Fixes another N+1 location in the AI indexing, including the per document update which would hurt

Added a new --url argument to specify the base URL of the Paperless instance, allowing matched documents to be displayed as clickable links. Updated the logic to fetch document titles based on the presence of the base URL.

docs/administration.md

@@ -699,6 +699,7 @@ document_fuzzy_match [--ratio] [--processes N]
 | --ratio     | No       | 85.0                | a number between 0 and 100, setting how similar a document must be for it to be reported. Higher numbers mean more similarity. |
 | --processes | No       | 1/4 of system cores | Number of processes to use for matching. Setting 1 disables multiple processes                                                 |
 | --delete    | No       | False               | If provided, one document of a matched pair above the ratio will be deleted.                                                   |
+| --url       | No       | blank               | If an instance URL is provided, the output table will show URLs to each documents instead of the document ID and name.         |
 
 !!! warning
 

docs/configuration.md

@@ -948,10 +948,11 @@ for display in the web interface.
 
     !!! note
 
-        The **remote OCR parser** (Azure AI) always produces a searchable
-        PDF and stores it as the archive copy, regardless of this setting.
-        `ARCHIVE_FILE_GENERATION=never` has no effect when the remote
-        parser handles a document.
+        The **remote OCR parser** (Azure AI) also honors this setting: when
+        no archive is requested (`never`, or `auto` with a born-digital PDF),
+        the remote engine is skipped entirely and locally-extracted text is
+        used instead, avoiding an unnecessary API call and a duplicate text
+        layer.
 
 #### [`PAPERLESS_OCR_CLEAN=<mode>`](#PAPERLESS_OCR_CLEAN) {#PAPERLESS_OCR_CLEAN}
 

docs/migration-v3.md

@@ -187,10 +187,11 @@ PAPERLESS_ARCHIVE_FILE_GENERATION=auto
 
 ### Remote OCR parser
 
-If you use the **remote OCR parser** (Azure AI), note that it always produces a
-searchable PDF and stores it as the archive copy. `ARCHIVE_FILE_GENERATION=never`
-has no effect for documents handled by the remote parser - the archive is produced
-unconditionally by the remote engine.
+If you use the **remote OCR parser** (Azure AI), `ARCHIVE_FILE_GENERATION` is
+honored the same way as for the local engine: when no archive is requested
+(`never`, or `auto` with a born-digital PDF), the remote engine is skipped
+entirely and locally-extracted text is used instead, avoiding an unnecessary
+API call and a duplicate text layer.
 
 ## Search Index (Whoosh -> Tantivy)
 

docs/usage.md

@@ -576,7 +576,9 @@ The following workflow action types are available:
 - Tags, correspondent, document type and storage path
 - Document owner
 - View and / or edit permissions to users or groups
-- Custom fields. Note that no value for the field will be set
+- Custom fields, optionally with a value. If no value is set, the field is only added to the
+  document and any value it may already have is left untouched. If a value is set, it will
+  overwrite an existing value of that field on the document.
 
 ##### Removal {#workflow-action-removal}
 

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

@@ -111,7 +111,7 @@
                     routerLinkActive="active" (click)="closeMenu()" [ngbPopover]="view.name"
                     [disablePopover]="!slimSidebarEnabled" placement="end" container="body" triggers="mouseenter:mouseleave"
                     popoverClass="popover-slim">
-                    <i-bs class="me-2" name="funnel"></i-bs><span><div class="d-inline-flex view-name"><span class="overflow-hidden" [class.text-wrap]="!slimSidebarEnabled">{{view.name}}</span></div>
+                    <i-bs class="me-2" [name]="view.icon || 'funnel'"></i-bs><span><div class="d-inline-flex view-name"><span class="overflow-hidden" [class.text-wrap]="!slimSidebarEnabled">{{view.name}}</span></div>
                         @if (showSidebarCounts && !slimSidebarEnabled) {
                           <span class="badge bg-info text-dark ms-2 d-inline">{{ savedViewService.getDocumentCount(view) }}</span>
                         }

src-ui/src/app/components/common/input/custom-fields-values/custom-fields-values.component.spec.ts

@@ -52,10 +52,10 @@ describe('CustomFieldsValuesComponent', () => {
   })
 
   it('should set selectedFields and map values correctly', () => {
-    component.value = { 1: 'value1' }
-    component.selectedFields = [1, 2]
-    expect(component.selectedFields).toEqual([1, 2])
-    expect(component.value).toEqual({ 1: 'value1', 2: null })
+    component.value = { 1: 'value1', 3: 0, 4: false }
+    component.selectedFields = [1, 2, 3, 4]
+    expect(component.selectedFields).toEqual([1, 2, 3, 4])
+    expect(component.value).toEqual({ 1: 'value1', 2: null, 3: 0, 4: false })
   })
 
   it('should return the correct custom field by id', () => {

src-ui/src/app/components/common/input/custom-fields-values/custom-fields-values.component.ts

@@ -77,7 +77,7 @@ export class CustomFieldsValuesComponent extends AbstractInputComponent<Object>
     this._selectedFields = newFields
     // map the selected fields to an object with field_id as key and value as value
     this.value = newFields.reduce((acc, fieldId) => {
-      acc[fieldId] = this.value?.[fieldId] || null
+      acc[fieldId] = this.value?.[fieldId] ?? null
       return acc
     }, {})
     this.onChange(this.value)

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

@@ -36,7 +36,16 @@
           (focus)="clearLastSearchTerm()"
           (clear)="clearLastSearchTerm()"
           (blur)="onBlur()">
+          <ng-template ng-label-tmp let-item="item">
+            @if (iconField && item[iconField]) {
+              <i-bs class="me-2" [name]="item[iconField]"></i-bs>
+            }
+            <span [title]="item[bindLabel]">{{item[bindLabel]}}</span>
+          </ng-template>
           <ng-template ng-option-tmp let-item="item">
+              @if (iconField && item[iconField]) {
+                <i-bs class="me-2" [name]="item[iconField]"></i-bs>
+              }
               <span [title]="item[bindLabel]">{{item[bindLabel]}}</span>
           </ng-template>
         </ng-select>

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

@@ -35,7 +35,7 @@ import { AbstractInputComponent } from '../abstract-input'
     NgxBootstrapIconsModule,
   ],
 })
-export class SelectComponent extends AbstractInputComponent<number> {
+export class SelectComponent extends AbstractInputComponent<number | string> {
   constructor() {
     super()
     this.addItemRef = this.addItem.bind(this)
@@ -100,6 +100,9 @@ export class SelectComponent extends AbstractInputComponent<number> {
   @Input()
   bindLabel: string = 'name'
 
+  @Input()
+  iconField: string
+
   public searchFn = (term: string, item: any): boolean =>
     matchesSearchText(item?.[this.bindLabel], term)
 

src-ui/src/app/components/dashboard/widgets/saved-view-widget/saved-view-widget.component.html

@@ -1,6 +1,7 @@
 <pngx-widget-frame
   *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }"
   [title]="savedView.name"
+  [titleIcon]="savedView.icon || 'funnel'"
   [loading]="false"
   [draggable]="savedView"
   >

src-ui/src/app/components/dashboard/widgets/widget-frame/widget-frame.component.html

@@ -8,7 +8,12 @@
               <i-bs name="grip-vertical"></i-bs>
             </div>
           }
-          <h6 class="card-title mb-0">{{title()}}</h6>
+          <h6 class="card-title mb-0">
+            @if (titleIcon()) {
+              <i-bs class="me-2" [name]="titleIcon()"></i-bs>
+            }
+            {{title()}}
+          </h6>
           <ng-content select="[title-badge]"></ng-content>
           @if (badge() !== null && badge() !== undefined) {
             <span class="badge bg-info text-dark ms-2">{{badge()}}</span>

src-ui/src/app/components/dashboard/widgets/widget-frame/widget-frame.component.ts

@@ -16,6 +16,8 @@ export class WidgetFrameComponent implements AfterViewInit {
 
   title = input<string>()
 
+  titleIcon = input<string>()
+
   draggable = input<any>()
 
   cardless = input(false)

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

@@ -97,7 +97,9 @@
     <div class="dropdown-menu shadow dropdown-menu-right" ngbDropdownMenu>
       @if (!list.activeSavedViewId) {
         @for (view of savedViewService.allViews; track view) {
-          <button ngbDropdownItem (click)="loadViewConfig(view.id)">{{view.name}}</button>
+          <button ngbDropdownItem (click)="loadViewConfig(view.id)">
+            <i-bs class="me-2" [name]="view.icon || 'funnel'"></i-bs>{{view.name}}
+          </button>
         }
         @if (savedViewService.allViews.length > 0) {
           <div class="dropdown-divider"></div>

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

@@ -457,6 +457,7 @@ export class DocumentListComponent
       modal.componentInstance.buttonsEnabled.set(false)
       let savedView: SavedView = {
         name: formValue.name,
+        icon: formValue.icon,
         filter_rules: this.list.filterRules,
         sort_reverse: this.list.sortReverse,
         sort_field: this.list.sortField,

src-ui/src/app/components/document-list/save-view-config-dialog/save-view-config-dialog.component.html

@@ -6,6 +6,14 @@
   </div>
   <div class="modal-body">
     <pngx-input-text i18n-title title="Name" formControlName="name" [error]="error()?.name" autocomplete="off"></pngx-input-text>
+    <pngx-input-select
+      i18n-title
+      title="Icon"
+      formControlName="icon"
+      [items]="savedViewIcons"
+      iconField="icon"
+      [error]="error()?.icon">
+    </pngx-input-select>
     <pngx-input-check i18n-title title="Show in sidebar" formControlName="showInSideBar"></pngx-input-check>
     <pngx-input-check i18n-title title="Show on dashboard" formControlName="showOnDashboard"></pngx-input-check>
     <pngx-permissions-form accordion="true" formControlName="permissions_form"></pngx-permissions-form>

src-ui/src/app/components/document-list/save-view-config-dialog/save-view-config-dialog.component.spec.ts

@@ -9,6 +9,7 @@ import { CheckComponent } from '../../common/input/check/check.component'
 import { PermissionsFormComponent } from '../../common/input/permissions/permissions-form/permissions-form.component'
 import { PermissionsGroupComponent } from '../../common/input/permissions/permissions-group/permissions-group.component'
 import { PermissionsUserComponent } from '../../common/input/permissions/permissions-user/permissions-user.component'
+import { SelectComponent } from '../../common/input/select/select.component'
 import { TextComponent } from '../../common/input/text/text.component'
 import { SaveViewConfigDialogComponent } from './save-view-config-dialog.component'
 
@@ -40,6 +41,7 @@ describe('SaveViewConfigDialogComponent', () => {
         ReactiveFormsModule,
         SaveViewConfigDialogComponent,
         TextComponent,
+        SelectComponent,
         CheckComponent,
         PermissionsFormComponent,
         PermissionsUserComponent,
@@ -63,6 +65,7 @@ describe('SaveViewConfigDialogComponent', () => {
     expect(component.defaultName()).toEqual(name)
     expect(result).toEqual({
       name,
+      icon: 'funnel',
       showInSideBar: false,
       showOnDashboard: false,
     })
@@ -94,6 +97,7 @@ describe('SaveViewConfigDialogComponent', () => {
     component.save()
     expect(result).toEqual({
       name,
+      icon: 'funnel',
       showInSideBar: true,
       showOnDashboard: true,
     })
@@ -113,6 +117,7 @@ describe('SaveViewConfigDialogComponent', () => {
     component.save()
     expect(result).toEqual({
       name: '',
+      icon: 'funnel',
       showInSideBar: false,
       showOnDashboard: false,
       permissions_form: permissions,

src-ui/src/app/components/document-list/save-view-config-dialog/save-view-config-dialog.component.ts

@@ -13,9 +13,14 @@ import {
   ReactiveFormsModule,
 } from '@angular/forms'
 import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
+import {
+  DEFAULT_SAVED_VIEW_ICON,
+  SAVED_VIEW_ICONS,
+} from 'src/app/data/saved-view-icons'
 import { User } from 'src/app/data/user'
 import { CheckComponent } from '../../common/input/check/check.component'
 import { PermissionsFormComponent } from '../../common/input/permissions/permissions-form/permissions-form.component'
+import { SelectComponent } from '../../common/input/select/select.component'
 import { TextComponent } from '../../common/input/text/text.component'
 
 @Component({
@@ -24,6 +29,7 @@ import { TextComponent } from '../../common/input/text/text.component'
   styleUrls: ['./save-view-config-dialog.component.scss'],
   imports: [
     CheckComponent,
+    SelectComponent,
     TextComponent,
     PermissionsFormComponent,
     FormsModule,
@@ -41,6 +47,7 @@ export class SaveViewConfigDialogComponent implements OnInit {
   public saveClicked = new EventEmitter()
 
   users: User[]
+  readonly savedViewIcons = SAVED_VIEW_ICONS
 
   setDefaultName(value: string) {
     this.defaultName.set(value)
@@ -49,6 +56,7 @@ export class SaveViewConfigDialogComponent implements OnInit {
 
   saveViewConfigForm = new FormGroup({
     name: new FormControl(''),
+    icon: new FormControl(DEFAULT_SAVED_VIEW_ICON),
     showInSideBar: new FormControl(false),
     showOnDashboard: new FormControl(false),
     permissions_form: new FormControl(null),
@@ -65,6 +73,7 @@ export class SaveViewConfigDialogComponent implements OnInit {
     const formValue = this.saveViewConfigForm.value
     const saveViewConfig = {
       name: formValue.name,
+      icon: formValue.icon,
       showInSideBar: formValue.showInSideBar,
       showOnDashboard: formValue.showOnDashboard,
     }

src-ui/src/app/components/manage/saved-views/saved-views.component.html

@@ -7,15 +7,24 @@
 </pngx-page-header>
 <form [formGroup]="savedViewsForm" (ngSubmit)="save()">
   <ul class="list-group mb-3" formGroupName="savedViews">
-    @for (view of savedViews(); track view) {
+    @for (view of pagedSavedViews(); track view) {
       <li class="list-group-item py-3">
       <div [formGroupName]="view.id">
         <div class="row">
-          <div class="col">
+          <div class="col-md">
             <pngx-input-text title="Name" formControlName="name"></pngx-input-text>
           </div>
+          <div class="col-md">
+            <pngx-input-select
+            i18n-title
+            title="Icon"
+            formControlName="icon"
+            [items]="savedViewIcons"
+            iconField="icon">
+            </pngx-input-select>
+          </div>
           @if (canSaveSettings) {
-            <div class="col">
+            <div class="col-md">
               <div class="form-check form-switch mt-3">
                 <input type="checkbox" class="form-check-input" id="show_on_dashboard_{{view.id}}" formControlName="show_on_dashboard">
                 <label class="form-check-label" for="show_on_dashboard_{{view.id}}" i18n>Show on dashboard</label>
@@ -81,6 +90,11 @@
     }
   </ul>
 
-  <button type="button" (click)="reset()" class="btn btn-outline-secondary mb-2" [disabled]="(isDirty$ | async) === false" i18n>Cancel</button>
-  <button type="submit" class="btn btn-primary ms-2 mb-2" [disabled]="(isDirty$ | async) === false" i18n>Save</button>
+  <div class="d-flex align-items-center mb-3">
+    <button type="button" (click)="reset()" class="btn btn-outline-secondary mb-2" [disabled]="(isDirty$ | async) === false" i18n>Cancel</button>
+    <button type="submit" class="btn btn-primary ms-2 mb-2" [disabled]="(isDirty$ | async) === false" i18n>Save</button>
+    @if (savedViews()?.length > pageSize) {
+      <ngb-pagination class="ms-auto" [pageSize]="pageSize" [collectionSize]="savedViews().length" [page]="page()" [maxSize]="5" (pageChange)="page.set($event)" size="sm" aria-label="Pagination"></ngb-pagination>
+    }
+  </div>
 </form>

src-ui/src/app/components/manage/saved-views/saved-views.component.spec.ts

@@ -4,6 +4,7 @@ import { provideHttpClientTesting } from '@angular/common/http/testing'
 import { signal } from '@angular/core'
 import { ComponentFixture, TestBed } from '@angular/core/testing'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
+import { By } from '@angular/platform-browser'
 import { NgbModal, NgbModule } from '@ng-bootstrap/ng-bootstrap'
 import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
 import { Subject, of, throwError } from 'rxjs'
@@ -25,8 +26,20 @@ import { PageHeaderComponent } from '../../common/page-header/page-header.compon
 import { SavedViewsComponent } from './saved-views.component'
 
 const savedViews = [
-  { id: 1, name: 'view1', show_in_sidebar: true, show_on_dashboard: true },
-  { id: 2, name: 'view2', show_in_sidebar: false, show_on_dashboard: false },
+  {
+    id: 1,
+    name: 'view1',
+    icon: 'archive',
+    show_in_sidebar: true,
+    show_on_dashboard: true,
+  },
+  {
+    id: 2,
+    name: 'view2',
+    icon: 'funnel',
+    show_in_sidebar: false,
+    show_on_dashboard: false,
+  },
 ]
 
 describe('SavedViewsComponent', () => {
@@ -157,6 +170,24 @@ describe('SavedViewsComponent', () => {
     expect(patchBody.show_in_sidebar).toBeUndefined()
   })
 
+  it('should persist a changed icon', () => {
+    const patchSpy = jest.spyOn(savedViewService, 'patchMany')
+    const view = savedViews[0]
+    const iconControl = component.savedViewsForm
+      .get('savedViews')
+      .get(view.id.toString())
+      .get('icon')
+
+    iconControl.setValue('bell')
+    iconControl.markAsDirty()
+    component.save()
+
+    expect(patchSpy.mock.calls[0][0][0]).toMatchObject({
+      id: view.id,
+      icon: 'bell',
+    })
+  })
+
   it('should persist visibility changes to user settings', () => {
     const patchSpy = jest.spyOn(savedViewService, 'patchMany')
     const updateVisibilitySpy = jest
@@ -222,6 +253,44 @@ describe('SavedViewsComponent', () => {
     ).toEqual(view.show_on_dashboard)
   })
 
+  it('should page saved views, clamp the page if views are removed', () => {
+    const manyViews = Array.from({ length: 30 }, (_, i) => ({
+      id: i + 1,
+      name: `view${i + 1}`,
+    })) as SavedView[]
+    const listSpy = jest.spyOn(savedViewService, 'list').mockReturnValue(
+      of({
+        all: manyViews.map((v) => v.id),
+        count: manyViews.length,
+        results: manyViews.concat([]),
+      })
+    )
+    component.ngOnInit()
+    fixture.detectChanges()
+    expect(listSpy).toHaveBeenCalledWith(1, 100000, null, false, {
+      full_perms: true,
+    })
+    expect(component.pagedSavedViews()).toHaveLength(25)
+    expect(fixture.debugElement.query(By.css('ngb-pagination'))).not.toBeNull()
+    // all views have controls, not just the current page
+    expect(
+      Object.keys(component.savedViewsForm.get('savedViews').value)
+    ).toHaveLength(30)
+
+    component.page.set(2)
+    expect(component.pagedSavedViews()).toHaveLength(5)
+
+    listSpy.mockReturnValue(
+      of({
+        all: manyViews.slice(0, 25).map((v) => v.id),
+        count: 25,
+        results: manyViews.slice(0, 25),
+      })
+    )
+    component.ngOnInit()
+    expect(component.page()).toEqual(1)
+  })
+
   it('should support editing permissions', () => {
     const confirmClicked = new Subject<any>()
     const modalRef = {

src-ui/src/app/components/manage/saved-views/saved-views.component.ts

@@ -1,18 +1,29 @@
 import { AsyncPipe } from '@angular/common'
-import { Component, OnDestroy, OnInit, inject, signal } from '@angular/core'
+import {
+  Component,
+  OnDestroy,
+  OnInit,
+  computed,
+  inject,
+  signal,
+} from '@angular/core'
 import {
   FormControl,
   FormGroup,
   FormsModule,
   ReactiveFormsModule,
 } from '@angular/forms'
-import { NgbModal } from '@ng-bootstrap/ng-bootstrap'
+import { NgbModal, NgbPaginationModule } from '@ng-bootstrap/ng-bootstrap'
 import { dirtyCheck } from '@ngneat/dirty-check-forms'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
 import { BehaviorSubject, Observable, of, switchMap, takeUntil } from 'rxjs'
 import { PermissionsDialogComponent } from 'src/app/components/common/permissions-dialog/permissions-dialog.component'
 import { DisplayMode } from 'src/app/data/document'
 import { SavedView } from 'src/app/data/saved-view'
+import {
+  DEFAULT_SAVED_VIEW_ICON,
+  SAVED_VIEW_ICONS,
+} from 'src/app/data/saved-view-icons'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import {
   PermissionAction,
@@ -25,6 +36,7 @@ import { ToastService } from 'src/app/services/toast.service'
 import { ConfirmButtonComponent } from '../../common/confirm-button/confirm-button.component'
 import { DragDropSelectComponent } from '../../common/input/drag-drop-select/drag-drop-select.component'
 import { NumberComponent } from '../../common/input/number/number.component'
+import { SelectComponent } from '../../common/input/select/select.component'
 import { TextComponent } from '../../common/input/text/text.component'
 import { PageHeaderComponent } from '../../common/page-header/page-header.component'
 import { LoadingComponentWithPermissions } from '../../loading-component/loading.component'
@@ -36,12 +48,14 @@ import { LoadingComponentWithPermissions } from '../../loading-component/loading
     PageHeaderComponent,
     ConfirmButtonComponent,
     NumberComponent,
+    SelectComponent,
     TextComponent,
     IfPermissionsDirective,
     DragDropSelectComponent,
     FormsModule,
     ReactiveFormsModule,
     AsyncPipe,
+    NgbPaginationModule,
     NgxBootstrapIconsModule,
   ],
 })
@@ -56,8 +70,17 @@ export class SavedViewsComponent
   private readonly modalService = inject(NgbModal)
 
   DisplayMode = DisplayMode
+  readonly savedViewIcons = SAVED_VIEW_ICONS
 
   readonly savedViews = signal<SavedView[]>(undefined)
+  readonly page = signal(1)
+  public readonly pageSize = 25
+  // All views are loaded at init, so paging is only for display
+  readonly pagedSavedViews = computed(() => {
+    const start = (this.page() - 1) * this.pageSize
+    return this.savedViews()?.slice(start, start + this.pageSize)
+  })
+
   private savedViewsGroup = new FormGroup({})
   public savedViewsForm: FormGroup = new FormGroup({
     savedViews: this.savedViewsGroup,
@@ -84,9 +107,11 @@ export class SavedViewsComponent
   private reloadViews(): void {
     this.loading.set(true)
     this.savedViewService
-      .list(null, null, null, false, { full_perms: true })
+      .list(1, 100000, null, false, { full_perms: true })
       .subscribe((r) => {
         this.savedViews.set(r.results)
+        const pageCount = Math.ceil(r.results.length / this.pageSize)
+        this.page.update((page) => Math.min(page, Math.max(1, pageCount)))
         this.initialize()
       })
   }
@@ -110,6 +135,7 @@ export class SavedViewsComponent
       storeData.savedViews[view.id.toString()] = {
         id: view.id,
         name: view.name,
+        icon: view.icon ?? DEFAULT_SAVED_VIEW_ICON,
         show_on_dashboard: view.show_on_dashboard,
         show_in_sidebar: view.show_in_sidebar,
         page_size: view.page_size,
@@ -122,6 +148,7 @@ export class SavedViewsComponent
         new FormGroup({
           id: new FormControl({ value: null, disabled: !canEdit }),
           name: new FormControl({ value: null, disabled: !canEdit }),
+          icon: new FormControl({ value: null, disabled: !canEdit }),
           show_on_dashboard: new FormControl({
             value: null,
             disabled: false,
@@ -200,6 +227,7 @@ export class SavedViewsComponent
 
       const modelFieldsChanged =
         group.get('name')?.dirty ||
+        group.get('icon')?.dirty ||
         group.get('page_size')?.dirty ||
         group.get('display_mode')?.dirty ||
         group.get('display_fields')?.dirty

src-ui/src/app/data/saved-view-icons.ts

@@ -0,0 +1,89 @@
+export const DEFAULT_SAVED_VIEW_ICON = 'funnel'
+
+export const SAVED_VIEW_ICONS = [
+  { id: 'archive', name: $localize`Archive`, icon: 'archive' },
+  { id: 'bank', name: $localize`Bank`, icon: 'bank' },
+  { id: 'basket', name: $localize`Basket`, icon: 'basket' },
+  { id: 'bell', name: $localize`Bell`, icon: 'bell' },
+  { id: 'bookmark', name: $localize`Bookmark`, icon: 'bookmark' },
+  { id: 'boxes', name: $localize`Boxes`, icon: 'boxes' },
+  { id: 'briefcase', name: $localize`Briefcase`, icon: 'briefcase' },
+  { id: 'building', name: $localize`Building`, icon: 'building' },
+  { id: 'calculator', name: $localize`Calculator`, icon: 'calculator' },
+  { id: 'calendar', name: $localize`Calendar`, icon: 'calendar' },
+  { id: 'camera', name: $localize`Camera`, icon: 'camera' },
+  {
+    id: 'card-checklist',
+    name: $localize`Checklist`,
+    icon: 'card-checklist',
+  },
+  { id: 'cash', name: $localize`Cash`, icon: 'cash' },
+  { id: 'chat-left-text', name: $localize`Chat`, icon: 'chat-left-text' },
+  { id: 'check-circle', name: $localize`Check`, icon: 'check-circle' },
+  { id: 'clipboard', name: $localize`Clipboard`, icon: 'clipboard' },
+  { id: 'clock-history', name: $localize`Clock`, icon: 'clock-history' },
+  { id: 'credit-card', name: $localize`Credit card`, icon: 'credit-card' },
+  { id: 'download', name: $localize`Download`, icon: 'download' },
+  { id: 'envelope', name: $localize`Envelope`, icon: 'envelope' },
+  {
+    id: 'exclamation-triangle',
+    name: $localize`Warning`,
+    icon: 'exclamation-triangle',
+  },
+  { id: 'file-earmark', name: $localize`File`, icon: 'file-earmark' },
+  {
+    id: 'file-earmark-check',
+    name: $localize`Checked file`,
+    icon: 'file-earmark-check',
+  },
+  {
+    id: 'file-earmark-lock',
+    name: $localize`Locked file`,
+    icon: 'file-earmark-lock',
+  },
+  {
+    id: 'file-earmark-medical',
+    name: $localize`Medical file`,
+    icon: 'file-earmark-medical',
+  },
+  {
+    id: 'file-earmark-person',
+    name: $localize`Person file`,
+    icon: 'file-earmark-person',
+  },
+  {
+    id: 'file-earmark-spreadsheet',
+    name: $localize`Spreadsheet`,
+    icon: 'file-earmark-spreadsheet',
+  },
+  { id: 'file-text', name: $localize`Text file`, icon: 'file-text' },
+  { id: 'files', name: $localize`Files`, icon: 'files' },
+  { id: 'folder', name: $localize`Folder`, icon: 'folder' },
+  { id: 'funnel', name: $localize`Filter`, icon: 'funnel' },
+  { id: 'gear', name: $localize`Gear`, icon: 'gear' },
+  { id: 'globe2', name: $localize`Globe`, icon: 'globe2' },
+  { id: 'hash', name: $localize`Hash`, icon: 'hash' },
+  { id: 'heart', name: $localize`Heart`, icon: 'heart' },
+  { id: 'house', name: $localize`House`, icon: 'house' },
+  { id: 'inbox', name: $localize`Inbox`, icon: 'inbox' },
+  { id: 'journals', name: $localize`Journals`, icon: 'journals' },
+  { id: 'list-task', name: $localize`Task list`, icon: 'list-task' },
+  { id: 'newspaper', name: $localize`Newspaper`, icon: 'newspaper' },
+  { id: 'paperclip', name: $localize`Attachment`, icon: 'paperclip' },
+  { id: 'people', name: $localize`People`, icon: 'people' },
+  { id: 'person', name: $localize`Person`, icon: 'person' },
+  { id: 'printer', name: $localize`Printer`, icon: 'printer' },
+  { id: 'receipt', name: $localize`Receipt`, icon: 'receipt' },
+  { id: 'safe', name: $localize`Safe`, icon: 'safe' },
+  { id: 'search', name: $localize`Search`, icon: 'search' },
+  { id: 'send', name: $localize`Send`, icon: 'send' },
+  { id: 'shop', name: $localize`Shop`, icon: 'shop' },
+  { id: 'stack', name: $localize`Stack`, icon: 'stack' },
+  { id: 'stars', name: $localize`Stars`, icon: 'stars' },
+  { id: 'tag', name: $localize`Tag`, icon: 'tag' },
+  { id: 'tags', name: $localize`Tags`, icon: 'tags' },
+  { id: 'telephone', name: $localize`Telephone`, icon: 'telephone' },
+  { id: 'truck', name: $localize`Truck`, icon: 'truck' },
+  { id: 'upc-scan', name: $localize`Barcode`, icon: 'upc-scan' },
+  { id: 'wallet2', name: $localize`Wallet`, icon: 'wallet2' },
+]

src-ui/src/app/data/saved-view.ts

@@ -5,6 +5,8 @@ import { ObjectWithPermissions } from './object-with-permissions'
 export interface SavedView extends ObjectWithPermissions {
   name?: string
 
+  icon?: string
+
   show_on_dashboard?: boolean
 
   show_in_sidebar?: boolean

src-ui/src/main.ts

@@ -35,19 +35,27 @@ import {
   arrowRightShort,
   arrowUpRight,
   asterisk,
+  bank,
+  basket,
   bell,
   bodyText,
+  bookmark,
   boxArrowUp,
   boxArrowUpRight,
   boxes,
   braces,
+  briefcase,
+  building,
+  calculator,
   calendar,
   calendarEvent,
   calendarEventFill,
+  camera,
   cardChecklist,
   cardHeading,
   caretDown,
   caretUp,
+  cash,
   chatLeftText,
   chatSquareDots,
   check,
@@ -65,6 +73,7 @@ import {
   clipboardCheckFill,
   clipboardFill,
   clockHistory,
+  creditCard,
   dash,
   dashCircle,
   diagram3,
@@ -83,9 +92,12 @@ import {
   fileEarmarkDiff,
   fileEarmarkFill,
   fileEarmarkLock,
+  fileEarmarkMedical,
   fileEarmarkMinus,
+  fileEarmarkPerson,
   fileEarmarkPlus,
   fileEarmarkRichtext,
+  fileEarmarkSpreadsheet,
   fileText,
   files,
   filter,
@@ -93,12 +105,15 @@ import {
   folderFill,
   funnel,
   gear,
+  globe2,
   google,
   grid,
   gripVertical,
   hash,
   hddStack,
+  heart,
   house,
+  inbox,
   infoCircle,
   journals,
   link,
@@ -106,7 +121,9 @@ import {
   listTask,
   listUl,
   microsoft,
+  newspaper,
   nodePlus,
+  paperclip,
   pencil,
   people,
   peopleFill,
@@ -121,9 +138,12 @@ import {
   plusCircle,
   printer,
   questionCircle,
+  receipt,
+  safe,
   scissors,
   search,
   send,
+  shop,
   slashCircle,
   sliders2Vertical,
   sortAlphaDown,
@@ -133,14 +153,17 @@ import {
   tag,
   tagFill,
   tags,
+  telephone,
   textIndentLeft,
   textLeft,
   threeDots,
   threeDotsVertical,
   trash,
+  truck,
   uiRadios,
   unlock,
   upcScan,
+  wallet2,
   windowStack,
   x,
   xCircle,
@@ -258,15 +281,22 @@ const icons = {
   arrowRightShort,
   arrowUpRight,
   asterisk,
+  bank,
+  basket,
   bell,
   braces,
   bodyText,
+  bookmark,
   boxArrowUp,
   boxArrowUpRight,
   boxes,
+  briefcase,
+  building,
+  calculator,
   calendar,
   calendarEvent,
   calendarEventFill,
+  camera,
   cardChecklist,
   cardHeading,
   caretDown,
@@ -288,6 +318,8 @@ const icons = {
   clipboardCheckFill,
   clipboardFill,
   clockHistory,
+  cash,
+  creditCard,
   dash,
   dashCircle,
   diagram3,
@@ -306,9 +338,12 @@ const icons = {
   fileEarmarkDiff,
   fileEarmarkFill,
   fileEarmarkLock,
+  fileEarmarkMedical,
   fileEarmarkMinus,
+  fileEarmarkPerson,
   fileEarmarkPlus,
   fileEarmarkRichtext,
+  fileEarmarkSpreadsheet,
   files,
   fileText,
   filter,
@@ -316,12 +351,15 @@ const icons = {
   folderFill,
   funnel,
   gear,
+  globe2,
   google,
   grid,
   gripVertical,
   hash,
   hddStack,
+  heart,
   house,
+  inbox,
   infoCircle,
   journals,
   link,
@@ -329,8 +367,10 @@ const icons = {
   listTask,
   listUl,
   microsoft,
+  newspaper,
   nodePlus,
   pencil,
+  paperclip,
   people,
   peopleFill,
   person,
@@ -344,10 +384,13 @@ const icons = {
   plusCircle,
   printer,
   questionCircle,
+  receipt,
+  safe,
   scissors,
   search,
   send,
   slashCircle,
+  shop,
   sliders2Vertical,
   sortAlphaDown,
   sortAlphaUpAlt,
@@ -358,12 +401,15 @@ const icons = {
   tags,
   textIndentLeft,
   textLeft,
+  telephone,
   threeDots,
   threeDotsVertical,
   trash,
+  truck,
   uiRadios,
   unlock,
   upcScan,
+  wallet2,
   windowStack,
   x,
   xCircle,

src/documents/management/commands/document_fuzzy_match.py

@@ -55,7 +55,7 @@ class Command(PaperlessCommand):
             "--ratio",
             default=85.0,
             type=float,
-            help="Ratio to consider documents a match",
+            help="Ratio to consider documents a match (0.0 - 100.0)",
         )
         parser.add_argument(
             "--delete",
@@ -69,6 +69,17 @@ class Command(PaperlessCommand):
             action="store_true",
             help="Skip the confirmation prompt when used with --delete",
         )
+        parser.add_argument(
+            "--url",
+            default=None,
+            type=str,
+            help=(
+                "Base URL of the Paperless instance (e.g. "
+                "http://localhost:8000 or https://paperless.local). If set, matched "
+                "documents are shown as clickable (usually ctrl+click) links to "
+                "<url>/documents/<id>/details instead of by title."
+            ),
+        )
 
     def _render_results(
         self,
@@ -76,6 +87,7 @@ class Command(PaperlessCommand):
         *,
         opt_ratio: float,
         do_delete: bool,
+        base_url: str | None = None,
     ) -> list[int]:
         """Render match results as a Rich table. Returns list of PKs to delete."""
         if not matches:
@@ -88,13 +100,22 @@ class Command(PaperlessCommand):
             )
             return []
 
-        # Fetch titles for matched documents in a single query.
-        all_pks = {pk for m in matches for pk in (m.doc_one_pk, m.doc_two_pk)}
-        titles: dict[int, str] = dict(
-            Document.objects.filter(pk__in=all_pks)
-            .only("pk", "title")
-            .values_list("pk", "title"),
-        )
+        # Fetch titles for matched documents in a single query, unless we're
+        # going to show URLs instead.
+        titles: dict[int, str] = {}
+        if not base_url:
+            all_pks = {pk for m in matches for pk in (m.doc_one_pk, m.doc_two_pk)}
+            titles = dict(
+                Document.objects.filter(pk__in=all_pks)
+                .only("pk", "title")
+                .values_list("pk", "title"),
+            )
+
+        def _cell(pk: int) -> str:
+            if base_url:
+                doc_url = f"{base_url.rstrip('/')}/documents/{pk}/details"
+                return f"[link={doc_url}]{doc_url}[/link]"
+            return f"[dim]#{pk}[/dim] {titles.get(pk, 'Unknown')}"
 
         table = Table(
             title=f"Fuzzy Matches (threshold: {opt_ratio:.1f}%)",
@@ -124,8 +145,8 @@ class Command(PaperlessCommand):
 
             table.add_row(
                 str(i),
-                f"[dim]#{pk_a}[/dim] {titles.get(pk_a, 'Unknown')}",
-                f"[dim]#{pk_b}[/dim] {titles.get(pk_b, 'Unknown')}",
+                _cell(pk_a),
+                _cell(pk_b),
                 Text(f"{ratio:.1f}%", style=ratio_style),
             )
             maybe_delete_ids.append(pk_b)
@@ -208,6 +229,7 @@ class Command(PaperlessCommand):
             matches,
             opt_ratio=opt_ratio,
             do_delete=options["delete"],
+            base_url=options["url"],
         )
 
         if options["delete"] and maybe_delete_ids:

src/documents/migrations/0023_savedview_icon.py

@@ -0,0 +1,79 @@
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0022_add_perf_indexes"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="savedview",
+            name="icon",
+            field=models.CharField(
+                choices=[
+                    ("archive", "Archive"),
+                    ("bank", "Bank"),
+                    ("basket", "Basket"),
+                    ("bell", "Bell"),
+                    ("bookmark", "Bookmark"),
+                    ("boxes", "Boxes"),
+                    ("briefcase", "Briefcase"),
+                    ("building", "Building"),
+                    ("calculator", "Calculator"),
+                    ("calendar", "Calendar"),
+                    ("camera", "Camera"),
+                    ("card-checklist", "Checklist"),
+                    ("cash", "Cash"),
+                    ("chat-left-text", "Chat"),
+                    ("check-circle", "Check"),
+                    ("clipboard", "Clipboard"),
+                    ("clock-history", "Clock"),
+                    ("credit-card", "Credit card"),
+                    ("download", "Download"),
+                    ("envelope", "Envelope"),
+                    ("exclamation-triangle", "Warning"),
+                    ("file-earmark", "File"),
+                    ("file-earmark-check", "Checked file"),
+                    ("file-earmark-lock", "Locked file"),
+                    ("file-earmark-medical", "Medical file"),
+                    ("file-earmark-person", "Person file"),
+                    ("file-earmark-spreadsheet", "Spreadsheet"),
+                    ("file-text", "Text file"),
+                    ("files", "Files"),
+                    ("folder", "Folder"),
+                    ("funnel", "Filter"),
+                    ("gear", "Gear"),
+                    ("globe2", "Globe"),
+                    ("hash", "Hash"),
+                    ("heart", "Heart"),
+                    ("house", "House"),
+                    ("inbox", "Inbox"),
+                    ("journals", "Journals"),
+                    ("list-task", "Task list"),
+                    ("newspaper", "Newspaper"),
+                    ("paperclip", "Attachment"),
+                    ("people", "People"),
+                    ("person", "Person"),
+                    ("printer", "Printer"),
+                    ("receipt", "Receipt"),
+                    ("safe", "Safe"),
+                    ("search", "Search"),
+                    ("send", "Send"),
+                    ("shop", "Shop"),
+                    ("stack", "Stack"),
+                    ("stars", "Stars"),
+                    ("tag", "Tag"),
+                    ("tags", "Tags"),
+                    ("telephone", "Telephone"),
+                    ("truck", "Truck"),
+                    ("upc-scan", "Barcode"),
+                    ("wallet2", "Wallet"),
+                ],
+                default="funnel",
+                max_length=64,
+                verbose_name="icon",
+            ),
+        ),
+    ]

src/documents/models.py

@@ -519,6 +519,68 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
 
 
 class SavedView(ModelWithOwner):
+    class Icon(models.TextChoices):
+        ARCHIVE = ("archive", _("Archive"))
+        BANK = ("bank", _("Bank"))
+        BASKET = ("basket", _("Basket"))
+        BELL = ("bell", _("Bell"))
+        BOOKMARK = ("bookmark", _("Bookmark"))
+        BOXES = ("boxes", _("Boxes"))
+        BRIEFCASE = ("briefcase", _("Briefcase"))
+        BUILDING = ("building", _("Building"))
+        CALCULATOR = ("calculator", _("Calculator"))
+        CALENDAR = ("calendar", _("Calendar"))
+        CAMERA = ("camera", _("Camera"))
+        CARD_CHECKLIST = ("card-checklist", _("Checklist"))
+        CASH = ("cash", _("Cash"))
+        CHAT_LEFT_TEXT = ("chat-left-text", _("Chat"))
+        CHECK_CIRCLE = ("check-circle", _("Check"))
+        CLIPBOARD = ("clipboard", _("Clipboard"))
+        CLOCK_HISTORY = ("clock-history", _("Clock"))
+        CREDIT_CARD = ("credit-card", _("Credit card"))
+        DOWNLOAD = ("download", _("Download"))
+        ENVELOPE = ("envelope", _("Envelope"))
+        EXCLAMATION_TRIANGLE = ("exclamation-triangle", _("Warning"))
+        FILE_EARMARK = ("file-earmark", _("File"))
+        FILE_EARMARK_CHECK = ("file-earmark-check", _("Checked file"))
+        FILE_EARMARK_LOCK = ("file-earmark-lock", _("Locked file"))
+        FILE_EARMARK_MEDICAL = ("file-earmark-medical", _("Medical file"))
+        FILE_EARMARK_PERSON = ("file-earmark-person", _("Person file"))
+        FILE_EARMARK_SPREADSHEET = (
+            "file-earmark-spreadsheet",
+            _("Spreadsheet"),
+        )
+        FILE_TEXT = ("file-text", _("Text file"))
+        FILES = ("files", _("Files"))
+        FOLDER = ("folder", _("Folder"))
+        FUNNEL = ("funnel", _("Filter"))
+        GEAR = ("gear", _("Gear"))
+        GLOBE = ("globe2", _("Globe"))
+        HASH = ("hash", _("Hash"))
+        HEART = ("heart", _("Heart"))
+        HOUSE = ("house", _("House"))
+        INBOX = ("inbox", _("Inbox"))
+        JOURNALS = ("journals", _("Journals"))
+        LIST_TASK = ("list-task", _("Task list"))
+        NEWSPAPER = ("newspaper", _("Newspaper"))
+        PAPERCLIP = ("paperclip", _("Attachment"))
+        PEOPLE = ("people", _("People"))
+        PERSON = ("person", _("Person"))
+        PRINTER = ("printer", _("Printer"))
+        RECEIPT = ("receipt", _("Receipt"))
+        SAFE = ("safe", _("Safe"))
+        SEARCH = ("search", _("Search"))
+        SEND = ("send", _("Send"))
+        SHOP = ("shop", _("Shop"))
+        STACK = ("stack", _("Stack"))
+        STARS = ("stars", _("Stars"))
+        TAG = ("tag", _("Tag"))
+        TAGS = ("tags", _("Tags"))
+        TELEPHONE = ("telephone", _("Telephone"))
+        TRUCK = ("truck", _("Truck"))
+        UPC_SCAN = ("upc-scan", _("Barcode"))
+        WALLET = ("wallet2", _("Wallet"))
+
     class DisplayMode(models.TextChoices):
         TABLE = ("table", _("Table"))
         SMALL_CARDS = ("smallCards", _("Small Cards"))
@@ -541,6 +603,13 @@ class SavedView(ModelWithOwner):
 
     name = models.CharField(_("name"), max_length=128)
 
+    icon = models.CharField(
+        _("icon"),
+        max_length=64,
+        choices=Icon.choices,
+        default=Icon.FUNNEL,
+    )
+
     sort_field = models.CharField(
         _("sort field"),
         max_length=128,

src/documents/serialisers.py

@@ -1383,6 +1383,7 @@ class SavedViewSerializer(OwnedObjectSerializer):
         fields = [
             "id",
             "name",
+            "icon",
             "sort_field",
             "sort_reverse",
             "filter_rules",
@@ -3213,6 +3214,13 @@ class WorkflowActionSerializer(serializers.ModelSerializer[WorkflowAction]):
                         {"assign_title": f'Invalid f-string detected: "{e.args[0]}"'},
                     )
 
+        if attrs.get("assign_custom_fields_values"):
+            # Empty strings treated as None to avoid unexpected behavior
+            attrs["assign_custom_fields_values"] = {
+                field_id: (None if value == "" else value)
+                for field_id, value in attrs["assign_custom_fields_values"].items()
+            }
+
         if (
             "type" in attrs
             and attrs["type"] == WorkflowAction.WorkflowActionType.EMAIL

src/documents/tests/test_api_documents.py

@@ -2905,18 +2905,20 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
 
         v1 = SavedView.objects.get(name="test")
         self.assertEqual(v1.sort_field, "created2")
+        self.assertEqual(v1.icon, SavedView.Icon.FUNNEL)
         self.assertEqual(v1.filter_rules.count(), 1)
         self.assertEqual(v1.owner, self.user)
 
         response = self.client.patch(
             f"/api/saved_views/{v1.id}/",
-            {"sort_reverse": True},
+            {"sort_reverse": True, "icon": SavedView.Icon.RECEIPT},
             format="json",
         )
 
         v1 = SavedView.objects.get(id=v1.id)
         self.assertEqual(response.status_code, status.HTTP_200_OK)
         self.assertTrue(v1.sort_reverse)
+        self.assertEqual(v1.icon, SavedView.Icon.RECEIPT)
         self.assertEqual(v1.filter_rules.count(), 1)
 
         view["filter_rules"] = [{"rule_type": 12, "value": "secret"}]
@@ -2936,6 +2938,13 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         v1 = SavedView.objects.get(id=v1.id)
         self.assertEqual(v1.filter_rules.count(), 0)
 
+        response = self.client.patch(
+            f"/api/saved_views/{v1.id}/",
+            {"icon": "not-an-icon"},
+            format="json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+
     def test_saved_view_display_options(self) -> None:
         """
         GIVEN:

src/documents/tests/test_api_workflows.py

@@ -422,6 +422,11 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
             json.dumps(
                 {
                     "assign_title": "",
+                    "assign_custom_fields": [self.cf1.id, self.cf2.id],
+                    "assign_custom_fields_values": {
+                        str(self.cf1.id): "",
+                        str(self.cf2.id): 0,
+                    },
                 },
             ),
             content_type="application/json",
@@ -429,6 +434,10 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_201_CREATED)
         action = WorkflowAction.objects.get(id=response.data["id"])
         self.assertIsNone(action.assign_title)
+        self.assertEqual(
+            action.assign_custom_fields_values,
+            {str(self.cf1.id): None, str(self.cf2.id): 0},
+        )
 
         response = self.client.post(
             self.ENDPOINT_TRIGGERS,

src/documents/tests/test_management_fuzzy.py

@@ -1,3 +1,4 @@
+import os
 from io import StringIO
 from unittest.mock import patch
 
@@ -41,7 +42,7 @@ class TestFuzzyMatchCommand(TestCase):
 
     def test_invalid_ratio_upper_limit(self) -> None:
         """
-        GIVEN:s
+        GIVEN:
             - Invalid ratio above upper
         WHEN:
             - Command is called
@@ -108,6 +109,45 @@ class TestFuzzyMatchCommand(TestCase):
         stdout, _ = self.call_command("--processes", "1")
         self.assertIn("Found 1 matching pair(s)", stdout)
 
+    def test_with_matches_and_url(self) -> None:
+        """
+        GIVEN:
+            - 2 documents exist
+            - Similarity between content is 86.667
+            - --url is provided
+        WHEN:
+            - Command is called with --url
+        THEN:
+            - 1 match is returned from doc 1 to doc 2
+            - No match from doc 2 to doc 1 reported
+            - Output contains clickable links to the documents instead of titles
+        """
+        # Content similarity is 86.667
+        Document.objects.create(
+            checksum="BEEFCAFE",
+            title="A",
+            content="first document scanned by bob",
+            mime_type="application/pdf",
+            filename="test.pdf",
+        )
+        Document.objects.create(
+            checksum="DEADBEAF",
+            title="A",
+            content="first document scanned by alice",
+            mime_type="application/pdf",
+            filename="other_test.pdf",
+        )
+        with patch.dict(os.environ, {"COLUMNS": "200"}):
+            stdout, _ = self.call_command(
+                "--processes",
+                "1",
+                "--url",
+                "http://localhost:8000",
+            )
+        self.assertIn("Found 1 matching pair(s)", stdout)
+        self.assertIn("http://localhost:8000/documents/1/details", stdout)
+        self.assertIn("http://localhost:8000/documents/2/details", stdout)
+
     def test_with_3_matches(self) -> None:
         """
         GIVEN:

src/documents/tests/test_workflows.py

@@ -2000,6 +2000,55 @@ class TestWorkflows(
                 r"Doc added in \w{3,}",
             )  # Match any 3-letter month name
 
+    def test_document_updated_workflow_existing_custom_field_empty_value(self) -> None:
+        """
+        GIVEN:
+            - Existing workflow with UPDATED trigger and action that assigns a custom field
+              with an empty value
+        WHEN:
+            - Document is updated that already contains the field with a value
+        THEN:
+            - The existing value is left untouched, see GH #13627
+        """
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+            filter_has_document_type=self.dt,
+        )
+        action = WorkflowAction.objects.create()
+        action.assign_custom_fields.add(self.cf1)
+        action.assign_custom_fields_values = {self.cf1.pk: ""}
+        action.save()
+        w = Workflow.objects.create(
+            name="Workflow 1",
+            order=0,
+        )
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+        doc = Document.objects.create(
+            title="sample test",
+            correspondent=self.c,
+            original_filename="sample.pdf",
+        )
+        CustomFieldInstance.objects.create(
+            document=doc,
+            field=self.cf1,
+            value_text="existing value",
+        )
+
+        superuser = User.objects.create_superuser("superuser")
+        self.client.force_authenticate(user=superuser)
+
+        self.client.patch(
+            f"/api/documents/{doc.id}/",
+            {"document_type": self.dt.id},
+            format="json",
+        )
+
+        doc.refresh_from_db()
+        self.assertEqual(doc.custom_fields.get(field=self.cf1).value, "existing value")
+
     def test_document_updated_workflow_existing_custom_field(self) -> None:
         """
         GIVEN:

src/documents/views.py

@@ -2267,7 +2267,7 @@ class ChatStreamingView(GenericAPIView[Any]):
             if not has_perms_owner_aware(request.user, "view_document", document):
                 return HttpResponseForbidden("Insufficient permissions")
 
-            documents = [document]
+            documents = Document.objects.filter(pk=document.pk)
         else:
             documents = Document.objects.filter(
                 id__in=permitted_document_ids(request.user),

src/documents/workflows/mutations.py

@@ -105,7 +105,8 @@ def apply_assignment_to_document(
                 field=field,
                 document=document,
             ).first()
-            if instance and args[value_field_name] is not None:
+            # empty string is indistinguishable from no value in the UI
+            if instance and args[value_field_name] not in (None, ""):
                 setattr(instance, value_field_name, args[value_field_name])
                 instance.save()
             elif not instance:

src/paperless/parsers/remote.py

@@ -3,7 +3,9 @@ Built-in remote-OCR document parser.
 
 Handles documents by sending them to a configured remote OCR engine
 (currently Azure AI Vision / Document Intelligence) and retrieving both
-the extracted text and a searchable PDF with an embedded text layer.
+the extracted text and a searchable PDF with an embedded text layer. For
+born-digital PDFs that need no archive copy, the remote call is skipped
+entirely in favor of locally-extracted text (see ``RemoteDocumentParser.parse``).
 
 When no engine is configured, ``score()`` returns ``None`` so the parser
 is effectively invisible to the registry — the tesseract parser handles
@@ -22,6 +24,8 @@ from typing import Self
 from django.conf import settings
 
 from documents.parsers import ParseError
+from paperless.parsers.utils import extract_pdf_text
+from paperless.parsers.utils import post_process_text
 from paperless.version import __full_version_str__
 
 if TYPE_CHECKING:
@@ -70,8 +74,11 @@ class RemoteDocumentParser:
     """Parse documents via a remote OCR API (currently Azure AI Vision).
 
     This parser sends documents to a remote engine that returns both
-    extracted text and a searchable PDF with an embedded text layer.
-    It does not depend on Tesseract or ocrmypdf.
+    extracted text and a searchable PDF with an embedded text layer,
+    except when ``parse()`` is called with ``produce_archive=False`` for
+    a PDF, in which case the remote call is skipped and only locally
+    extracted text is returned (no archive). It does not depend on
+    Tesseract or ocrmypdf.
 
     Class attributes
     ----------------
@@ -160,8 +167,11 @@ class RemoteDocumentParser:
         Returns
         -------
         bool
-            Always True — the remote engine always returns a PDF with an
-            embedded text layer that serves as the archive copy.
+            Always True — the remote engine is capable of returning a PDF
+            with an embedded text layer to serve as the archive copy.
+            Whether it actually does so for a given document depends on
+            ``produce_archive`` passed to :meth:`parse` (see there for when
+            the remote engine call, and thus archive generation, is skipped).
         """
         return True
 
@@ -218,6 +228,12 @@ class RemoteDocumentParser:
     ) -> None:
         """Send the document to the remote engine and store results.
 
+        When *produce_archive* is False for a PDF, the caller (via
+        ``documents.consumer.should_produce_archive``) has already determined
+        that the document is born-digital and needs no archive — skip the
+        remote engine entirely rather than re-OCRing it and creating a
+        duplicate text layer.
+
         Parameters
         ----------
         document_path:
@@ -225,8 +241,8 @@ class RemoteDocumentParser:
         mime_type:
             Detected MIME type of the document.
         produce_archive:
-            Ignored — the remote engine always returns a searchable PDF,
-            which is stored as the archive copy regardless of this flag.
+            Whether an archive copy is wanted. For PDFs, False skips the
+            remote engine and uses locally-extracted text instead.
         """
         config = RemoteEngineConfig(
             engine=settings.REMOTE_OCR_ENGINE,
@@ -241,6 +257,16 @@ class RemoteDocumentParser:
             self._text = ""
             return
 
+        if not produce_archive and mime_type == "application/pdf":
+            logger.debug(
+                "Remote OCR: skipped — no archive requested, "
+                "using locally-extracted text",
+            )
+            self._text = (
+                post_process_text(extract_pdf_text(document_path, log=logger)) or ""
+            )
+            return
+
         if config.engine == "azureai":
             self._text = self._azure_ai_vision_parse(document_path, config)
 

src/paperless/tests/parsers/test_remote_parser.py

@@ -337,6 +337,117 @@ class TestRemoteParserParse:
         assert remote_parser.get_date() is None
 
 
+# ---------------------------------------------------------------------------
+# parse() — produce_archive=False skips the remote engine (PDFs only)
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserSkipsWhenNoArchiveWanted:
+    """When the caller has already decided no archive is needed for a PDF
+    (documents.consumer.should_produce_archive), the remote engine call is
+    skipped entirely in favor of locally-extracted text.
+    """
+
+    def test_pdf_skips_azure_when_no_archive_requested(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        """
+        GIVEN: produce_archive=False for a PDF
+        WHEN:  parse() is called
+        THEN:  Azure is never invoked, no archive is produced, and text
+               comes from local pdftotext extraction
+        """
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        azure_client.begin_analyze_document.assert_not_called()
+        assert remote_parser.get_archive_path() is None
+        assert remote_parser.get_text() != ""
+
+    def test_pdf_no_archive_requested_text_matches_local_extraction(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+        azure_client: Mock,
+        mocker: MockerFixture,
+    ) -> None:
+        """
+        GIVEN: produce_archive=False for a PDF
+        WHEN:  parse() is called
+        THEN:  the returned text is exactly the locally-extracted text,
+               not anything from the (unused) Azure mock
+        """
+        mocker.patch(
+            "paperless.parsers.remote.extract_pdf_text",
+            return_value="Local digital text.",
+        )
+
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        assert remote_parser.get_text() == "Local digital text."
+
+    def test_pdf_no_archive_requested_closes_no_client(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        azure_client.close.assert_not_called()
+
+    def test_non_pdf_still_calls_azure_when_no_archive_requested(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        """
+        Images have no local-text fallback, so produce_archive=False does
+        not skip the remote engine for non-PDF MIME types.
+        """
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "image/png",
+            produce_archive=False,
+        )
+
+        azure_client.begin_analyze_document.assert_called_once()
+        assert remote_parser.get_text() == _DEFAULT_TEXT
+
+    @pytest.mark.usefixtures("no_engine_settings")
+    def test_unconfigured_engine_takes_precedence_over_skip(
+        self,
+        remote_parser: RemoteDocumentParser,
+        simple_digital_pdf_file: Path,
+    ) -> None:
+        """An unconfigured engine still short-circuits before the
+        produce_archive check, returning empty text as before.
+        """
+        remote_parser.parse(
+            simple_digital_pdf_file,
+            "application/pdf",
+            produce_archive=False,
+        )
+
+        assert remote_parser.get_text() == ""
+        assert remote_parser.get_archive_path() is None
+
+
 # ---------------------------------------------------------------------------
 # parse() — Azure failure path
 # ---------------------------------------------------------------------------

src/paperless_ai/chat.py

@@ -2,6 +2,8 @@ import json
 import logging
 import sys
 
+from django.db.models import QuerySet
+
 from documents.models import Document
 from paperless.config import AIConfig
 from paperless_ai.client import AIClient
@@ -82,10 +84,21 @@ def _build_document_reference(
 
 
 def _get_document_references(
-    documents: list[Document],
+    documents: QuerySet[Document],
     top_nodes: list,
 ) -> list[dict[str, int | str]]:
-    allowed_documents = {doc.pk: doc for doc in documents}
+    candidate_ids: set[int] = set()
+    for node in top_nodes:
+        try:
+            candidate_ids.add(int(node.metadata["document_id"]))
+        except (KeyError, TypeError, ValueError):  # pragma: no cover
+            continue
+
+    if not candidate_ids:
+        return []
+
+    allowed_documents = {doc.pk: doc for doc in documents.filter(pk__in=candidate_ids)}
+
     references: list[dict[str, int | str]] = []
     seen_document_ids: set[int] = set()
 
@@ -119,7 +132,7 @@ def _format_chat_metadata_trailer(references: list[dict[str, int | str]]) -> str
 
 def stream_chat_with_documents(
     query_str: str,
-    documents: list[Document],
+    documents: QuerySet[Document],
     output_language: str | None = None,
 ):
     try:
@@ -135,10 +148,10 @@ def stream_chat_with_documents(
 
 def _stream_chat_with_documents(
     query_str: str,
-    documents: list[Document],
+    documents: QuerySet[Document],
     output_language: str | None = None,
 ):
-    if not documents:
+    if not documents.exists():
         yield CHAT_NO_CONTENT_MESSAGE
         return
 
@@ -148,7 +161,9 @@ def _stream_chat_with_documents(
     from llama_index.core.retrievers import VectorIndexRetriever
 
     config = AIConfig()
-    filters = _document_id_filters(str(doc.pk) for doc in documents)
+    filters = _document_id_filters(
+        str(pk) for pk in documents.values_list("pk", flat=True)
+    )
 
     # Hold the shared read lock for the whole operation: the query engine
     # retrieves from the vector store again during synthesis, so the connection

src/paperless_ai/indexing.py

@@ -24,6 +24,7 @@ from paperless_ai.embedding import get_configured_model_name
 from paperless_ai.embedding import get_embedding_model
 
 if TYPE_CHECKING:
+    from django.db.models import QuerySet
     from llama_index.core.schema import BaseNode
 
     from paperless_ai.vector_store import PaperlessSqliteVecVectorStore
@@ -252,6 +253,20 @@ def _safe_related_name(document: Document, field: str) -> str | None:
     return related.name if related else None
 
 
+def _document_index_queryset() -> "QuerySet[Document]":
+    """Document queryset with every relation build_document_node() /
+    build_llm_index_text() touches -- correspondent, document_type,
+    storage_path, tags, notes, custom_fields__field -- pre-loaded, so
+    indexing one document costs a fixed handful of queries regardless of
+    its tag or custom field count, instead of one query per related object.
+    """
+    return Document.objects.select_related(
+        "correspondent",
+        "document_type",
+        "storage_path",
+    ).prefetch_related("tags", "notes", "custom_fields__field")
+
+
 def build_document_node(
     document: Document,
     *,
@@ -425,11 +440,7 @@ def update_llm_index(
                 "Skipping LLM index update: migration check deferred; "
                 "will retry next run."
             )
-    documents = Document.objects.select_related(
-        "correspondent",
-        "document_type",
-        "storage_path",
-    ).prefetch_related("tags", "notes", "custom_fields__field")
+    documents = _document_index_queryset()
     no_documents = not documents.exists()
 
     # Fast exit before touching config: nothing to index and no existing index.
@@ -494,6 +505,21 @@ def update_llm_index(
 def llm_index_add_or_update_document(document: Document):
     """Add or atomically replace a document's chunks in the index."""
     config = AIConfig()
+    document_id = document.id
+    # Re-fetch with the same select_related/prefetch_related shape as the
+    # bulk path (update_llm_index()) uses: the caller's ``document`` instance
+    # (e.g. straight off a signal) has none of that loaded, and
+    # build_document_node()/build_llm_index_text() touch
+    # correspondent/document_type/storage_path/tags/notes/custom_fields__field
+    # -- without prefetching, that's one query per related object, including
+    # one per custom field instance.
+    document = _document_index_queryset().filter(pk=document_id).first()
+    if document is None:
+        logger.info(
+            "Skipping LLM index update for document %s: it no longer exists.",
+            document_id,
+        )
+        return
     new_nodes = build_document_node(
         document,
         chunk_size=config.llm_embedding_chunk_size,

src/paperless_ai/tests/test_ai_indexing.py

@@ -735,8 +735,71 @@ class TestLlmIndexAddOrUpdateDocumentEmptyContent:
         )
         mock_load = mocker.patch("paperless_ai.indexing.load_or_build_index")
 
-        doc = MagicMock(spec=Document)
-        doc.id = 42
+        doc = DocumentFactory.create()
+        # Must not raise
+        indexing.llm_index_add_or_update_document(doc)
+
+        mock_load.assert_not_called()
+
+
+@pytest.mark.django_db
+class TestLlmIndexAddOrUpdateDocumentPrefetch:
+    """llm_index_add_or_update_document must prefetch the relations
+    build_document_node()/build_llm_index_text() touch, not re-query per
+    tag/note/custom field.
+    """
+
+    def test_query_count_does_not_scale_with_custom_field_count(
+        self,
+        temp_llm_index_dir: Path,
+        mock_embed_model: FakeEmbedding,
+    ) -> None:
+        """
+        GIVEN a document with several custom fields, a note, and a tag
+        WHEN it is incrementally indexed via llm_index_add_or_update_document
+        THEN the query count stays flat instead of growing with the number
+             of custom fields -- a regression here would add one query per
+             custom field instance (instance.field.name unprefetched), see
+             build_llm_index_text().
+        """
+        doc = DocumentFactory.create()
+        Note.objects.create(document=doc, note="a note")
+        for i in range(5):
+            field = CustomField.objects.create(
+                name=f"Field {i}",
+                data_type=CustomField.FieldDataType.STRING,
+            )
+            CustomFieldInstance.objects.create(
+                document=doc,
+                field=field,
+                value_text="value",
+            )
+
+        with CaptureQueriesContext(connection) as ctx:
+            indexing.llm_index_add_or_update_document(doc)
+
+        # Flat regardless of custom field count -- an unprefetched
+        # custom_fields__field would add one query per instance (5 here) on
+        # top of this budget.
+        assert len(ctx.captured_queries) <= 10
+
+    def test_skips_write_when_document_no_longer_exists(
+        self,
+        temp_llm_index_dir: Path,
+        mock_embed_model: FakeEmbedding,
+        mocker: pytest_mock.MockerFixture,
+    ) -> None:
+        """
+        GIVEN a document that has been deleted since the caller looked it up
+             (e.g. a race between a signal firing and its async task running)
+        WHEN llm_index_add_or_update_document is called with that stale instance
+        THEN it skips the write instead of raising Document.DoesNotExist
+        """
+        doc = DocumentFactory.create()
+        doc_id = doc.pk
+        Document.objects.filter(pk=doc_id).delete()
+        mock_load = mocker.patch("paperless_ai.indexing.load_or_build_index")
+
         # Must not raise
         indexing.llm_index_add_or_update_document(doc)
 
@@ -793,8 +856,7 @@ class TestLlmIndexLocking:
             return_value=[mock_node],
         )
 
-        doc = MagicMock(spec=Document)
-        doc.id = 1
+        doc = DocumentFactory.create()
         indexing.llm_index_add_or_update_document(doc)
 
         mock_store.upsert_document.assert_called_once()
@@ -825,8 +887,7 @@ class TestLlmIndexLocking:
             return_value=[mock_node],
         )
 
-        doc = MagicMock(spec=Document)
-        doc.id = 1
+        doc = DocumentFactory.create()
         indexing.llm_index_add_or_update_document(doc)
 
         mock_store.upsert_document.assert_not_called()
@@ -863,8 +924,7 @@ class TestLlmIndexLocking:
             return_value=[mock_node],
         )
 
-        doc = MagicMock(spec=Document)
-        doc.id = 1
+        doc = DocumentFactory.create()
         indexing.llm_index_add_or_update_document(doc)
 
         mock_store.upsert_document.assert_not_called()

src/paperless_ai/tests/test_chat.py

@@ -3,10 +3,12 @@ from unittest.mock import MagicMock
 from unittest.mock import patch
 
 import pytest
+from django.db.models.signals import post_init
 from llama_index.core import settings as llama_settings
 from llama_index.core.embeddings.mock_embed_model import MockEmbedding
 from llama_index.core.schema import TextNode
 
+from documents.models import Document
 from documents.tests.factories import DocumentFactory
 from paperless_ai import chat
 from paperless_ai import indexing
@@ -36,16 +38,6 @@ def patch_embed_nodes():
         yield mock_embed_nodes
 
 
-@pytest.fixture
-def mock_document():
-    doc = MagicMock()
-    doc.pk = 1
-    doc.title = "Test Document"
-    doc.filename = "test_file.pdf"
-    doc.content = "This is the document content."
-    return doc
-
-
 def assert_chat_output(
     output: list[str],
     *,
@@ -61,6 +53,13 @@ def assert_chat_output(
     }
 
 
+def _fake_documents_queryset(pks: list[int]) -> MagicMock:
+    qs = MagicMock()
+    qs.exists.return_value = bool(pks)
+    qs.values_list.return_value = pks
+    return qs
+
+
 @pytest.mark.parametrize(
     ("output_language", "expected_language_line"),
     [
@@ -107,9 +106,10 @@ def test_build_refine_prompt(
 
 @pytest.mark.django_db
 def test_stream_chat_with_one_document_retrieval(
-    mock_document,
     patch_embed_nodes,
 ) -> None:
+    document = DocumentFactory.create(title="Test Document", content="ignored")
+    documents = Document.objects.filter(pk=document.pk)
     with (
         patch("paperless_ai.chat.AIClient") as mock_client_cls,
         patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
@@ -124,22 +124,19 @@ def test_stream_chat_with_one_document_retrieval(
         mock_client_cls.return_value = mock_client
         mock_client.llm = MagicMock()
 
-        mock_node = TextNode(
-            text="This is node content.",
-            metadata={"document_id": str(mock_document.pk), "title": "Test Document"},
-        )
         mock_index = MagicMock()
-        # Simulate get_nodes returning nodes (content exists)
-        mock_index.vector_store.get_nodes.return_value = [mock_node]
+        mock_index.vector_store.get_nodes.return_value = [
+            TextNode(
+                text="This is node content.",
+                metadata={"document_id": str(document.pk), "title": "Test Document"},
+            ),
+        ]
         mock_load_index.return_value = mock_index
 
         mock_retriever_instance = MagicMock()
         mock_retriever_instance.retrieve.return_value = [
             MagicMock(
-                metadata={
-                    "document_id": str(mock_document.pk),
-                    "title": "Test Document",
-                },
+                metadata={"document_id": str(document.pk), "title": "Test Document"},
             ),
         ]
 
@@ -153,7 +150,7 @@ def test_stream_chat_with_one_document_retrieval(
             "llama_index.core.retrievers.VectorIndexRetriever",
             return_value=mock_retriever_instance,
         ):
-            output = list(stream_chat_with_documents("What is this?", [mock_document]))
+            output = list(stream_chat_with_documents("What is this?", documents))
 
         mock_query_engine.query.assert_called_once_with("What is this?")
         synthesizer_kwargs = mock_get_response_synthesizer.call_args.kwargs
@@ -166,13 +163,16 @@ def test_stream_chat_with_one_document_retrieval(
             output,
             expected_chunks=["chunk1", "chunk2"],
             expected_references=[
-                {"id": mock_document.pk, "title": "Test Document"},
+                {"id": document.pk, "title": "Test Document"},
             ],
         )
 
 
 @pytest.mark.django_db
 def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> None:
+    doc1 = DocumentFactory.create(title="Document 1", content="ignored")
+    doc2 = DocumentFactory.create(title="Document 2", content="ignored")
+    documents = Document.objects.filter(pk__in=[doc1.pk, doc2.pk])
     with (
         patch("paperless_ai.chat.AIClient") as mock_client_cls,
         patch("paperless_ai.chat.load_or_build_index") as mock_load_index,
@@ -184,23 +184,23 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
         mock_client_cls.return_value = mock_client
         mock_client.llm = MagicMock()
 
-        mock_node1 = TextNode(
-            text="Content for doc 1.",
-            metadata={"document_id": "1", "title": "Document 1"},
-        )
-        mock_node2 = TextNode(
-            text="Content for doc 2.",
-            metadata={"document_id": "2", "title": "Document 2"},
-        )
         mock_index = MagicMock()
-        # Simulate get_nodes returning nodes (content exists)
-        mock_index.vector_store.get_nodes.return_value = [mock_node1, mock_node2]
+        mock_index.vector_store.get_nodes.return_value = [
+            TextNode(
+                text="Content for doc 1.",
+                metadata={"document_id": str(doc1.pk), "title": "Document 1"},
+            ),
+            TextNode(
+                text="Content for doc 2.",
+                metadata={"document_id": str(doc2.pk), "title": "Document 2"},
+            ),
+        ]
         mock_load_index.return_value = mock_index
 
         mock_retriever_instance = MagicMock()
         mock_retriever_instance.retrieve.return_value = [
-            MagicMock(metadata={"document_id": "1", "title": "Document 1"}),
-            MagicMock(metadata={"document_id": "2", "title": "Document 2"}),
+            MagicMock(metadata={"document_id": str(doc1.pk), "title": "Document 1"}),
+            MagicMock(metadata={"document_id": str(doc2.pk), "title": "Document 2"}),
         ]
 
         mock_response_stream = MagicMock()
@@ -210,14 +210,11 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
         mock_query_engine_cls.return_value = mock_query_engine
         mock_query_engine.query.return_value = mock_response_stream
 
-        doc1 = MagicMock(pk=1, title="Document 1", filename="doc1.pdf")
-        doc2 = MagicMock(pk=2, title="Document 2", filename="doc2.pdf")
-
         with patch(
             "llama_index.core.retrievers.VectorIndexRetriever",
             return_value=mock_retriever_instance,
         ):
-            output = list(stream_chat_with_documents("What's up?", [doc1, doc2]))
+            output = list(stream_chat_with_documents("What's up?", documents))
 
         mock_query_engine.query.assert_called_once_with("What's up?")
         patch_embed_nodes.assert_not_called()
@@ -225,15 +222,15 @@ def test_stream_chat_with_multiple_documents_retrieval(patch_embed_nodes) -> Non
             output,
             expected_chunks=["chunk1", "chunk2"],
             expected_references=[
-                {"id": 1, "title": "Document 1"},
-                {"id": 2, "title": "Document 2"},
+                {"id": doc1.pk, "title": "Document 1"},
+                {"id": doc2.pk, "title": "Document 2"},
             ],
         )
 
 
 def test_stream_chat_empty_document_list() -> None:
     with patch("paperless_ai.chat.load_or_build_index") as mock_load_index:
-        output = list(stream_chat_with_documents("Any info?", []))
+        output = list(stream_chat_with_documents("Any info?", Document.objects.none()))
         mock_load_index.assert_not_called()
         assert output == ["Sorry, I couldn't find any content to answer your question."]
 
@@ -253,7 +250,9 @@ def test_stream_chat_no_matching_nodes() -> None:
         mock_index.vector_store.get_nodes.return_value = []
         mock_load_index.return_value = mock_index
 
-        output = list(stream_chat_with_documents("Any info?", [MagicMock(pk=1)]))
+        output = list(
+            stream_chat_with_documents("Any info?", _fake_documents_queryset([1])),
+        )
 
         assert output == ["Sorry, I couldn't find any content to answer your question."]
 
@@ -282,7 +281,9 @@ def test_stream_chat_unexpected_failure_returns_generic_error(caplog) -> None:
             )
             mock_retriever_cls.return_value = mock_retriever
 
-            output = list(stream_chat_with_documents("Any info?", [MagicMock(pk=1)]))
+            output = list(
+                stream_chat_with_documents("Any info?", _fake_documents_queryset([1])),
+            )
 
         assert output == [CHAT_ERROR_MESSAGE]
         assert "Failed to stream document chat response" in caplog.text
@@ -298,7 +299,12 @@ class TestStreamChatRetrieval:
     ) -> None:
         doc = DocumentFactory.create(content="hello world")
         # Nothing indexed for this document yet.
-        out = list(chat.stream_chat_with_documents("question?", [doc]))
+        out = list(
+            chat.stream_chat_with_documents(
+                "question?",
+                Document.objects.filter(pk=doc.pk),
+            ),
+        )
         assert chat.CHAT_NO_CONTENT_MESSAGE in out
 
     def test_chat_filter_contains_only_requested_document_ids(
@@ -332,7 +338,12 @@ class TestStreamChatRetrieval:
             side_effect=capture_retriever,
         )
 
-        list(chat.stream_chat_with_documents("question?", [included]))
+        list(
+            chat.stream_chat_with_documents(
+                "question?",
+                Document.objects.filter(pk=included.pk),
+            ),
+        )
 
         assert captured_filters, "VectorIndexRetriever was never constructed"
         filt = captured_filters[0]
@@ -340,3 +351,47 @@ class TestStreamChatRetrieval:
         filter_values = filt.filters[0].value
         assert str(included.pk) in filter_values
         assert str(excluded.pk) not in filter_values
+
+    @pytest.mark.django_db
+    def test_get_document_references_only_queries_referenced_documents(
+        self,
+        django_assert_num_queries,
+    ) -> None:
+        """Building references must not hydrate every document the caller is
+        permitted to see -- only the (<= CHAT_RETRIEVER_TOP_K) documents that
+        the retriever actually returned nodes for.
+        """
+        referenced = DocumentFactory.create(title="Referenced Document")
+        # Many more documents are "accessible" but never referenced by a node.
+        DocumentFactory.create_batch(200)
+
+        documents = Document.objects.all()
+        top_nodes = [
+            MagicMock(
+                metadata={
+                    "document_id": str(referenced.pk),
+                    "title": "Referenced Document",
+                },
+            ),
+        ]
+
+        hydrated_count = 0
+
+        def _count_hydration(sender, instance, **kwargs):
+            nonlocal hydrated_count
+            hydrated_count += 1
+
+        post_init.connect(_count_hydration, sender=Document)
+        try:
+            # One query: `documents.filter(pk__in=candidate_ids)` for the single
+            # referenced id. No query should scale with the 200 unreferenced documents.
+            with django_assert_num_queries(1):
+                references = chat._get_document_references(documents, top_nodes)
+        finally:
+            post_init.disconnect(_count_hydration, sender=Document)
+
+        # The bug this guards against: the old code hydrated all 201 accessible
+        # documents via `{doc.pk: doc for doc in documents}` before filtering by
+        # top_nodes. Only the referenced document should ever be constructed.
+        assert hydrated_count == 1
+        assert references == [{"id": referenced.pk, "title": "Referenced Document"}]