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>

server/src/utils/database.ts

@@ -200,6 +200,14 @@ export function withFiles(eb: ExpressionBuilder<DB, 'asset'>, type?: AssetFileTy
   ).as('files');
 }
 
+export function withFilePath(eb: ExpressionBuilder<DB, 'asset'>, type: AssetFileType) {
+  return eb
+    .selectFrom('asset_file')
+    .select('asset_file.path')
+    .whereRef('asset_file.assetId', '=', 'asset.id')
+    .where('asset_file.type', '=', type);
+}
+
 export function withFacesAndPeople(eb: ExpressionBuilder<DB, 'asset'>, withDeletedFace?: boolean) {
   return jsonArrayFrom(
     eb
@@ -380,6 +388,11 @@ export function searchAssetBuilder(kysely: Kysely<DB>, options: AssetSearchBuild
         .innerJoin('asset_exif', 'asset.id', 'asset_exif.assetId')
         .where(sql`f_unaccent(asset_exif.description)`, 'ilike', sql`'%' || f_unaccent(${options.description}) || '%'`),
     )
+    .$if(!!options.ocr, (qb) =>
+      qb
+        .innerJoin('ocr_search', 'asset.id', 'ocr_search.assetId')
+        .where(() => sql`f_unaccent(ocr_search.text) %>> f_unaccent(${options.ocr!})`),
+    )
     .$if(!!options.type, (qb) => qb.where('asset.type', '=', options.type!))
     .$if(options.isFavorite !== undefined, (qb) => qb.where('asset.isFavorite', '=', options.isFavorite!))
     .$if(options.isOffline !== undefined, (qb) => qb.where('asset.isOffline', '=', options.isOffline!))