Actually, fix the action dropdown thing

docs/api.md

@@ -301,7 +301,8 @@ The following methods are supported:
 - `delete`
   - No `parameters` required
 - `reprocess`
-  - No `parameters` required
+  - Optional `parameters`: `{ "remote_ocr": true }` to send the documents to the
+    remote OCR engine, see [Remote OCR](usage.md#remote-ocr). Defaults to false.
 - `set_permissions`
   - Requires `parameters`:
     - `"set_permissions": PERMISSIONS_OBJ` (see format [above](#permissions)) and / or

docs/usage.md

@@ -648,6 +648,19 @@ happened while it was still encrypted, that original version will likewise be mi
 **Current limitation**: Passwords are stored as a simple list without descriptions. To handle
 multiple PDF types with different passwords, create separate workflows for each use case.
 
+##### Remote OCR {#workflow-action-remote-ocr}
+
+"Remote OCR" actions send the document to the configured remote OCR engine instead of processing it
+locally. To use remote OCR selectively, set the [remote OCR mode](configuration.md#PAPERLESS_REMOTE_OCR_MODE)
+to `workflow_only` then add this action to a workflow that matches only the documents you
+want sent to the remote engine. See [Remote OCR](#remote-ocr) for the engine setup. The action only works with
+a **Consumption Started** trigger.
+
+The action takes no options, its presence is what enables remote OCR for a matching document.
+
+If the remote engine is not configured, or does not support the document's file type, the document is
+processed locally instead and a warning is written to the log.
+
 #### Workflow placeholders
 
 Titles and webhook payloads can be generated by workflows using [Jinja templates](https://jinja.palletsprojects.com/en/3.1.x/templates/).
@@ -1092,7 +1105,10 @@ or page limitations (e.g. with a free tier).
 
 By default, every document of a supported file type is sent to the remote engine. To use it more selectively, set the
 [remote OCR mode](configuration.md#PAPERLESS_REMOTE_OCR_MODE) to `workflow_only`. Documents are then processed locally
-unless a workflow explicitly enables remote OCR for them, so you can limit the remote engine to particular documents.
+unless a [remote OCR workflow action](#workflow-action-remote-ocr) enables it for them, so you can limit the remote
+engine to particular documents.
+
+Setting the mode to `workflow_only` also allows the **Reprocess** actions to selectively use remote OCR for individual documents.
 
 ## Architecture
 

src-ui/src/app/components/common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component.html

@@ -0,0 +1,28 @@
+<div class="modal-header">
+  <h4 class="modal-title" id="modal-basic-title">{{title}}</h4>
+  <button type="button" class="btn-close" aria-label="Close" (click)="cancel()">
+  </button>
+</div>
+<div class="modal-body">
+  @if (messageBold) {
+    <p class="text-break"><b>{{messageBold}}</b></p>
+  }
+  @if (message) {
+    <p class="mb-0 text-break" [innerHTML]="message"></p>
+  }
+  @if (showRemoteOcr) {
+    <div class="form-check mt-3">
+      <input class="form-check-input" type="checkbox" id="reprocessRemoteOcr" [(ngModel)]="remoteOcr" />
+      <label class="form-check-label" for="reprocessRemoteOcr" i18n>Use remote OCR</label>
+      <div class="form-text" i18n>Sends the document to the configured remote OCR service, which may incur costs.</div>
+    </div>
+  }
+</div>
+<div class="modal-footer">
+  <button type="button" class="btn" [class]="cancelBtnClass" (click)="cancel()" [disabled]="!buttonsEnabled">
+    <span class="d-inline-block" style="padding-bottom: 1px;">{{cancelBtnCaption}}</span>
+  </button>
+  <button type="button" class="btn" [class]="btnClass" (click)="confirm()" [disabled]="!confirmButtonEnabled || !buttonsEnabled">
+    {{btnCaption}}
+  </button>
+</div>

src-ui/src/app/components/common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component.spec.ts

@@ -0,0 +1,72 @@
+import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
+import { provideHttpClientTesting } from '@angular/common/http/testing'
+import { ComponentFixture, TestBed } from '@angular/core/testing'
+import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
+import { RemoteOCRModeConfig } from 'src/app/data/paperless-config'
+import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
+import { SettingsService } from 'src/app/services/settings.service'
+import { ReprocessConfirmDialogComponent } from './reprocess-confirm-dialog.component'
+
+describe('ReprocessConfirmDialogComponent', () => {
+  let component: ReprocessConfirmDialogComponent
+  let fixture: ComponentFixture<ReprocessConfirmDialogComponent>
+  let settingsService: SettingsService
+
+  const createComponent = (configured: boolean, mode: string) => {
+    settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, configured)
+    settingsService.set(SETTINGS_KEYS.REMOTE_OCR_MODE, mode)
+
+    fixture = TestBed.createComponent(ReprocessConfirmDialogComponent)
+    component = fixture.componentInstance
+    fixture.detectChanges()
+  }
+
+  beforeEach(async () => {
+    TestBed.configureTestingModule({
+      providers: [
+        NgbActiveModal,
+        provideHttpClient(withInterceptorsFromDi()),
+        provideHttpClientTesting(),
+      ],
+      imports: [ReprocessConfirmDialogComponent],
+    }).compileComponents()
+
+    settingsService = TestBed.inject(SettingsService)
+  })
+
+  it('should not request remote OCR by default', () => {
+    createComponent(true, RemoteOCRModeConfig.WORKFLOW_ONLY)
+
+    expect(component.remoteOcr).toBeFalsy()
+  })
+
+  it('should not offer remote OCR when no engine is configured', () => {
+    createComponent(false, RemoteOCRModeConfig.WORKFLOW_ONLY)
+
+    expect(component.showRemoteOcr).toBeFalsy()
+    expect(
+      fixture.nativeElement.querySelector('#reprocessRemoteOcr')
+    ).toBeNull()
+  })
+
+  it('should not offer remote OCR when it already handles every document', () => {
+    createComponent(true, RemoteOCRModeConfig.ALWAYS)
+
+    expect(component.showRemoteOcr).toBeFalsy()
+    expect(
+      fixture.nativeElement.querySelector('#reprocessRemoteOcr')
+    ).toBeNull()
+  })
+
+  it('should offer remote OCR when configured and selective', () => {
+    createComponent(true, RemoteOCRModeConfig.WORKFLOW_ONLY)
+
+    expect(component.showRemoteOcr).toBeTruthy()
+    const checkbox = fixture.nativeElement.querySelector('#reprocessRemoteOcr')
+    expect(checkbox).not.toBeNull()
+
+    checkbox.click()
+    fixture.detectChanges()
+    expect(component.remoteOcr).toBeTruthy()
+  })
+})

src-ui/src/app/components/common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component.ts

@@ -0,0 +1,20 @@
+import { Component, inject } from '@angular/core'
+import { FormsModule } from '@angular/forms'
+import { SettingsService } from 'src/app/services/settings.service'
+import { ConfirmDialogComponent } from '../confirm-dialog.component'
+
+@Component({
+  selector: 'pngx-reprocess-confirm-dialog',
+  templateUrl: './reprocess-confirm-dialog.component.html',
+  imports: [FormsModule],
+})
+export class ReprocessConfirmDialogComponent extends ConfirmDialogComponent {
+  private settings = inject(SettingsService)
+
+  remoteOcr: boolean = false
+
+  public get showRemoteOcr(): boolean {
+    // Hidden when it is not configured, or when it already handles every document anyway.
+    return this.settings.remoteOCRIsSelectable
+  }
+}

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

@@ -455,6 +455,13 @@
           </div>
         </div>
       }
+      @case (WorkflowActionType.RemoteOcr) {
+        <div class="row">
+          <div class="col">
+            <p class="text-muted small" i18n>The document will be sent to the configured remote OCR service. May incur costs.</p>
+          </div>
+        </div>
+      }
     }
   </div>
 </ng-template>

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

@@ -29,6 +29,7 @@ import {
   DocumentSource,
   WorkflowTriggerType,
 } from 'src/app/data/workflow-trigger'
+import { SETTINGS_KEYS } from 'src/app/data/ui-settings'
 import { IfOwnerDirective } from 'src/app/directives/if-owner.directive'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import { CorrespondentService } from 'src/app/services/rest/correspondent.service'
@@ -224,7 +225,12 @@ describe('WorkflowEditDialogComponent', () => {
     ).toEqual('Document Added')
     expect(component.getTriggerTypeOptionName(null)).toEqual('')
     expect(component.sourceOptions).toEqual(DOCUMENT_SOURCE_OPTIONS)
-    expect(component.actionTypeOptions).toEqual(WORKFLOW_ACTION_OPTIONS)
+    // Remote OCR is absent until the workflow has a consumption trigger
+    expect(component.actionTypeOptions).toEqual(
+      WORKFLOW_ACTION_OPTIONS.filter(
+        (a) => a.id !== WorkflowActionType.RemoteOcr
+      )
+    )
     expect(
       component.getActionTypeOptionName(WorkflowActionType.Assignment)
     ).toEqual('Assignment')
@@ -237,7 +243,104 @@ describe('WorkflowEditDialogComponent', () => {
     jest.spyOn(settingsService, 'get').mockReturnValue(false)
     component.ngOnInit()
     expect(component.actionTypeOptions).toEqual(
-      WORKFLOW_ACTION_OPTIONS.filter((a) => a.id !== WorkflowActionType.Email)
+      WORKFLOW_ACTION_OPTIONS.filter(
+        (a) =>
+          a.id !== WorkflowActionType.Email &&
+          a.id !== WorkflowActionType.RemoteOcr
+      )
+    )
+  })
+
+  it('should offer remote OCR only for consumption workflows', () => {
+    jest.spyOn(settingsService, 'get').mockReturnValue(true)
+
+    // A consumption trigger makes the action reachable
+    component.object = {
+      name: 'Workflow 1',
+      order: 0,
+      enabled: true,
+      triggers: [{ type: WorkflowTriggerType.Consumption }],
+      actions: [],
+    } as Workflow
+    component.ngOnInit()
+    expect(component.actionTypeOptions.map((a) => a.id)).toContain(
+      WorkflowActionType.RemoteOcr
+    )
+
+    // Any other trigger type runs after the document has been parsed
+    component.object = {
+      name: 'Workflow 2',
+      order: 0,
+      enabled: true,
+      triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
+      actions: [],
+    } as Workflow
+    component.ngOnInit()
+    expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
+      WorkflowActionType.RemoteOcr
+    )
+  })
+
+  it('should offer remote OCR on a trigger added to a new workflow', () => {
+    jest.spyOn(settingsService, 'get').mockReturnValue(true)
+    component.ngOnInit()
+
+    // Nothing for the action to apply to yet
+    expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
+      WorkflowActionType.RemoteOcr
+    )
+
+    // addTrigger creates the form field with emitEvent false, so the options
+    // have to be computed on read rather than cached from valueChanges
+    component.addTrigger()
+    expect(component.actionTypeOptions.map((a) => a.id)).toContain(
+      WorkflowActionType.RemoteOcr
+    )
+
+    // Switching that trigger to a type that runs after parsing removes it
+    component.triggerFields
+      .at(0)
+      .get('type')
+      .setValue(WorkflowTriggerType.DocumentAdded)
+    expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
+      WorkflowActionType.RemoteOcr
+    )
+  })
+
+  it('should keep remote OCR listed when an action already uses it', () => {
+    jest.spyOn(settingsService, 'get').mockReturnValue(true)
+
+    // Otherwise changing the trigger would silently blank the selection
+    component.object = {
+      name: 'Workflow 1',
+      order: 0,
+      enabled: true,
+      triggers: [{ type: WorkflowTriggerType.DocumentAdded }],
+      actions: [{ type: WorkflowActionType.RemoteOcr }],
+    } as Workflow
+    component.ngOnInit()
+
+    expect(component.actionTypeOptions.map((a) => a.id)).toContain(
+      WorkflowActionType.RemoteOcr
+    )
+  })
+
+  it('should not offer remote OCR when no engine is configured', () => {
+    jest
+      .spyOn(settingsService, 'get')
+      .mockImplementation((key) => key !== SETTINGS_KEYS.REMOTE_OCR_CONFIGURED)
+
+    component.object = {
+      name: 'Workflow 1',
+      order: 0,
+      enabled: true,
+      triggers: [{ type: WorkflowTriggerType.Consumption }],
+      actions: [],
+    } as Workflow
+    component.ngOnInit()
+
+    expect(component.actionTypeOptions.map((a) => a.id)).not.toContain(
+      WorkflowActionType.RemoteOcr
     )
   })
 

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

@@ -148,6 +148,10 @@ export const WORKFLOW_ACTION_OPTIONS = [
     id: WorkflowActionType.MoveToTrash,
     name: $localize`Move to trash`,
   },
+  {
+    id: WorkflowActionType.RemoteOcr,
+    name: $localize`Remote OCR`,
+  },
 ]
 
 export enum TriggerFilterType {
@@ -504,8 +508,6 @@ export class WorkflowEditDialogComponent
 
   expandedItem: number = null
 
-  readonly allowedActionTypes = signal([])
-
   private readonly triggerFilterOptionsMap = new WeakMap<
     FormArray,
     TriggerFilterOption[]
@@ -548,13 +550,40 @@ export class WorkflowEditDialogComponent
       this.checkRemovalActionFields.bind(this)
     )
     this.checkRemovalActionFields(this.objectForm.value)
-    this.allowedActionTypes.set(
+  }
-      this.settingsService.get(SETTINGS_KEYS.EMAIL_ENABLED)
+
-        ? WORKFLOW_ACTION_OPTIONS
+  private allowedActionTypes: typeof WORKFLOW_ACTION_OPTIONS = null
-        : WORKFLOW_ACTION_OPTIONS.filter(
+
-            (a) => a.id !== WorkflowActionType.Email
+  private getAllowedActionTypes() {
-          )
+    let allowed = WORKFLOW_ACTION_OPTIONS
-    )
+
+    if (!this.settingsService.get(SETTINGS_KEYS.EMAIL_ENABLED)) {
+      allowed = allowed.filter((a) => a.id !== WorkflowActionType.Email)
+    }
+
+    // Remote OCR is decided before the document is parsed, so it is only
+    // offered for workflows that run at consumption.
+    const formWorkflow: Workflow = this.objectForm?.value
+    const remoteOcrUsable =
+      this.settingsService.get(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED) &&
+      (formWorkflow?.triggers?.some(
+        (trigger) => trigger.type === WorkflowTriggerType.Consumption
+      ) ||
+        formWorkflow?.actions?.some(
+          (action) => action.type === WorkflowActionType.RemoteOcr
+        ))
+    if (!remoteOcrUsable) {
+      allowed = allowed.filter((a) => a.id !== WorkflowActionType.RemoteOcr)
+    }
+
+    if (
+      this.allowedActionTypes?.length === allowed.length &&
+      this.allowedActionTypes.every((a, i) => a.id === allowed[i].id)
+    ) {
+      return this.allowedActionTypes
+    }
+    this.allowedActionTypes = allowed
+    return allowed
   }
 
   private checkRemovalActionFields(formWorkflow: Workflow) {
@@ -1279,7 +1308,8 @@ export class WorkflowEditDialogComponent
 
   get actionTypeOptions() {
     this.settingsService.trackChanges()
-    return this.allowedActionTypes()
+    // Computed on read rather than cached
+    return this.getAllowedActionTypes()
   }
 
   getActionTypeOptionName(type: WorkflowActionType): string {

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

@@ -963,12 +963,24 @@ describe('DocumentDetailComponent', () => {
     component.reprocess()
     const modalCloseSpy = jest.spyOn(openModal, 'close')
     openModal.componentInstance.confirmClicked.next()
-    expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] })
+    expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }, false)
     expect(modalSpy).toHaveBeenCalled()
     expect(toastSpy).toHaveBeenCalled()
     expect(modalCloseSpy).toHaveBeenCalled()
   })
 
+  it('should pass remote OCR choice when reprocessing', () => {
+    initNormally()
+    const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')
+    reprocessSpy.mockReturnValue(of(true))
+    let openModal: NgbModalRef
+    modalService.activeInstances.subscribe((modal) => (openModal = modal[0]))
+    component.reprocess()
+    openModal.componentInstance.remoteOcr = true
+    openModal.componentInstance.confirmClicked.next()
+    expect(reprocessSpy).toHaveBeenCalledWith({ documents: [doc.id] }, true)
+  })
+
   it('should show error if redo ocr call fails', () => {
     initNormally()
     const reprocessSpy = jest.spyOn(documentService, 'reprocessDocuments')

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

@@ -97,6 +97,7 @@ import { ISODateAdapter } from 'src/app/utils/ngb-iso-date-adapter'
 import * as UTIF from 'utif'
 import { DocumentDetailFieldID } from '../admin/settings/settings.component'
 import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component'
+import { ReprocessConfirmDialogComponent } from '../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
 import { PasswordRemovalConfirmDialogComponent } from '../common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component'
 import { CustomFieldsDropdownComponent } from '../common/custom-fields-dropdown/custom-fields-dropdown.component'
 import { CorrespondentEditDialogComponent } from '../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
@@ -1402,7 +1403,7 @@ export class DocumentDetailComponent
   }
 
   reprocess() {
-    let modal = this.modalService.open(ConfirmDialogComponent, {
+    let modal = this.modalService.open(ReprocessConfirmDialogComponent, {
       backdrop: 'static',
     })
     modal.componentInstance.title = $localize`Reprocess confirm`
@@ -1413,7 +1414,10 @@ export class DocumentDetailComponent
     modal.componentInstance.confirmClicked.subscribe(() => {
       modal.componentInstance.buttonsEnabled = false
       this.documentsService
-        .reprocessDocuments({ documents: [this.document().id] })
+        .reprocessDocuments(
+          { documents: [this.document().id] },
+          modal.componentInstance.remoteOcr
+        )
         .subscribe({
           next: () => {
             this.toastService.showInfo(

src-ui/src/app/components/document-list/bulk-editor/bulk-editor.component.spec.ts

@@ -1122,6 +1122,7 @@ describe('BulkEditorComponent', () => {
     req.flush(true)
     expect(req.request.body).toEqual({
       documents: [3, 4],
+      remote_ocr: false,
     })
     httpTestingController.match(
       `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true&include_selection_data=true`

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

@@ -51,6 +51,7 @@ import { ToastService } from 'src/app/services/toast.service'
 import { flattenTags } from 'src/app/utils/flatten-tags'
 import { queryParamsFromFilterRules } from 'src/app/utils/query-params'
 import { MergeConfirmDialogComponent } from '../../common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component'
+import { ReprocessConfirmDialogComponent } from '../../common/confirm-dialog/reprocess-confirm-dialog/reprocess-confirm-dialog.component'
 import { RotateConfirmDialogComponent } from '../../common/confirm-dialog/rotate-confirm-dialog/rotate-confirm-dialog.component'
 import { CorrespondentEditDialogComponent } from '../../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
 import { CustomFieldEditDialogComponent } from '../../common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component'
@@ -909,7 +910,7 @@ export class BulkEditorComponent
   }
 
   reprocessSelected() {
-    let modal = this.modalService.open(ConfirmDialogComponent, {
+    let modal = this.modalService.open(ReprocessConfirmDialogComponent, {
       backdrop: 'static',
     })
     modal.componentInstance.title = $localize`Reprocess confirm`
@@ -923,7 +924,10 @@ export class BulkEditorComponent
         modal.componentInstance.buttonsEnabled = false
         this.executeDocumentAction(
           modal,
-          this.documentService.reprocessDocuments(this.getSelectionQuery())
+          this.documentService.reprocessDocuments(
+            this.getSelectionQuery(),
+            modal.componentInstance.remoteOcr
+          )
         )
       })
   }

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

@@ -1,5 +1,6 @@
 import { PdfEditorEditMode } from '../components/common/pdf-editor/pdf-editor-edit-mode'
 import { PdfZoomScale } from '../components/common/pdf-viewer/pdf-viewer.types'
+import { RemoteOCRModeConfig } from './paperless-config'
 import { User } from './user'
 
 export interface UiSettings {
@@ -94,6 +95,8 @@ export const SETTINGS_KEYS = {
   OUTLOOK_OAUTH_URL: 'outlook_oauth_url',
   EMAIL_ENABLED: 'email_enabled',
   AI_ENABLED: 'ai_enabled',
+  REMOTE_OCR_CONFIGURED: 'remote_ocr:configured',
+  REMOTE_OCR_MODE: 'remote_ocr:mode',
 }
 
 export const SETTINGS: UiSetting[] = [
@@ -347,4 +350,14 @@ export const SETTINGS: UiSetting[] = [
     type: 'string',
     default: PdfEditorEditMode.Create,
   },
+  {
+    key: SETTINGS_KEYS.REMOTE_OCR_CONFIGURED,
+    type: 'boolean',
+    default: false,
+  },
+  {
+    key: SETTINGS_KEYS.REMOTE_OCR_MODE,
+    type: 'string',
+    default: RemoteOCRModeConfig.ALWAYS,
+  },
 ]

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

@@ -7,6 +7,7 @@ export enum WorkflowActionType {
   Webhook = 4,
   PasswordRemoval = 5,
   MoveToTrash = 6,
+  RemoteOcr = 7,
 }
 
 export interface WorkflowActionEmail extends ObjectWithId {

src-ui/src/app/services/rest/document.service.spec.ts

@@ -284,6 +284,21 @@ describe(`DocumentService`, () => {
     expect(req.request.method).toEqual('POST')
     expect(req.request.body).toEqual({
       documents: ids,
+      remote_ocr: false,
+    })
+  })
+
+  it('should request remote OCR when reprocessing with it enabled', () => {
+    const ids = [1, 2, 3]
+    subscription = service
+      .reprocessDocuments({ documents: ids }, true)
+      .subscribe()
+    const req = httpTestingController.expectOne(
+      `${environment.apiBaseUrl}${endpoint}/reprocess/`
+    )
+    expect(req.request.body).toEqual({
+      documents: ids,
+      remote_ocr: true,
     })
   })
 

src-ui/src/app/services/rest/document.service.ts

@@ -349,9 +349,13 @@ export class DocumentService extends AbstractPaperlessService<Document> {
     })
   }
 
-  reprocessDocuments(selection: DocumentSelectionQuery) {
+  reprocessDocuments(
+    selection: DocumentSelectionQuery,
+    remoteOcr: boolean = false
+  ) {
     return this.http.post(this.getResourceUrl(null, 'reprocess'), {
       ...selection,
+      remote_ocr: remoteOcr,
     })
   }
 

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

@@ -13,6 +13,7 @@ import { environment } from 'src/environments/environment'
 import { CustomFieldDataType } from '../data/custom-field'
 import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document'
 import { SavedView } from '../data/saved-view'
+import { RemoteOCRModeConfig } from '../data/paperless-config'
 import { SETTINGS_KEYS, UiSettings } from '../data/ui-settings'
 import { PermissionsService } from './permissions.service'
 import { CustomFieldsService } from './rest/custom-fields.service'
@@ -434,4 +435,26 @@ describe('SettingsService', () => {
         ).name
     ).toEqual(customFields[0].name)
   })
+  it('should offer remote OCR only when configured and selective', () => {
+    settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, false)
+    settingsService.set(
+      SETTINGS_KEYS.REMOTE_OCR_MODE,
+      RemoteOCRModeConfig.WORKFLOW_ONLY
+    )
+    expect(settingsService.remoteOCRIsSelectable).toBeFalsy()
+
+    // configured, but already handling every document
+    settingsService.set(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED, true)
+    settingsService.set(
+      SETTINGS_KEYS.REMOTE_OCR_MODE,
+      RemoteOCRModeConfig.ALWAYS
+    )
+    expect(settingsService.remoteOCRIsSelectable).toBeFalsy()
+
+    settingsService.set(
+      SETTINGS_KEYS.REMOTE_OCR_MODE,
+      RemoteOCRModeConfig.WORKFLOW_ONLY
+    )
+    expect(settingsService.remoteOCRIsSelectable).toBeTruthy()
+  })
 })

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

@@ -19,6 +19,7 @@ import {
 } from 'src/app/utils/color'
 import { DEFAULT_APP_TITLE, environment } from 'src/environments/environment'
 import { DEFAULT_DISPLAY_FIELDS, DisplayField } from '../data/document'
+import { RemoteOCRModeConfig } from '../data/paperless-config'
 import { SavedView } from '../data/saved-view'
 import {
   PAPERLESS_GREEN_HEX,
@@ -687,6 +688,17 @@ export class SettingsService {
     return this.settingIsSet(SETTINGS_KEYS.UPDATE_CHECKING_ENABLED)
   }
 
+  /**
+   * Offering remote OCR as a  choice only makes sense when an engine
+   * is configured but is not already handling every document.
+   */
+  get remoteOCRIsSelectable(): boolean {
+    return (
+      this.get(SETTINGS_KEYS.REMOTE_OCR_CONFIGURED) &&
+      this.get(SETTINGS_KEYS.REMOTE_OCR_MODE) !== RemoteOCRModeConfig.ALWAYS
+    )
+  }
+
   offerTour(): boolean {
     return this.dashboardIsEmpty() && !this.get(SETTINGS_KEYS.TOUR_COMPLETE)
   }

src/documents/bulk_edit.py

@@ -394,10 +394,16 @@ def delete(doc_ids: list[int]) -> Literal["OK"]:
     return "OK"
 
 
-def reprocess(doc_ids: list[int]) -> Literal["OK"]:
+def reprocess(doc_ids: list[int], *, remote_ocr: bool = False) -> Literal["OK"]:
+    """
+    Re-run parsing for the given documents.
+
+    Consumption workflows do not run here, so ``remote_ocr`` is how the user
+    asks for the remote engine when it is not configured to handle everything.
+    """
     for document_id in doc_ids:
         update_document_content_maybe_archive_file.apply_async(
-            kwargs={"document_id": document_id},
+            kwargs={"document_id": document_id, "remote_ocr": remote_ocr},
             headers={"trigger_source": PaperlessTask.TriggerSource.MANUAL},
         )
 

src/documents/consumer.py

@@ -473,6 +473,16 @@ class ConsumerPlugin(
                     f"Unsupported mime type {mime_type}",
                 )
 
+            if self.metadata.remote_ocr and not getattr(
+                parser_class,
+                "uses_remote_service",
+                False,
+            ):
+                self.log.warning(
+                    "Remote OCR was requested for this document but no remote "
+                    "parser is available for it, processing locally instead.",
+                )
+
             # Notify all listeners that we're going to do some work.
 
             document_consumption_started.send(

src/documents/migrations/0023_alter_workflowaction_type.py

@@ -0,0 +1,30 @@
+# Generated by Django 5.2.16 on 2026-08-10 17:27
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0022_add_perf_indexes"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="workflowaction",
+            name="type",
+            field=models.PositiveSmallIntegerField(
+                choices=[
+                    (1, "Assignment"),
+                    (2, "Removal"),
+                    (3, "Email"),
+                    (4, "Webhook"),
+                    (5, "Password removal"),
+                    (6, "Move to trash"),
+                    (7, "Remote OCR"),
+                ],
+                default=1,
+                verbose_name="Workflow Action Type",
+            ),
+        ),
+    ]

src/documents/models.py

@@ -1599,6 +1599,10 @@ class WorkflowAction(models.Model):
             6,
             _("Move to trash"),
         )
+        REMOTE_OCR = (
+            7,
+            _("Remote OCR"),
+        )
 
     type = models.PositiveSmallIntegerField(
         _("Workflow Action Type"),

src/documents/serialisers.py

@@ -1744,7 +1744,7 @@ class DeleteDocumentsSerializer(DocumentSelectionSerializer):
 
 
 class ReprocessDocumentsSerializer(DocumentSelectionSerializer):
-    pass
+    remote_ocr = serializers.BooleanField(required=False, default=False)
 
 
 class BulkEditSerializer(
@@ -2086,6 +2086,13 @@ class BulkEditSerializer(
                         f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
                     )
 
+    def _validate_parameters_reprocess(self, parameters) -> None:
+        if "remote_ocr" in parameters:
+            if not isinstance(parameters["remote_ocr"], bool):
+                raise serializers.ValidationError("remote_ocr must be a boolean")
+        else:
+            parameters["remote_ocr"] = False
+
     def validate_parameters_remove_password(self, parameters):
         if "password" not in parameters:
             raise serializers.ValidationError("password not specified")
@@ -2150,6 +2157,8 @@ class BulkEditSerializer(
             self._validate_parameters_edit_pdf(parameters, attrs["documents"][0])
         elif method == bulk_edit.remove_password:
             self.validate_parameters_remove_password(parameters)
+        elif method == bulk_edit.reprocess:
+            self._validate_parameters_reprocess(parameters)
 
         return attrs
 
@@ -3268,6 +3277,26 @@ class WorkflowSerializer(serializers.ModelSerializer[Workflow]):
             "actions",
         ]
 
+    def validate(self, attrs):
+        attrs = super().validate(attrs)
+
+        triggers = attrs.get("triggers") or []
+        actions = attrs.get("actions") or []
+
+        # Remote OCR can only work with consumption triggers
+        if any(
+            action.get("type") == WorkflowAction.WorkflowActionType.REMOTE_OCR
+            for action in actions
+        ) and not any(
+            trigger.get("type") == WorkflowTrigger.WorkflowTriggerType.CONSUMPTION
+            for trigger in triggers
+        ):
+            raise serializers.ValidationError(
+                "Remote OCR actions require a consumption started trigger",
+            )
+
+        return attrs
+
     def update_triggers_and_actions(
         self,
         instance: Workflow,

src/documents/signals/handlers.py

@@ -971,6 +971,17 @@ def run_workflows(
                     )
                 elif action.type == WorkflowAction.WorkflowActionType.MOVE_TO_TRASH:
                     has_move_to_trash_action = True
+                elif action.type == WorkflowAction.WorkflowActionType.REMOTE_OCR:
+                    if use_overrides and overrides:
+                        overrides.remote_ocr = True
+                    else:
+                        # If a workflow has a consumption trigger *and* another type,
+                        # the document has already been parsed by the time the other one fires
+                        logger.debug(
+                            "Remote OCR action only applies to consumption "
+                            "triggers, ignoring",
+                            extra={"group": logging_group},
+                        )
 
             if not use_overrides:
                 # limit title to 128 characters

src/documents/tests/test_api_bulk_edit.py

@@ -532,7 +532,29 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         m.assert_called_once()
         args, kwargs = m.call_args
         self.assertEqual(args[0], [self.doc1.id])
-        self.assertEqual(len(kwargs), 0)
+        self.assertEqual(kwargs, {"remote_ocr": False})
+
+    @mock.patch("documents.views.bulk_edit.reprocess")
+    def test_reprocess_documents_endpoint_remote_ocr(self, m) -> None:
+        """
+        GIVEN:
+            - API data to reprocess a document with remote OCR requested
+        WHEN:
+            - API is called
+        THEN:
+            - reprocess is called with remote_ocr=True
+        """
+        self.setup_mock(m, "reprocess")
+        response = self.client.post(
+            "/api/documents/reprocess/",
+            json.dumps({"documents": [self.doc1.id], "remote_ocr": True}),
+            content_type="application/json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        m.assert_called_once()
+        args, kwargs = m.call_args
+        self.assertEqual(args[0], [self.doc1.id])
+        self.assertEqual(kwargs, {"remote_ocr": True})
 
     @mock.patch("documents.serialisers.bulk_edit.set_storage_path")
     def test_api_set_storage_path(self, m) -> None:
@@ -1553,6 +1575,29 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
                             ),
                         )
 
+    def test_legacy_bulk_edit_reprocess_invalid_remote_ocr(self) -> None:
+        """
+        GIVEN:
+            - The deprecated bulk_edit endpoint with a non-boolean remote_ocr
+        WHEN:
+            - API is called
+        THEN:
+            - The request is rejected rather than passed through to the task
+        """
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc1.id],
+                    "method": "reprocess",
+                    "parameters": {"remote_ocr": "yes please"},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+
     @mock.patch("documents.views.bulk_edit.edit_pdf")
     def test_edit_pdf(self, m) -> None:
         self.setup_mock(m, "edit_pdf")

src/documents/tests/test_api_uisettings.py

@@ -60,6 +60,10 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):
                 },
                 "email_enabled": False,
                 "ai_enabled": False,
+                "remote_ocr": {
+                    "configured": False,
+                    "mode": "always",
+                },
             },
         )
 
@@ -154,6 +158,50 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):
             str(response.data["settings"]),
         )
 
+    @override_settings(
+        REMOTE_OCR_ENGINE="azureai",
+        REMOTE_OCR_API_KEY="somekey",
+        REMOTE_OCR_ENDPOINT="https://example.cognitiveservices.azure.com",
+        REMOTE_OCR_MODE="workflow_only",
+    )
+    def test_settings_reports_remote_ocr_when_configured(self) -> None:
+        """
+        GIVEN:
+            - A fully configured remote OCR engine in workflow_only mode
+        WHEN:
+            - The ui_settings endpoint is called
+        THEN:
+            - The UI is told remote OCR is available and selective, so it can
+              offer it where it would actually change something
+        """
+        response = self.client.get(self.ENDPOINT, format="json")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertEqual(
+            response.data["settings"]["remote_ocr"],
+            {"configured": True, "mode": "workflow_only"},
+        )
+
+    @override_settings(
+        REMOTE_OCR_ENGINE="azureai",
+        REMOTE_OCR_API_KEY=None,
+        REMOTE_OCR_ENDPOINT=None,
+    )
+    def test_settings_reports_remote_ocr_incompletely_configured(self) -> None:
+        """
+        GIVEN:
+            - An engine named but missing its endpoint and API key
+        WHEN:
+            - The ui_settings endpoint is called
+        THEN:
+            - It is reported as not configured, matching what the parser
+              registry will actually do
+        """
+        response = self.client.get(self.ENDPOINT, format="json")
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+        self.assertFalse(response.data["settings"]["remote_ocr"]["configured"])
+
     @override_settings(
         OAUTH_CALLBACK_BASE_URL="http://localhost:8000",
         GMAIL_OAUTH_CLIENT_ID="abc123",

src/documents/tests/test_api_workflows.py

@@ -390,6 +390,82 @@ class TestApiWorkflows(DirectoriesMixin, APITestCase):
 
         self.assertEqual(Workflow.objects.count(), 1)
 
+    def test_api_create_remote_ocr_action_requires_consumption_trigger(
+        self,
+    ) -> None:
+        """
+        GIVEN:
+            - API request to create a workflow with a remote OCR action
+            - No consumption started trigger, so the action could never run
+        WHEN:
+            - API is called
+        THEN:
+            - Correct HTTP 400 response
+            - No objects are created
+        """
+        existing_count = Workflow.objects.count()
+
+        response = self.client.post(
+            self.ENDPOINT,
+            json.dumps(
+                {
+                    "name": "Remote OCR too late",
+                    "order": 1,
+                    "triggers": [
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+                        },
+                    ],
+                    "actions": [
+                        {
+                            "type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertEqual(Workflow.objects.count(), existing_count)
+
+    def test_api_create_remote_ocr_action_with_consumption_trigger(self) -> None:
+        """
+        GIVEN:
+            - API request to create a workflow with a remote OCR action
+            - A consumption started trigger alongside another trigger type
+        WHEN:
+            - API is called
+        THEN:
+            - The workflow is created, the action applies to consumption only
+        """
+        response = self.client.post(
+            self.ENDPOINT,
+            json.dumps(
+                {
+                    "name": "Remote OCR on consume",
+                    "order": 1,
+                    "triggers": [
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+                            "filter_filename": "*.pdf",
+                        },
+                        {
+                            "type": WorkflowTrigger.WorkflowTriggerType.DOCUMENT_ADDED,
+                        },
+                    ],
+                    "actions": [
+                        {
+                            "type": WorkflowAction.WorkflowActionType.REMOTE_OCR,
+                        },
+                    ],
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_201_CREATED)
+
     def test_api_create_workflow_trigger_action_empty_fields(self) -> None:
         """
         GIVEN:

src/documents/tests/test_bulk_edit.py

@@ -1782,3 +1782,56 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
         self.assertIn("wrong password", str(exc.exception))
         self.assertIn("Error removing password from document", cm.output[0])
+
+
+class TestBulkEditReprocess(DirectoriesMixin, TestCase):
+    def setUp(self) -> None:
+        super().setUp()
+
+        self.doc = Document.objects.create(
+            title="test",
+            checksum="A",
+            mime_type="application/pdf",
+        )
+
+    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
+    def test_reprocess_defaults_to_local(self, mock_task: mock.Mock) -> None:
+        """
+        GIVEN:
+            - A reprocess request that says nothing about remote OCR
+        WHEN:
+            - reprocess is called
+        THEN:
+            - The task is queued without asking for the remote engine
+        """
+        result = bulk_edit.reprocess([self.doc.id])
+
+        self.assertEqual(result, "OK")
+        mock_task.apply_async.assert_called_once()
+        _, kwargs = mock_task.apply_async.call_args
+        self.assertEqual(
+            kwargs["kwargs"],
+            {"document_id": self.doc.id, "remote_ocr": False},
+        )
+
+    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
+    def test_reprocess_passes_remote_ocr(self, mock_task: mock.Mock) -> None:
+        """
+        GIVEN:
+            - A reprocess request that explicitly asks for remote OCR
+        WHEN:
+            - reprocess is called
+        THEN:
+            - The request is forwarded to the task for every document
+        """
+        other = Document.objects.create(
+            title="test2",
+            checksum="B",
+            mime_type="application/pdf",
+        )
+
+        bulk_edit.reprocess([self.doc.id, other.id], remote_ocr=True)
+
+        self.assertEqual(mock_task.apply_async.call_count, 2)
+        for call in mock_task.apply_async.call_args_list:
+            self.assertTrue(call.kwargs["kwargs"]["remote_ocr"])

src/documents/tests/test_workflows.py

@@ -5360,3 +5360,82 @@ class TestDateWorkflowLocalization(
             document = Document.objects.first()
             assert document is not None
             assert document.title == expected_title
+
+
+class TestRemoteOCRWorkflowAction(DirectoriesMixin, SampleDirMixin, APITestCase):
+    def _make_workflow(self, trigger_type) -> None:
+        trigger = WorkflowTrigger.objects.create(type=trigger_type)
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
+        )
+        w = Workflow.objects.create(name="Remote OCR", order=0)
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+    def test_consumption_trigger_requests_remote_ocr(self) -> None:
+        """
+        GIVEN:
+            - A consumption workflow with a remote OCR action
+        WHEN:
+            - A matching document is consumed
+        THEN:
+            - The overrides ask for remote OCR, which is what the consumer
+              reads when choosing a parser
+        """
+        self._make_workflow(WorkflowTrigger.WorkflowTriggerType.CONSUMPTION)
+
+        test_file = shutil.copy(
+            self.SAMPLE_DIR / "simple.pdf",
+            self.dirs.scratch_dir / "simple.pdf",
+        )
+        overrides = DocumentMetadataOverrides()
+
+        run_workflows(
+            WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+            ConsumableDocument(
+                source=DocumentSource.ConsumeFolder,
+                original_file=test_file,
+            ),
+            overrides=overrides,
+        )
+
+        self.assertTrue(overrides.remote_ocr)
+
+    def test_other_trigger_types_are_ignored(self) -> None:
+        """
+        GIVEN:
+            - A workflow with a remote OCR action that also has a
+              non-consumption trigger, which is a valid combination
+        WHEN:
+            - The non-consumption trigger fires
+        THEN:
+            - The action is skipped, since the document has already been
+              parsed by this point
+        """
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
+        )
+        updated_trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+        )
+        action = WorkflowAction.objects.create(
+            type=WorkflowAction.WorkflowActionType.REMOTE_OCR,
+        )
+        w = Workflow.objects.create(name="Remote OCR", order=0)
+        w.triggers.add(trigger, updated_trigger)
+        w.actions.add(action)
+        w.save()
+
+        doc = Document.objects.create(
+            title="sample test",
+            original_filename="sample.pdf",
+        )
+
+        with self.assertLogs("paperless.handlers", level="DEBUG") as cm:
+            run_workflows(
+                WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+                doc,
+            )
+
+        self.assertIn("only applies to consumption triggers", "".join(cm.output))

src/documents/views.py

@@ -236,8 +236,10 @@ from paperless import version
 from paperless.celery import app as celery_app
 from paperless.config import AIConfig
 from paperless.config import GeneralConfig
+from paperless.config import RemoteOCRConfig
 from paperless.models import ApplicationConfiguration
 from paperless.parsers.registry import get_parser_registry
+from paperless.parsers.remote import RemoteEngineConfig
 from paperless.serialisers import GroupSerializer
 from paperless.serialisers import UserSerializer
 from paperless.views import StandardPagination
@@ -4010,6 +4012,11 @@ class UiSettingsView(GenericAPIView[Any]):
 
         ui_settings["auditlog_enabled"] = settings.AUDIT_LOG_ENABLED
 
+        ui_settings["remote_ocr"] = {
+            "configured": RemoteEngineConfig.from_app_config().engine_is_valid(),
+            "mode": RemoteOCRConfig().remote_ocr_mode,
+        }
+
         if settings.GMAIL_OAUTH_ENABLED or settings.OUTLOOK_OAUTH_ENABLED:
             manager = PaperlessMailOAuth2Manager()
             if settings.GMAIL_OAUTH_ENABLED: