured number of times before either consuming or
+    giving up
+    """
+    if _is_ignored(file):
+        return
+
+    logger.debug(f"Waiting for file {file} to remain unmodified")
+    mtime = -1
+    size = -1
+    current_try = 0
+    while current_try < settings.CONSUMER_POLLING_RETRY_COUNT:
+        try:
+            stat_data = file.stat()
+            new_mtime = stat_data.st_mtime
+            new_size = stat_data.st_size
+        except FileNotFoundError:
+            logger.debug(
+                f"File {file} moved while waiting for it to remain unmodified.",
+            )
+            return
+        if new_mtime == mtime and new_size == size:
+            _consume(file)
+            return
+        mtime = new_mtime
+        size = new_size
+        sleep(settings.CONSUMER_POLLING_DELAY)
+        current_try += 1
+
+    logger.error(f"Timeout while waiting on file {file} to remain unmodified.")
+
+
+class Handler(FileSystemEventHandler):
+    def __init__(self, pool: ThreadPoolExecutor) -> None:
+        super().__init__()
+        self._pool = pool
+
+    def on_created(self, event):
+        self._pool.submit(_consume_wait_unmodified, Path(event.src_path))
+
+    def on_moved(self, event):
+        self._pool.submit(_consume_wait_unmodified, Path(event.dest_path))
 
 
 class Command(BaseCommand):
     """
-    Watch a consumption directory and queue new documents for processing.
-
-    Uses watchfiles for efficient file system monitoring. Supports both
-    native OS notifications (inotify on Linux, FSEvents on macOS) and
-    polling for network filesystems.
+    On every iteration of an infinite loop, consume what we can from the
+    consumption directory.
     """
 
-    help = "Watch the consumption directory for new documents"
-
-    # For testing - allows tests to stop the consumer
-    stop_flag: Event = Event()
-
-    # Testing timeout in seconds
+    # This is here primarily for the tests and is irrelevant in production.
+    stop_flag = Event()
+    # Also only for testing, configures in one place the timeout used before checking
+    # the stop flag
     testing_timeout_s: Final[float] = 0.5
+    testing_timeout_ms: Final[float] = testing_timeout_s * 1000.0
 
-    def add_arguments(self, parser) -> None:
+    def add_arguments(self, parser):
         parser.add_argument(
             "directory",
-            default=None,
+            default=settings.CONSUMPTION_DIR,
             nargs="?",
-            help="The consumption directory (defaults to CONSUMPTION_DIR setting)",
-        )
-        parser.add_argument(
-            "--oneshot",
-            action="store_true",
-            help="Process existing files and exit without watching",
+            help="The consumption directory.",
         )
+        parser.add_argument("--oneshot", action="store_true", help="Run only once.")
+
+        # Only use during unit testing, will configure a timeout
+        # Leaving it unset or false and the consumer will exit when it
+        # receives SIGINT
         parser.add_argument(
             "--testing",
             action="store_true",
-            help="Enable testing mode with shorter timeouts",
+            help="Flag used only for unit testing",
             default=False,
         )
 
-    def handle(self, *args, **options) -> None:
-        # Resolve consumption directory
-        directory = options.get("directory")
+    def handle(self, *args, **options):
+        directory = options["directory"]
+        recursive = settings.CONSUMER_RECURSIVE
+
         if not directory:
-            directory = getattr(settings, "CONSUMPTION_DIR", None)
-        if not directory:
-            raise CommandError("CONSUMPTION_DIR is not configured")
+            raise CommandError("CONSUMPTION_DIR does not appear to be set.")
 
         directory = Path(directory).resolve()
 
-        if not directory.exists():
-            raise CommandError(f"Consumption directory does not exist: {directory}")
-
         if not directory.is_dir():
-            raise CommandError(f"Consumption path is not a directory: {directory}")
+            raise CommandError(f"Consumption directory {directory} does not exist")
 
-        # Ensure scratch directory exists
+        # Consumer will need this
         settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
 
-        # Get settings
-        recursive: bool = settings.CONSUMER_RECURSIVE
-        subdirs_as_tags: bool = settings.CONSUMER_SUBDIRS_AS_TAGS
-        polling_interval: float = settings.CONSUMER_POLLING_INTERVAL
-        stability_delay: float = settings.CONSUMER_STABILITY_DELAY
-        ignore_patterns: list[str] = settings.CONSUMER_IGNORE_PATTERNS
-        ignore_dirs: list[str] = settings.CONSUMER_IGNORE_DIRS
-        is_testing: bool = options.get("testing", False)
-        is_oneshot: bool = options.get("oneshot", False)
+        if recursive:
+            for dirpath, _, filenames in os.walk(directory):
+                for filename in filenames:
+                    filepath = Path(dirpath) / filename
+                    _consume(filepath)
+        else:
+            for filepath in directory.iterdir():
+                _consume(filepath)
 
-        # Create filter
-        consumer_filter = ConsumerFilter(
-            ignore_patterns=ignore_patterns,
-            ignore_dirs=ignore_dirs,
-        )
-
-        # Process existing files
-        self._process_existing_files(
-            directory=directory,
-            recursive=recursive,
-            subdirs_as_tags=subdirs_as_tags,
-            consumer_filter=consumer_filter,
-        )
-
-        if is_oneshot:
-            logger.info("Oneshot mode: processed existing files, exiting")
+        if options["oneshot"]:
             return
 
-        # Start watching
-        self._watch_directory(
-            directory=directory,
-            recursive=recursive,
-            subdirs_as_tags=subdirs_as_tags,
-            consumer_filter=consumer_filter,
-            polling_interval=polling_interval,
-            stability_delay=stability_delay,
-            is_testing=is_testing,
-        )
-
-        logger.debug("Consumer exiting")
-
-    def _process_existing_files(
-        self,
-        *,
-        directory: Path,
-        recursive: bool,
-        subdirs_as_tags: bool,
-        consumer_filter: ConsumerFilter,
-    ) -> None:
-        """Process any existing files in the consumption directory."""
-        logger.info(f"Processing existing files in {directory}")
-
-        glob_pattern = "**/*" if recursive else "*"
-
-        for filepath in directory.glob(glob_pattern):
-            # Use filter to check if file should be processed
-            if not filepath.is_file():
-                continue
-
-            if not consumer_filter(Change.added, str(filepath)):
-                continue
-
-            _consume_file(
-                filepath=filepath,
-                consumption_dir=directory,
-                subdirs_as_tags=subdirs_as_tags,
-            )
-
-    def _watch_directory(
-        self,
-        *,
-        directory: Path,
-        recursive: bool,
-        subdirs_as_tags: bool,
-        consumer_filter: ConsumerFilter,
-        polling_interval: float,
-        stability_delay: float,
-        is_testing: bool,
-    ) -> None:
-        """Watch directory for changes and process stable files."""
-        use_polling = polling_interval > 0
-        poll_delay_ms = int(polling_interval * 1000) if use_polling else 0
-
-        if use_polling:
-            logger.info(
-                f"Watching {directory} using polling (interval: {polling_interval}s)",
-            )
+        if settings.CONSUMER_POLLING == 0 and INotify:
+            self.handle_inotify(directory, recursive, is_testing=options["testing"])
         else:
-            logger.info(f"Watching {directory} using native file system events")
+            if INotify is None and settings.CONSUMER_POLLING == 0:  # pragma: no cover
+                logger.warning("Using polling as INotify import failed")
+            self.handle_polling(directory, recursive, is_testing=options["testing"])
 
-        # Create stability tracker
-        tracker = FileStabilityTracker(stability_delay=stability_delay)
+        logger.debug("Consumer exiting.")
 
-        # Calculate timeouts
-        stability_timeout_ms = int(stability_delay * 1000)
-        testing_timeout_ms = int(self.testing_timeout_s * 1000)
+    def handle_polling(self, directory, recursive, *, is_testing: bool):
+        logger.info(f"Polling directory for changes: {directory}")
 
-        # Start with no timeout (wait indefinitely for first event)
-        # unless in testing mode
-        timeout_ms = testing_timeout_ms if is_testing else 0
+        timeout = None
+        if is_testing:
+            timeout = self.testing_timeout_s
+            logger.debug(f"Configuring timeout to {timeout}s")
 
-        self.stop_flag.clear()
+        polling_interval = settings.CONSUMER_POLLING
+        if polling_interval == 0:  # pragma: no cover
+            # Only happens if INotify failed to import
+            logger.warning("Using polling of 10s, consider setting this")
+            polling_interval = 10
 
-        while not self.stop_flag.is_set():
+        with ThreadPoolExecutor(max_workers=4) as pool:
+            observer = PollingObserver(timeout=polling_interval)
+            observer.schedule(Handler(pool), directory, recursive=recursive)
+            observer.start()
             try:
-                for changes in watch(
-                    directory,
-                    watch_filter=consumer_filter,
-                    rust_timeout=timeout_ms,
-                    yield_on_timeout=True,
-                    force_polling=use_polling,
-                    poll_delay_ms=poll_delay_ms,
-                    recursive=recursive,
-                    stop_event=self.stop_flag,
-                ):
-                    # Process each change
-                    for change_type, path in changes:
-                        path = Path(path).resolve()
-                        if not path.is_file():
+                while observer.is_alive():
+                    observer.join(timeout)
+                    if self.stop_flag.is_set():
+                        observer.stop()
+            except KeyboardInterrupt:
+                observer.stop()
+            observer.join()
+
+    def handle_inotify(self, directory, recursive, *, is_testing: bool):
+        logger.info(f"Using inotify to watch directory for changes: {directory}")
+
+        timeout_ms = None
+        if is_testing:
+            timeout_ms = self.testing_timeout_ms
+            logger.debug(f"Configuring timeout to {timeout_ms}ms")
+
+        inotify = INotify()
+        inotify_flags = flags.CLOSE_WRITE | flags.MOVED_TO | flags.MODIFY
+        if recursive:
+            inotify.add_watch_recursive(directory, inotify_flags)
+        else:
+            inotify.add_watch(directory, inotify_flags)
+
+        inotify_debounce_secs: Final[float] = settings.CONSUMER_INOTIFY_DELAY
+        inotify_debounce_ms: Final[int] = inotify_debounce_secs * 1000
+
+        finished = False
+
+        notified_files = {}
+
+        try:
+            while not finished:
+                try:
+                    for event in inotify.read(timeout=timeout_ms):
+                        path = inotify.get_path(event.wd) if recursive else directory
+                        filepath = Path(path) / event.name
+                        if flags.MODIFY in flags.from_mask(event.mask):
+                            notified_files.pop(filepath, None)
+                        else:
+                            notified_files[filepath] = monotonic()
+
+                    # Check the files against the timeout
+                    still_waiting = {}
+                    # last_event_time is time of the last inotify event for this file
+                    for filepath, last_event_time in notified_files.items():
+                        # Current time - last time over the configured timeout
+                        waited_long_enough = (
+                            monotonic() - last_event_time
+                        ) > inotify_debounce_secs
+
+                        # Also make sure the file exists still, some scanners might write a
+                        # temporary file first
+                        try:
+                            file_still_exists = filepath.exists() and filepath.is_file()
+                        except (PermissionError, OSError):  # pragma: no cover
+                            # If we can't check, let it fail in the _consume function
+                            file_still_exists = True
                             continue
-                        logger.debug(f"Event: {change_type.name} for {path}")
-                        tracker.track(path, change_type)
 
-                    # Check for stable files
-                    for stable_path in tracker.get_stable_files():
-                        _consume_file(
-                            filepath=stable_path,
-                            consumption_dir=directory,
-                            subdirs_as_tags=subdirs_as_tags,
-                        )
+                        if waited_long_enough and file_still_exists:
+                            _consume(filepath)
+                        elif file_still_exists:
+                            still_waiting[filepath] = last_event_time
 
-                    # Exit watch loop to reconfigure timeout
-                    break
+                    # These files are still waiting to hit the timeout
+                    notified_files = still_waiting
 
-                # Determine next timeout
-                if tracker.has_pending_files():
-                    # Check pending files at stability interval
-                    timeout_ms = stability_timeout_ms
-                elif is_testing:
-                    # In testing, use short timeout to check stop flag
-                    timeout_ms = testing_timeout_ms
-                else:  # pragma: nocover
-                    # No pending files, wait indefinitely
-                    timeout_ms = 0
+                    # If files are waiting, need to exit read() to check them
+                    # Otherwise, go back to infinite sleep time, but only if not testing
+                    if len(notified_files) > 0:
+                        timeout_ms = inotify_debounce_ms
+                    elif is_testing:
+                        timeout_ms = self.testing_timeout_ms
+                    else:
+                        timeout_ms = None
 
-            except KeyboardInterrupt:  # pragma: nocover
-                logger.info("Received interrupt, stopping consumer")
-                self.stop_flag.set()
+                    if self.stop_flag.is_set():
+                        logger.debug("Finishing because event is set")
+                        finished = True
+
+                except KeyboardInterrupt:
+                    logger.info("Received SIGINT, stopping inotify")
+                    finished = True
+        finally:
+            inotify.close()

src/documents/management/commands/document_llmindex.py

@@ -1,22 +0,0 @@
-from django.core.management import BaseCommand
-from django.db import transaction
-
-from documents.management.commands.mixins import ProgressBarMixin
-from documents.tasks import llmindex_index
-
-
-class Command(ProgressBarMixin, BaseCommand):
-    help = "Manages the LLM-based vector index for Paperless."
-
-    def add_arguments(self, parser):
-        parser.add_argument("command", choices=["rebuild", "update"])
-        self.add_argument_progress_bar_mixin(parser)
-
-    def handle(self, *args, **options):
-        self.handle_progress_bar_mixin(**options)
-        with transaction.atomic():
-            llmindex_index(
-                progress_bar_disable=self.no_progress_bar,
-                rebuild=options["command"] == "rebuild",
-                scheduled=False,
-            )

src/documents/migrations/0002_auto_20151226_1316.py

@@ -0,0 +1,26 @@
+# Generated by Django 1.9 on 2015-12-26 13:16
+
+import django.utils.timezone
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AlterModelOptions(
+            name="document",
+            options={"ordering": ("sender", "title")},
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="created",
+            field=models.DateTimeField(
+                default=django.utils.timezone.now,
+                editable=False,
+            ),
+        ),
+    ]

src/documents/migrations/0003_sender.py

@@ -0,0 +1,70 @@
+# Generated by Django 1.9 on 2016-01-11 12:21
+
+import django.db.models.deletion
+from django.db import migrations
+from django.db import models
+from django.template.defaultfilters import slugify
+
+DOCUMENT_SENDER_MAP = {}
+
+
+def move_sender_strings_to_sender_model(apps, schema_editor):
+    sender_model = apps.get_model("documents", "Sender")
+    document_model = apps.get_model("documents", "Document")
+
+    # Create the sender and log the relationship with the document
+    for document in document_model.objects.all():
+        if document.sender:
+            (
+                DOCUMENT_SENDER_MAP[document.pk],
+                _,
+            ) = sender_model.objects.get_or_create(
+                name=document.sender,
+                defaults={"slug": slugify(document.sender)},
+            )
+
+
+def realign_senders(apps, schema_editor):
+    document_model = apps.get_model("documents", "Document")
+    for pk, sender in DOCUMENT_SENDER_MAP.items():
+        document_model.objects.filter(pk=pk).update(sender=sender)
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0002_auto_20151226_1316"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="Sender",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("name", models.CharField(max_length=128, unique=True)),
+                ("slug", models.SlugField()),
+            ],
+        ),
+        migrations.RunPython(move_sender_strings_to_sender_model),
+        migrations.RemoveField(
+            model_name="document",
+            name="sender",
+        ),
+        migrations.AddField(
+            model_name="document",
+            name="sender",
+            field=models.ForeignKey(
+                blank=True,
+                on_delete=django.db.models.deletion.CASCADE,
+                to="documents.Sender",
+            ),
+        ),
+        migrations.RunPython(realign_senders),
+    ]

src/documents/migrations/0004_auto_20160114_1844.py

@@ -0,0 +1,25 @@
+# Generated by Django 1.9 on 2016-01-14 18:44
+
+import django.db.models.deletion
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0003_sender"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="sender",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="documents",
+                to="documents.Sender",
+            ),
+        ),
+    ]

src/documents/migrations/0004_auto_20160114_1844_squashed_0011_auto_20160303_1929.py

@@ -0,0 +1,178 @@
+# Generated by Django 4.2.13 on 2024-06-28 17:52
+
+import django.db.models.deletion
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    replaces = [
+        ("documents", "0004_auto_20160114_1844"),
+        ("documents", "0005_auto_20160123_0313"),
+        ("documents", "0006_auto_20160123_0430"),
+        ("documents", "0007_auto_20160126_2114"),
+        ("documents", "0008_document_file_type"),
+        ("documents", "0009_auto_20160214_0040"),
+        ("documents", "0010_log"),
+        ("documents", "0011_auto_20160303_1929"),
+    ]
+
+    dependencies = [
+        ("documents", "0003_sender"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="sender",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="documents",
+                to="documents.sender",
+            ),
+        ),
+        migrations.AlterModelOptions(
+            name="sender",
+            options={"ordering": ("name",)},
+        ),
+        migrations.CreateModel(
+            name="Tag",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("name", models.CharField(max_length=128, unique=True)),
+                ("slug", models.SlugField(blank=True)),
+                (
+                    "colour",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (1, "#a6cee3"),
+                            (2, "#1f78b4"),
+                            (3, "#b2df8a"),
+                            (4, "#33a02c"),
+                            (5, "#fb9a99"),
+                            (6, "#e31a1c"),
+                            (7, "#fdbf6f"),
+                            (8, "#ff7f00"),
+                            (9, "#cab2d6"),
+                            (10, "#6a3d9a"),
+                            (11, "#b15928"),
+                            (12, "#000000"),
+                            (13, "#cccccc"),
+                        ],
+                        default=1,
+                    ),
+                ),
+                ("match", models.CharField(blank=True, max_length=256)),
+                (
+                    "matching_algorithm",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (1, "Any"),
+                            (2, "All"),
+                            (3, "Literal"),
+                            (4, "Regular Expression"),
+                        ],
+                        default=1,
+                        help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  If you don\'t know what a regex is, you probably don\'t want this option.',
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+        migrations.AlterField(
+            model_name="sender",
+            name="slug",
+            field=models.SlugField(blank=True),
+        ),
+        migrations.AddField(
+            model_name="document",
+            name="file_type",
+            field=models.CharField(
+                choices=[
+                    ("pdf", "PDF"),
+                    ("png", "PNG"),
+                    ("jpg", "JPG"),
+                    ("gif", "GIF"),
+                    ("tiff", "TIFF"),
+                ],
+                default="pdf",
+                editable=False,
+                max_length=4,
+            ),
+            preserve_default=False,
+        ),
+        migrations.AddField(
+            model_name="document",
+            name="tags",
+            field=models.ManyToManyField(
+                blank=True,
+                related_name="documents",
+                to="documents.tag",
+            ),
+        ),
+        migrations.CreateModel(
+            name="Log",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("group", models.UUIDField(blank=True)),
+                ("message", models.TextField()),
+                (
+                    "level",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (10, "Debugging"),
+                            (20, "Informational"),
+                            (30, "Warning"),
+                            (40, "Error"),
+                            (50, "Critical"),
+                        ],
+                        default=20,
+                    ),
+                ),
+                (
+                    "component",
+                    models.PositiveIntegerField(
+                        choices=[(1, "Consumer"), (2, "Mail Fetcher")],
+                    ),
+                ),
+                ("created", models.DateTimeField(auto_now_add=True)),
+                ("modified", models.DateTimeField(auto_now=True)),
+            ],
+            options={
+                "ordering": ("-modified",),
+            },
+        ),
+        migrations.RenameModel(
+            old_name="Sender",
+            new_name="Correspondent",
+        ),
+        migrations.AlterModelOptions(
+            name="document",
+            options={"ordering": ("correspondent", "title")},
+        ),
+        migrations.RenameField(
+            model_name="document",
+            old_name="sender",
+            new_name="correspondent",
+        ),
+    ]

src/documents/migrations/0005_auto_20160123_0313.py

@@ -0,0 +1,16 @@
+# Generated by Django 1.9 on 2016-01-23 03:13
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0004_auto_20160114_1844"),
+    ]
+
+    operations = [
+        migrations.AlterModelOptions(
+            name="sender",
+            options={"ordering": ("name",)},
+        ),
+    ]

src/documents/migrations/0006_auto_20160123_0430.py

@@ -0,0 +1,64 @@
+# Generated by Django 1.9 on 2016-01-23 04:30
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0005_auto_20160123_0313"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="Tag",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("name", models.CharField(max_length=128, unique=True)),
+                ("slug", models.SlugField(blank=True)),
+                (
+                    "colour",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (1, "#a6cee3"),
+                            (2, "#1f78b4"),
+                            (3, "#b2df8a"),
+                            (4, "#33a02c"),
+                            (5, "#fb9a99"),
+                            (6, "#e31a1c"),
+                            (7, "#fdbf6f"),
+                            (8, "#ff7f00"),
+                            (9, "#cab2d6"),
+                            (10, "#6a3d9a"),
+                            (11, "#ffff99"),
+                            (12, "#b15928"),
+                            (13, "#000000"),
+                            (14, "#cccccc"),
+                        ],
+                        default=1,
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+        migrations.AlterField(
+            model_name="sender",
+            name="slug",
+            field=models.SlugField(blank=True),
+        ),
+        migrations.AddField(
+            model_name="document",
+            name="tags",
+            field=models.ManyToManyField(related_name="documents", to="documents.Tag"),
+        ),
+    ]

src/documents/migrations/0007_auto_20160126_2114.py

@@ -0,0 +1,55 @@
+# Generated by Django 1.9 on 2016-01-26 21:14
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0006_auto_20160123_0430"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="tag",
+            name="match",
+            field=models.CharField(blank=True, max_length=256),
+        ),
+        migrations.AddField(
+            model_name="tag",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                blank=True,
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                ],
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  If you don\'t know what a regex is, you probably don\'t want this option.',
+                null=True,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="colour",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "#a6cee3"),
+                    (2, "#1f78b4"),
+                    (3, "#b2df8a"),
+                    (4, "#33a02c"),
+                    (5, "#fb9a99"),
+                    (6, "#e31a1c"),
+                    (7, "#fdbf6f"),
+                    (8, "#ff7f00"),
+                    (9, "#cab2d6"),
+                    (10, "#6a3d9a"),
+                    (11, "#b15928"),
+                    (12, "#000000"),
+                    (13, "#cccccc"),
+                ],
+                default=1,
+            ),
+        ),
+    ]

src/documents/migrations/0008_document_file_type.py

@@ -0,0 +1,39 @@
+# Generated by Django 1.9 on 2016-01-29 22:58
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0007_auto_20160126_2114"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="document",
+            name="file_type",
+            field=models.CharField(
+                choices=[
+                    ("pdf", "PDF"),
+                    ("png", "PNG"),
+                    ("jpg", "JPG"),
+                    ("gif", "GIF"),
+                    ("tiff", "TIFF"),
+                ],
+                default="pdf",
+                editable=False,
+                max_length=4,
+            ),
+            preserve_default=False,
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="tags",
+            field=models.ManyToManyField(
+                blank=True,
+                related_name="documents",
+                to="documents.Tag",
+            ),
+        ),
+    ]

src/documents/migrations/0009_auto_20160214_0040.py

@@ -0,0 +1,27 @@
+# Generated by Django 1.9 on 2016-02-14 00:40
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0008_document_file_type"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="tag",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                ],
+                default=1,
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  If you don\'t know what a regex is, you probably don\'t want this option.',
+            ),
+        ),
+    ]

src/documents/migrations/0010_log.py

@@ -0,0 +1,53 @@
+# Generated by Django 1.9 on 2016-02-27 17:54
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0009_auto_20160214_0040"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="Log",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("group", models.UUIDField(blank=True)),
+                ("message", models.TextField()),
+                (
+                    "level",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (10, "Debugging"),
+                            (20, "Informational"),
+                            (30, "Warning"),
+                            (40, "Error"),
+                            (50, "Critical"),
+                        ],
+                        default=20,
+                    ),
+                ),
+                (
+                    "component",
+                    models.PositiveIntegerField(
+                        choices=[(1, "Consumer"), (2, "Mail Fetcher")],
+                    ),
+                ),
+                ("created", models.DateTimeField(auto_now_add=True)),
+                ("modified", models.DateTimeField(auto_now=True)),
+            ],
+            options={
+                "ordering": ("-modified",),
+            },
+        ),
+    ]

src/documents/migrations/0011_auto_20160303_1929.py

@@ -0,0 +1,26 @@
+# Generated by Django 1.9.2 on 2016-03-03 19:29
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    atomic = False
+    dependencies = [
+        ("documents", "0010_log"),
+    ]
+
+    operations = [
+        migrations.RenameModel(
+            old_name="Sender",
+            new_name="Correspondent",
+        ),
+        migrations.AlterModelOptions(
+            name="document",
+            options={"ordering": ("correspondent", "title")},
+        ),
+        migrations.RenameField(
+            model_name="document",
+            old_name="sender",
+            new_name="correspondent",
+        ),
+    ]

src/documents/migrations/0012_auto_20160305_0040.py

@@ -0,0 +1,128 @@
+# Generated by Django 1.9.2 on 2016-03-05 00:40
+
+import os
+import re
+import shutil
+import subprocess
+import tempfile
+from pathlib import Path
+
+import gnupg
+from django.conf import settings
+from django.db import migrations
+from django.utils.termcolors import colorize as colourise  # Spelling hurts me
+
+
+class GnuPG:
+    """
+    A handy singleton to use when handling encrypted files.
+    """
+
+    gpg = gnupg.GPG(gnupghome=settings.GNUPG_HOME)
+
+    @classmethod
+    def decrypted(cls, file_handle):
+        return cls.gpg.decrypt_file(file_handle, passphrase=settings.PASSPHRASE).data
+
+    @classmethod
+    def encrypted(cls, file_handle):
+        return cls.gpg.encrypt_file(
+            file_handle,
+            recipients=None,
+            passphrase=settings.PASSPHRASE,
+            symmetric=True,
+        ).data
+
+
+def move_documents_and_create_thumbnails(apps, schema_editor):
+    (Path(settings.MEDIA_ROOT) / "documents" / "originals").mkdir(
+        parents=True,
+        exist_ok=True,
+    )
+    (Path(settings.MEDIA_ROOT) / "documents" / "thumbnails").mkdir(
+        parents=True,
+        exist_ok=True,
+    )
+
+    documents: list[str] = os.listdir(Path(settings.MEDIA_ROOT) / "documents")  # noqa: PTH208
+
+    if set(documents) == {"originals", "thumbnails"}:
+        return
+
+    print(
+        colourise(
+            "\n\n"
+            "  This is a one-time only migration to generate thumbnails for all of your\n"
+            "  documents so that future UIs will have something to work with.  If you have\n"
+            "  a lot of documents though, this may take a while, so a coffee break may be\n"
+            "  in order."
+            "\n",
+            opts=("bold",),
+        ),
+    )
+
+    Path(settings.SCRATCH_DIR).mkdir(parents=True, exist_ok=True)
+
+    for f in sorted(documents):
+        if not f.endswith("gpg"):
+            continue
+
+        print(
+            "    {} {} {}".format(
+                colourise("*", fg="green"),
+                colourise("Generating a thumbnail for", fg="white"),
+                colourise(f, fg="cyan"),
+            ),
+        )
+
+        thumb_temp: str = tempfile.mkdtemp(prefix="paperless", dir=settings.SCRATCH_DIR)
+        orig_temp: str = tempfile.mkdtemp(prefix="paperless", dir=settings.SCRATCH_DIR)
+
+        orig_source: Path = Path(settings.MEDIA_ROOT) / "documents" / f
+        orig_target: Path = Path(orig_temp) / f.replace(".gpg", "")
+
+        with orig_source.open("rb") as encrypted, orig_target.open("wb") as unencrypted:
+            unencrypted.write(GnuPG.decrypted(encrypted))
+
+        subprocess.Popen(
+            (
+                settings.CONVERT_BINARY,
+                "-scale",
+                "500x5000",
+                "-alpha",
+                "remove",
+                orig_target,
+                Path(thumb_temp) / "convert-%04d.png",
+            ),
+        ).wait()
+
+        thumb_source: Path = Path(thumb_temp) / "convert-0000.png"
+        thumb_target: Path = (
+            Path(settings.MEDIA_ROOT)
+            / "documents"
+            / "thumbnails"
+            / re.sub(r"(\d+)\.\w+(\.gpg)", "\\1.png\\2", f)
+        )
+        with (
+            thumb_source.open("rb") as unencrypted,
+            thumb_target.open("wb") as encrypted,
+        ):
+            encrypted.write(GnuPG.encrypted(unencrypted))
+
+        shutil.rmtree(thumb_temp)
+        shutil.rmtree(orig_temp)
+
+        shutil.move(
+            Path(settings.MEDIA_ROOT) / "documents" / f,
+            Path(settings.MEDIA_ROOT) / "documents" / "originals" / f,
+        )
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0011_auto_20160303_1929"),
+    ]
+
+    operations = [
+        migrations.RunPython(move_documents_and_create_thumbnails),
+    ]

src/documents/migrations/0013_auto_20160325_2111.py

@@ -0,0 +1,42 @@
+# Generated by Django 1.9.4 on 2016-03-25 21:11
+
+import django.utils.timezone
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0012_auto_20160305_0040"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="correspondent",
+            name="match",
+            field=models.CharField(blank=True, max_length=256),
+        ),
+        migrations.AddField(
+            model_name="correspondent",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                ],
+                default=1,
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  If you don\'t know what a regex is, you probably don\'t want this option.',
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="created",
+            field=models.DateTimeField(default=django.utils.timezone.now),
+        ),
+        migrations.RemoveField(
+            model_name="log",
+            name="component",
+        ),
+    ]

src/documents/migrations/0014_document_checksum.py

@@ -0,0 +1,182 @@
+# Generated by Django 1.9.4 on 2016-03-28 19:09
+
+import hashlib
+from pathlib import Path
+
+import django.utils.timezone
+import gnupg
+from django.conf import settings
+from django.db import migrations
+from django.db import models
+from django.template.defaultfilters import slugify
+from django.utils.termcolors import colorize as colourise  # Spelling hurts me
+
+
+class GnuPG:
+    """
+    A handy singleton to use when handling encrypted files.
+    """
+
+    gpg = gnupg.GPG(gnupghome=settings.GNUPG_HOME)
+
+    @classmethod
+    def decrypted(cls, file_handle):
+        return cls.gpg.decrypt_file(file_handle, passphrase=settings.PASSPHRASE).data
+
+    @classmethod
+    def encrypted(cls, file_handle):
+        return cls.gpg.encrypt_file(
+            file_handle,
+            recipients=None,
+            passphrase=settings.PASSPHRASE,
+            symmetric=True,
+        ).data
+
+
+class Document:
+    """
+    Django's migrations restrict access to model methods, so this is a snapshot
+    of the methods that existed at the time this migration was written, since
+    we need to make use of a lot of these shortcuts here.
+    """
+
+    def __init__(self, doc):
+        self.pk = doc.pk
+        self.correspondent = doc.correspondent
+        self.title = doc.title
+        self.file_type = doc.file_type
+        self.tags = doc.tags
+        self.created = doc.created
+
+    def __str__(self):
+        created = self.created.strftime("%Y%m%d%H%M%S")
+        if self.correspondent and self.title:
+            return f"{created}: {self.correspondent} - {self.title}"
+        if self.correspondent or self.title:
+            return f"{created}: {self.correspondent or self.title}"
+        return str(created)
+
+    @property
+    def source_path(self):
+        return (
+            Path(settings.MEDIA_ROOT)
+            / "documents"
+            / "originals"
+            / f"{self.pk:07}.{self.file_type}.gpg"
+        )
+
+    @property
+    def source_file(self):
+        return self.source_path.open("rb")
+
+    @property
+    def file_name(self):
+        return slugify(str(self)) + "." + self.file_type
+
+
+def set_checksums(apps, schema_editor):
+    document_model = apps.get_model("documents", "Document")
+
+    if not document_model.objects.all().exists():
+        return
+
+    print(
+        colourise(
+            "\n\n"
+            "  This is a one-time only migration to generate checksums for all\n"
+            "  of your existing documents.  If you have a lot of documents\n"
+            "  though, this may take a while, so a coffee break may be in\n"
+            "  order."
+            "\n",
+            opts=("bold",),
+        ),
+    )
+
+    sums = {}
+    for d in document_model.objects.all():
+        document = Document(d)
+
+        print(
+            "    {} {} {}".format(
+                colourise("*", fg="green"),
+                colourise("Generating a checksum for", fg="white"),
+                colourise(document.file_name, fg="cyan"),
+            ),
+        )
+
+        with document.source_file as encrypted:
+            checksum = hashlib.md5(GnuPG.decrypted(encrypted)).hexdigest()
+
+        if checksum in sums:
+            error = "\n{line}{p1}\n\n{doc1}\n{doc2}\n\n{p2}\n\n{code}\n\n{p3}{line}".format(
+                p1=colourise(
+                    "It appears that you have two identical documents in your collection and \nPaperless no longer supports this (see issue #97).  The documents in question\nare:",
+                    fg="yellow",
+                ),
+                p2=colourise(
+                    "To fix this problem, you'll have to remove one of them from the database, a task\nmost easily done by running the following command in the same\ndirectory as manage.py:",
+                    fg="yellow",
+                ),
+                p3=colourise(
+                    "When that's finished, re-run the migrate, and provided that there aren't any\nother duplicates, you should be good to go.",
+                    fg="yellow",
+                ),
+                doc1=colourise(
+                    f"  * {sums[checksum][1]} (id: {sums[checksum][0]})",
+                    fg="red",
+                ),
+                doc2=colourise(
+                    f"  * {document.file_name} (id: {document.pk})",
+                    fg="red",
+                ),
+                code=colourise(
+                    f"  $ echo 'DELETE FROM documents_document WHERE id = {document.pk};' | ./manage.py dbshell",
+                    fg="green",
+                ),
+                line=colourise("\n{}\n".format("=" * 80), fg="white", opts=("bold",)),
+            )
+            raise RuntimeError(error)
+        sums[checksum] = (document.pk, document.file_name)
+
+        document_model.objects.filter(pk=document.pk).update(checksum=checksum)
+
+
+def do_nothing(apps, schema_editor):
+    pass
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0013_auto_20160325_2111"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                default="-",
+                db_index=True,
+                editable=False,
+                max_length=32,
+                help_text="The checksum of the original document (before it "
+                "was encrypted).  We use this to prevent duplicate "
+                "document imports.",
+            ),
+            preserve_default=False,
+        ),
+        migrations.RunPython(set_checksums, do_nothing),
+        migrations.AlterField(
+            model_name="document",
+            name="created",
+            field=models.DateTimeField(
+                db_index=True,
+                default=django.utils.timezone.now,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="modified",
+            field=models.DateTimeField(auto_now=True, db_index=True),
+        ),
+    ]

src/documents/migrations/0015_add_insensitive_to_match.py

@@ -0,0 +1,33 @@
+# Generated by Django 1.10.2 on 2016-10-05 21:38
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0014_document_checksum"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                editable=False,
+                help_text="The checksum of the original document (before it was encrypted).  We use this to prevent duplicate document imports.",
+                max_length=32,
+                unique=True,
+            ),
+        ),
+        migrations.AddField(
+            model_name="correspondent",
+            name="is_insensitive",
+            field=models.BooleanField(default=True),
+        ),
+        migrations.AddField(
+            model_name="tag",
+            name="is_insensitive",
+            field=models.BooleanField(default=True),
+        ),
+    ]

src/documents/migrations/0015_add_insensitive_to_match_squashed_0018_auto_20170715_1712.py

@@ -0,0 +1,92 @@
+# Generated by Django 4.2.13 on 2024-06-28 17:57
+
+import django.db.models.deletion
+from django.conf import settings
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    replaces = [
+        ("documents", "0015_add_insensitive_to_match"),
+        ("documents", "0016_auto_20170325_1558"),
+        ("documents", "0017_auto_20170512_0507"),
+        ("documents", "0018_auto_20170715_1712"),
+    ]
+
+    dependencies = [
+        ("documents", "0014_document_checksum"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                editable=False,
+                help_text="The checksum of the original document (before it was encrypted).  We use this to prevent duplicate document imports.",
+                max_length=32,
+                unique=True,
+            ),
+        ),
+        migrations.AddField(
+            model_name="correspondent",
+            name="is_insensitive",
+            field=models.BooleanField(default=True),
+        ),
+        migrations.AddField(
+            model_name="tag",
+            name="is_insensitive",
+            field=models.BooleanField(default=True),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="content",
+            field=models.TextField(
+                blank=True,
+                db_index=("mysql" not in settings.DATABASES["default"]["ENGINE"]),
+                help_text="The raw, text-only data of the document.  This field is primarily used for searching.",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="correspondent",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                    (5, "Fuzzy Match"),
+                ],
+                default=1,
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
+            ),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                    (5, "Fuzzy Match"),
+                ],
+                default=1,
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="correspondent",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="documents",
+                to="documents.correspondent",
+            ),
+        ),
+    ]

src/documents/migrations/0016_auto_20170325_1558.py

@@ -0,0 +1,23 @@
+# Generated by Django 1.10.5 on 2017-03-25 15:58
+
+from django.conf import settings
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0015_add_insensitive_to_match"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="content",
+            field=models.TextField(
+                blank=True,
+                db_index=("mysql" not in settings.DATABASES["default"]["ENGINE"]),
+                help_text="The raw, text-only data of the document.  This field is primarily used for searching.",
+            ),
+        ),
+    ]

src/documents/migrations/0017_auto_20170512_0507.py

@@ -0,0 +1,43 @@
+# Generated by Django 1.10.5 on 2017-05-12 05:07
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0016_auto_20170325_1558"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="correspondent",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                    (5, "Fuzzy Match"),
+                ],
+                default=1,
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
+            ),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                    (5, "Fuzzy Match"),
+                ],
+                default=1,
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
+            ),
+        ),
+    ]

src/documents/migrations/0018_auto_20170715_1712.py

@@ -0,0 +1,25 @@
+# Generated by Django 1.10.5 on 2017-07-15 17:12
+
+import django.db.models.deletion
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0017_auto_20170512_0507"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="correspondent",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="documents",
+                to="documents.Correspondent",
+            ),
+        ),
+    ]

src/documents/migrations/0019_add_consumer_user.py

@@ -0,0 +1,22 @@
+# Generated by Django 1.10.5 on 2017-07-15 17:12
+
+from django.contrib.auth.models import User
+from django.db import migrations
+
+
+def forwards_func(apps, schema_editor):
+    User.objects.create(username="consumer")
+
+
+def reverse_func(apps, schema_editor):
+    User.objects.get(username="consumer").delete()
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0018_auto_20170715_1712"),
+    ]
+
+    operations = [
+        migrations.RunPython(forwards_func, reverse_func),
+    ]

src/documents/migrations/0020_document_added.py

@@ -0,0 +1,29 @@
+import django.utils.timezone
+from django.db import migrations
+from django.db import models
+
+
+def set_added_time_to_created_time(apps, schema_editor):
+    Document = apps.get_model("documents", "Document")
+    for doc in Document.objects.all():
+        doc.added = doc.created
+        doc.save()
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0019_add_consumer_user"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="document",
+            name="added",
+            field=models.DateTimeField(
+                db_index=True,
+                default=django.utils.timezone.now,
+                editable=False,
+            ),
+        ),
+        migrations.RunPython(set_added_time_to_created_time),
+    ]

src/documents/migrations/0021_document_storage_type.py

@@ -0,0 +1,41 @@
+# Generated by Django 1.11.10 on 2018-02-04 13:07
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0020_document_added"),
+    ]
+
+    operations = [
+        # Add the field with the default GPG-encrypted value
+        migrations.AddField(
+            model_name="document",
+            name="storage_type",
+            field=models.CharField(
+                choices=[
+                    ("unencrypted", "Unencrypted"),
+                    ("gpg", "Encrypted with GNU Privacy Guard"),
+                ],
+                default="gpg",
+                editable=False,
+                max_length=11,
+            ),
+        ),
+        # Now that the field is added, change the default to unencrypted
+        migrations.AlterField(
+            model_name="document",
+            name="storage_type",
+            field=models.CharField(
+                choices=[
+                    ("unencrypted", "Unencrypted"),
+                    ("gpg", "Encrypted with GNU Privacy Guard"),
+                ],
+                default="unencrypted",
+                editable=False,
+                max_length=11,
+            ),
+        ),
+    ]

src/documents/migrations/0022_auto_20181007_1420.py

@@ -0,0 +1,61 @@
+# Generated by Django 2.0.8 on 2018-10-07 14:20
+
+from django.db import migrations
+from django.db import models
+from django.utils.text import slugify
+
+
+def re_slug_all_the_things(apps, schema_editor):
+    """
+    Rewrite all slug values to make sure they're actually slugs before we brand
+    them as uneditable.
+    """
+
+    Tag = apps.get_model("documents", "Tag")
+    Correspondent = apps.get_model("documents", "Correspondent")
+
+    for klass in (Tag, Correspondent):
+        for instance in klass.objects.all():
+            klass.objects.filter(pk=instance.pk).update(slug=slugify(instance.slug))
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0021_document_storage_type"),
+    ]
+
+    operations = [
+        migrations.AlterModelOptions(
+            name="tag",
+            options={"ordering": ("name",)},
+        ),
+        migrations.AlterField(
+            model_name="correspondent",
+            name="slug",
+            field=models.SlugField(blank=True, editable=False),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="file_type",
+            field=models.CharField(
+                choices=[
+                    ("pdf", "PDF"),
+                    ("png", "PNG"),
+                    ("jpg", "JPG"),
+                    ("gif", "GIF"),
+                    ("tiff", "TIFF"),
+                    ("txt", "TXT"),
+                    ("csv", "CSV"),
+                    ("md", "MD"),
+                ],
+                editable=False,
+                max_length=4,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="slug",
+            field=models.SlugField(blank=True, editable=False),
+        ),
+        migrations.RunPython(re_slug_all_the_things, migrations.RunPython.noop),
+    ]

src/documents/migrations/0023_document_current_filename.py

@@ -0,0 +1,39 @@
+# Generated by Django 2.0.10 on 2019-04-26 18:57
+
+from django.db import migrations
+from django.db import models
+
+
+def set_filename(apps, schema_editor):
+    Document = apps.get_model("documents", "Document")
+    for doc in Document.objects.all():
+        file_name = f"{doc.pk:07}.{doc.file_type}"
+        if doc.storage_type == "gpg":
+            file_name += ".gpg"
+
+        # Set filename
+        doc.filename = file_name
+
+        # Save document
+        doc.save()
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0022_auto_20181007_1420"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="document",
+            name="filename",
+            field=models.FilePathField(
+                default=None,
+                null=True,
+                editable=False,
+                help_text="Current filename in storage",
+                max_length=256,
+            ),
+        ),
+        migrations.RunPython(set_filename),
+    ]

src/documents/migrations/1000_update_paperless_all.py

@@ -0,0 +1,147 @@
+# Generated by Django 3.1.3 on 2020-11-07 12:35
+import uuid
+
+import django.db.models.deletion
+from django.db import migrations
+from django.db import models
+
+
+def logs_set_default_group(apps, schema_editor):
+    Log = apps.get_model("documents", "Log")
+    for log in Log.objects.all():
+        if log.group is None:
+            log.group = uuid.uuid4()
+            log.save()
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0023_document_current_filename"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="document",
+            name="archive_serial_number",
+            field=models.IntegerField(
+                blank=True,
+                db_index=True,
+                help_text="The position of this document in your physical document archive.",
+                null=True,
+                unique=True,
+            ),
+        ),
+        migrations.AddField(
+            model_name="tag",
+            name="is_inbox_tag",
+            field=models.BooleanField(
+                default=False,
+                help_text="Marks this tag as an inbox tag: All newly consumed documents will be tagged with inbox tags.",
+            ),
+        ),
+        migrations.CreateModel(
+            name="DocumentType",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("name", models.CharField(max_length=128, unique=True)),
+                ("slug", models.SlugField(blank=True, editable=False)),
+                ("match", models.CharField(blank=True, max_length=256)),
+                (
+                    "matching_algorithm",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (1, "Any"),
+                            (2, "All"),
+                            (3, "Literal"),
+                            (4, "Regular Expression"),
+                            (5, "Fuzzy Match"),
+                            (6, "Automatic Classification"),
+                        ],
+                        default=1,
+                        help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
+                    ),
+                ),
+                ("is_insensitive", models.BooleanField(default=True)),
+            ],
+            options={
+                "abstract": False,
+                "ordering": ("name",),
+            },
+        ),
+        migrations.AddField(
+            model_name="document",
+            name="document_type",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="documents",
+                to="documents.documenttype",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="correspondent",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                    (5, "Fuzzy Match"),
+                    (6, "Automatic Classification"),
+                ],
+                default=1,
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
+            ),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any"),
+                    (2, "All"),
+                    (3, "Literal"),
+                    (4, "Regular Expression"),
+                    (5, "Fuzzy Match"),
+                    (6, "Automatic Classification"),
+                ],
+                default=1,
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="content",
+            field=models.TextField(
+                blank=True,
+                help_text="The raw, text-only data of the document. This field is primarily used for searching.",
+            ),
+        ),
+        migrations.AlterModelOptions(
+            name="log",
+            options={"ordering": ("-created",)},
+        ),
+        migrations.RemoveField(
+            model_name="log",
+            name="modified",
+        ),
+        migrations.AlterField(
+            model_name="log",
+            name="group",
+            field=models.UUIDField(blank=True, null=True),
+        ),
+        migrations.RunPython(
+            code=django.db.migrations.operations.special.RunPython.noop,
+            reverse_code=logs_set_default_group,
+        ),
+    ]

src/documents/migrations/1001_auto_20201109_1636.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.1.3 on 2020-11-09 16:36
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1000_update_paperless_all"),
+    ]
+
+    operations = [
+        migrations.RunPython(migrations.RunPython.noop, migrations.RunPython.noop),
+    ]

src/documents/migrations/1002_auto_20201111_1105.py

@@ -0,0 +1,24 @@
+# Generated by Django 3.1.3 on 2020-11-11 11:05
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1001_auto_20201109_1636"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="filename",
+            field=models.FilePathField(
+                default=None,
+                editable=False,
+                help_text="Current filename in storage",
+                max_length=1024,
+                null=True,
+            ),
+        ),
+    ]

src/documents/migrations/1003_mime_types.py

@@ -0,0 +1,92 @@
+# Generated by Django 3.1.3 on 2020-11-20 11:21
+from pathlib import Path
+
+import magic
+from django.conf import settings
+from django.db import migrations
+from django.db import models
+
+from paperless.db import GnuPG
+
+STORAGE_TYPE_UNENCRYPTED = "unencrypted"
+STORAGE_TYPE_GPG = "gpg"
+
+
+def source_path(self) -> Path:
+    if self.filename:
+        fname: str = str(self.filename)
+    else:
+        fname = f"{self.pk:07}.{self.file_type}"
+        if self.storage_type == STORAGE_TYPE_GPG:
+            fname += ".gpg"
+
+    return Path(settings.ORIGINALS_DIR) / fname
+
+
+def add_mime_types(apps, schema_editor):
+    Document = apps.get_model("documents", "Document")
+    documents = Document.objects.all()
+
+    for d in documents:
+        with Path(source_path(d)).open("rb") as f:
+            if d.storage_type == STORAGE_TYPE_GPG:
+                data = GnuPG.decrypted(f)
+            else:
+                data = f.read(1024)
+
+        d.mime_type = magic.from_buffer(data, mime=True)
+        d.save()
+
+
+def add_file_extensions(apps, schema_editor):
+    Document = apps.get_model("documents", "Document")
+    documents = Document.objects.all()
+
+    for d in documents:
+        d.file_type = Path(d.filename).suffix.lstrip(".")
+        d.save()
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1002_auto_20201111_1105"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="document",
+            name="mime_type",
+            field=models.CharField(default="-", editable=False, max_length=256),
+            preserve_default=False,
+        ),
+        migrations.RunPython(add_mime_types, migrations.RunPython.noop),
+        # This operation is here so that we can revert the entire migration:
+        # By allowing this field to be blank and null, we can revert the
+        # remove operation further down and the database won't complain about
+        # NOT NULL violations.
+        migrations.AlterField(
+            model_name="document",
+            name="file_type",
+            field=models.CharField(
+                choices=[
+                    ("pdf", "PDF"),
+                    ("png", "PNG"),
+                    ("jpg", "JPG"),
+                    ("gif", "GIF"),
+                    ("tiff", "TIFF"),
+                    ("txt", "TXT"),
+                    ("csv", "CSV"),
+                    ("md", "MD"),
+                ],
+                editable=False,
+                max_length=4,
+                null=True,
+                blank=True,
+            ),
+        ),
+        migrations.RunPython(migrations.RunPython.noop, add_file_extensions),
+        migrations.RemoveField(
+            model_name="document",
+            name="file_type",
+        ),
+    ]

src/documents/migrations/1004_sanity_check_schedule.py

@@ -0,0 +1,12 @@
+# Generated by Django 3.1.3 on 2020-11-25 14:53
+
+from django.db import migrations
+from django.db.migrations import RunPython
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1003_mime_types"),
+    ]
+
+    operations = [RunPython(migrations.RunPython.noop, migrations.RunPython.noop)]

src/documents/migrations/1005_checksums.py

@@ -0,0 +1,34 @@
+# Generated by Django 3.1.3 on 2020-11-29 00:48
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1004_sanity_check_schedule"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="document",
+            name="archive_checksum",
+            field=models.CharField(
+                blank=True,
+                editable=False,
+                help_text="The checksum of the archived document.",
+                max_length=32,
+                null=True,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                editable=False,
+                help_text="The checksum of the original document.",
+                max_length=32,
+                unique=True,
+            ),
+        ),
+    ]

src/documents/migrations/1006_auto_20201208_2209.py

@@ -0,0 +1,24 @@
+# Generated by Django 3.1.4 on 2020-12-08 22:09
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "1005_checksums"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="correspondent",
+            name="slug",
+        ),
+        migrations.RemoveField(
+            model_name="documenttype",
+            name="slug",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="slug",
+        ),
+    ]

src/documents/migrations/1006_auto_20201208_2209_squashed_1011_auto_20210101_2340.py

@@ -0,0 +1,485 @@
+# Generated by Django 4.2.13 on 2024-06-28 18:01
+
+import django.db.models.deletion
+import django.utils.timezone
+from django.conf import settings
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    replaces = [
+        ("documents", "1006_auto_20201208_2209"),
+        ("documents", "1007_savedview_savedviewfilterrule"),
+        ("documents", "1008_auto_20201216_1736"),
+        ("documents", "1009_auto_20201216_2005"),
+        ("documents", "1010_auto_20210101_2159"),
+        ("documents", "1011_auto_20210101_2340"),
+    ]
+
+    dependencies = [
+        ("documents", "1005_checksums"),
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="correspondent",
+            name="slug",
+        ),
+        migrations.RemoveField(
+            model_name="documenttype",
+            name="slug",
+        ),
+        migrations.RemoveField(
+            model_name="tag",
+            name="slug",
+        ),
+        migrations.CreateModel(
+            name="SavedView",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("name", models.CharField(max_length=128, verbose_name="name")),
+                (
+                    "show_on_dashboard",
+                    models.BooleanField(verbose_name="show on dashboard"),
+                ),
+                (
+                    "show_in_sidebar",
+                    models.BooleanField(verbose_name="show in sidebar"),
+                ),
+                (
+                    "sort_field",
+                    models.CharField(max_length=128, verbose_name="sort field"),
+                ),
+                (
+                    "sort_reverse",
+                    models.BooleanField(default=False, verbose_name="sort reverse"),
+                ),
+                (
+                    "user",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to=settings.AUTH_USER_MODEL,
+                        verbose_name="user",
+                    ),
+                ),
+            ],
+            options={
+                "ordering": ("name",),
+                "verbose_name": "saved view",
+                "verbose_name_plural": "saved views",
+            },
+        ),
+        migrations.AlterModelOptions(
+            name="correspondent",
+            options={
+                "ordering": ("name",),
+                "verbose_name": "correspondent",
+                "verbose_name_plural": "correspondents",
+            },
+        ),
+        migrations.AlterModelOptions(
+            name="document",
+            options={
+                "ordering": ("-created",),
+                "verbose_name": "document",
+                "verbose_name_plural": "documents",
+            },
+        ),
+        migrations.AlterModelOptions(
+            name="documenttype",
+            options={
+                "verbose_name": "document type",
+                "verbose_name_plural": "document types",
+            },
+        ),
+        migrations.AlterModelOptions(
+            name="log",
+            options={
+                "ordering": ("-created",),
+                "verbose_name": "log",
+                "verbose_name_plural": "logs",
+            },
+        ),
+        migrations.AlterModelOptions(
+            name="tag",
+            options={"verbose_name": "tag", "verbose_name_plural": "tags"},
+        ),
+        migrations.AlterField(
+            model_name="correspondent",
+            name="is_insensitive",
+            field=models.BooleanField(default=True, verbose_name="is insensitive"),
+        ),
+        migrations.AlterField(
+            model_name="correspondent",
+            name="match",
+            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
+        ),
+        migrations.AlterField(
+            model_name="correspondent",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any word"),
+                    (2, "All words"),
+                    (3, "Exact match"),
+                    (4, "Regular expression"),
+                    (5, "Fuzzy word"),
+                    (6, "Automatic"),
+                ],
+                default=1,
+                verbose_name="matching algorithm",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="correspondent",
+            name="name",
+            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="added",
+            field=models.DateTimeField(
+                db_index=True,
+                default=django.utils.timezone.now,
+                editable=False,
+                verbose_name="added",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="archive_checksum",
+            field=models.CharField(
+                blank=True,
+                editable=False,
+                help_text="The checksum of the archived document.",
+                max_length=32,
+                null=True,
+                verbose_name="archive checksum",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="archive_serial_number",
+            field=models.IntegerField(
+                blank=True,
+                db_index=True,
+                help_text="The position of this document in your physical document archive.",
+                null=True,
+                unique=True,
+                verbose_name="archive serial number",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                editable=False,
+                help_text="The checksum of the original document.",
+                max_length=32,
+                unique=True,
+                verbose_name="checksum",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="content",
+            field=models.TextField(
+                blank=True,
+                help_text="The raw, text-only data of the document. This field is primarily used for searching.",
+                verbose_name="content",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="correspondent",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="documents",
+                to="documents.correspondent",
+                verbose_name="correspondent",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="created",
+            field=models.DateTimeField(
+                db_index=True,
+                default=django.utils.timezone.now,
+                verbose_name="created",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="document_type",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="documents",
+                to="documents.documenttype",
+                verbose_name="document type",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="filename",
+            field=models.FilePathField(
+                default=None,
+                editable=False,
+                help_text="Current filename in storage",
+                max_length=1024,
+                null=True,
+                verbose_name="filename",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="mime_type",
+            field=models.CharField(
+                editable=False,
+                max_length=256,
+                verbose_name="mime type",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="modified",
+            field=models.DateTimeField(
+                auto_now=True,
+                db_index=True,
+                verbose_name="modified",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="storage_type",
+            field=models.CharField(
+                choices=[
+                    ("unencrypted", "Unencrypted"),
+                    ("gpg", "Encrypted with GNU Privacy Guard"),
+                ],
+                default="unencrypted",
+                editable=False,
+                max_length=11,
+                verbose_name="storage type",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="tags",
+            field=models.ManyToManyField(
+                blank=True,
+                related_name="documents",
+                to="documents.tag",
+                verbose_name="tags",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="document",
+            name="title",
+            field=models.CharField(
+                blank=True,
+                db_index=True,
+                max_length=128,
+                verbose_name="title",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="documenttype",
+            name="is_insensitive",
+            field=models.BooleanField(default=True, verbose_name="is insensitive"),
+        ),
+        migrations.AlterField(
+            model_name="documenttype",
+            name="match",
+            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
+        ),
+        migrations.AlterField(
+            model_name="documenttype",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any word"),
+                    (2, "All words"),
+                    (3, "Exact match"),
+                    (4, "Regular expression"),
+                    (5, "Fuzzy word"),
+                    (6, "Automatic"),
+                ],
+                default=1,
+                verbose_name="matching algorithm",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="documenttype",
+            name="name",
+            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
+        ),
+        migrations.AlterField(
+            model_name="log",
+            name="created",
+            field=models.DateTimeField(auto_now_add=True, verbose_name="created"),
+        ),
+        migrations.AlterField(
+            model_name="log",
+            name="group",
+            field=models.UUIDField(blank=True, null=True, verbose_name="group"),
+        ),
+        migrations.AlterField(
+            model_name="log",
+            name="level",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (10, "debug"),
+                    (20, "information"),
+                    (30, "warning"),
+                    (40, "error"),
+                    (50, "critical"),
+                ],
+                default=20,
+                verbose_name="level",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="log",
+            name="message",
+            field=models.TextField(verbose_name="message"),
+        ),
+        migrations.CreateModel(
+            name="SavedViewFilterRule",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "rule_type",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (0, "title contains"),
+                            (1, "content contains"),
+                            (2, "ASN is"),
+                            (3, "correspondent is"),
+                            (4, "document type is"),
+                            (5, "is in inbox"),
+                            (6, "has tag"),
+                            (7, "has any tag"),
+                            (8, "created before"),
+                            (9, "created after"),
+                            (10, "created year is"),
+                            (11, "created month is"),
+                            (12, "created day is"),
+                            (13, "added before"),
+                            (14, "added after"),
+                            (15, "modified before"),
+                            (16, "modified after"),
+                            (17, "does not have tag"),
+                        ],
+                        verbose_name="rule type",
+                    ),
+                ),
+                (
+                    "value",
+                    models.CharField(
+                        blank=True,
+                        max_length=128,
+                        null=True,
+                        verbose_name="value",
+                    ),
+                ),
+                (
+                    "saved_view",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="filter_rules",
+                        to="documents.savedview",
+                        verbose_name="saved view",
+                    ),
+                ),
+            ],
+            options={
+                "verbose_name": "filter rule",
+                "verbose_name_plural": "filter rules",
+            },
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="colour",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "#a6cee3"),
+                    (2, "#1f78b4"),
+                    (3, "#b2df8a"),
+                    (4, "#33a02c"),
+                    (5, "#fb9a99"),
+                    (6, "#e31a1c"),
+                    (7, "#fdbf6f"),
+                    (8, "#ff7f00"),
+                    (9, "#cab2d6"),
+                    (10, "#6a3d9a"),
+                    (11, "#b15928"),
+                    (12, "#000000"),
+                    (13, "#cccccc"),
+                ],
+                default=1,
+                verbose_name="color",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="is_inbox_tag",
+            field=models.BooleanField(
+                default=False,
+                help_text="Marks this tag as an inbox tag: All newly consumed documents will be tagged with inbox tags.",
+                verbose_name="is inbox tag",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="is_insensitive",
+            field=models.BooleanField(default=True, verbose_name="is insensitive"),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="match",
+            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="matching_algorithm",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Any word"),
+                    (2, "All words"),
+                    (3, "Exact match"),
+                    (4, "Regular expression"),
+                    (5, "Fuzzy word"),
+                    (6, "Automatic"),
+                ],
+                default=1,
+                verbose_name="matching algorithm",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="tag",
+            name="name",
+            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
+        ),
+    ]

src/documents/migrations/1007_savedview_savedviewfilterrule.py

@@ -0,0 +1,90 @@
+# Generated by Django 3.1.4 on 2020-12-12 14:41
+
+import django.db.models.deletion
+from django.conf import settings
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+        ("documents", "1006_auto_20201208_2209"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="SavedView",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("name", models.CharField(max_length=128)),
+                ("show_on_dashboard", models.BooleanField()),
+                ("show_in_sidebar", models.BooleanField()),
+                ("sort_field", models.CharField(max_length=128)),
+                ("sort_reverse", models.BooleanField(default=False)),
+                (
+                    "user",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to=settings.AUTH_USER_MODEL,
+                    ),
+                ),
+            ],
+        ),
+        migrations.CreateModel(
+            name="SavedViewFilterRule",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "rule_type",
+                    models.PositiveIntegerField(
+                        choices=[
+                            (0, "Title contains"),
+                            (1, "Content contains"),
+                            (2, "ASN is"),
+                            (3, "Correspondent is"),
+                            (4, "Document type is"),
+                            (5, "Is in inbox"),
+                            (6, "Has tag"),
+                            (7, "Has any tag"),
+                            (8, "Created before"),
+                            (9, "Created after"),
+                            (10, "Created year is"),
+                            (11, "Created month is"),
+                            (12, "Created day is"),
+                            (13, "Added before"),
+                            (14, "Added after"),
+                            (15, "Modified before"),
+                            (16, "Modified after"),
+                            (17, "Does not have tag"),
+                        ],
+                    ),
+                ),
+                ("value", models.CharField(max_length=128)),
+                (
+                    "saved_view",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="filter_rules",
+                        to="documents.savedview",
+                    ),
+                ),
+            ],
+        ),
+    ]