feat: ocr (#18836)

* feat: add OCR functionality and related configurations

* chore: update labeler configuration for machine learning files

* feat(i18n): enhance OCR model descriptions and add orientation classification and unwarping features

* chore: update Dockerfile to include ccache for improved build performance

* feat(ocr): enhance OCR model configuration with orientation classification and unwarping options, update PaddleOCR integration, and improve response structure

* refactor(ocr): remove OCR_CLEANUP job from enum and type definitions

* refactor(ocr): remove obsolete OCR entity and migration files, and update asset job status and schema to accommodate new OCR table structure

* refactor(ocr): update OCR schema and response structure to use individual coordinates instead of bounding box, and adjust related service and repository files

* feat: enhance OCR configuration and functionality

- Updated OCR settings to include minimum detection box score, minimum detection score, and minimum recognition score.
- Refactored PaddleOCRecognizer to utilize new scoring parameters.
- Introduced new database tables for asset OCR data and search functionality.
- Modified related services and repositories to support the new OCR features.
- Updated translations for improved clarity in settings UI.

* sql changes

* use rapidocr

* change dto

* update web

* update lock

* update api

* store positions as normalized floats

* match column order in db

* update admin ui settings descriptions

fix max resolution key

set min threshold to 0.1

fix bind

* apply config correctly, adjust defaults

* unnecessary model type

* unnecessary sources

* fix(ocr): switch RapidOCR lang type from LangDet to LangRec

* fix(ocr): expose lang_type (LangRec.CH) and font_path on OcrOptions for RapidOCR

* fix(ocr): make OCR text search case- and accent-insensitive using ILIKE + unaccent

* fix(ocr): add OCR search fields

* fix: Add OCR database migration and update ML prediction logic.

* trigrams are already case insensitive

* add tests

* format

* update migrations

* wrong uuid function

* linting

* maybe fix medium tests

* formatting

* fix weblate check

* openapi

* sql

* minor fixes

* maybe fix medium tests part 2

* passing medium tests

* format web

* readd sql

* format dart

* disabled in e2e

* chore: translation ordering

---------

Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
Co-authored-by: Alex Tran <alex.tran1502@gmail.com>

web/src/lib/components/shared-components/search-bar/search-bar.svelte

@@ -107,7 +107,7 @@
 
   const onSubmit = () => {
     const searchType = getSearchType();
-    let payload: SmartSearchDto | MetadataSearchDto = {} as SmartSearchDto | MetadataSearchDto;
+    let payload = {} as SmartSearchDto | MetadataSearchDto;
 
     switch (searchType) {
       case 'smart': {
@@ -122,6 +122,10 @@
         payload = { description: value } as MetadataSearchDto;
         break;
       }
+      case 'ocr': {
+        payload = { ocr: value } as MetadataSearchDto;
+        break;
+      }
     }
 
     handlePromiseError(handleSearch(payload));
@@ -171,17 +175,14 @@
     onSubmit();
   };
 
-  function getSearchType(): 'smart' | 'metadata' | 'description' {
+  function getSearchType() {
     const searchType = localStorage.getItem('searchQueryType');
     switch (searchType) {
-      case 'smart': {
-        return 'smart';
-      }
-      case 'metadata': {
-        return 'metadata';
-      }
-      case 'description': {
-        return 'description';
+      case 'smart':
+      case 'metadata':
+      case 'description':
+      case 'ocr': {
+        return searchType;
       }
       default: {
         return 'smart';
@@ -201,6 +202,9 @@
       case 'description': {
         return $t('description');
       }
+      case 'ocr': {
+        return $t('ocr');
+      }
     }
   }
 </script>

web/src/lib/components/shared-components/search-bar/search-text-section.svelte

@@ -4,7 +4,7 @@
 
   interface Props {
     query: string | undefined;
-    queryType?: 'smart' | 'metadata' | 'description';
+    queryType?: 'smart' | 'metadata' | 'description' | 'ocr';
   }
 
   let { query = $bindable(), queryType = $bindable('smart') }: Props = $props();
@@ -28,6 +28,7 @@
       bind:group={queryType}
       value="description"
     />
+    <RadioButton name="query-type" id="ocr-radio" label={$t('ocr')} bind:group={queryType} value="ocr" />
   </div>
 </fieldset>
 
@@ -63,4 +64,15 @@
     bind:value={query}
     aria-labelledby="description-label"
   />
+{:else if queryType === 'ocr'}
+  <label for="ocr-input" class="immich-form-label">{$t('search_by_ocr')}</label>
+  <input
+    class="immich-form-input hover:cursor-text w-full !mt-1"
+    type="text"
+    id="ocr-input"
+    name="ocr"
+    placeholder={$t('search_by_ocr_example')}
+    bind:value={query}
+    aria-labelledby="ocr-label"
+  />
 {/if}