mirror of
https://github.com/immich-app/immich.git
synced 2025-10-28 18:07:39 +09:00
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>
This commit is contained in:
@@ -696,6 +696,7 @@ export type AllJobStatusResponseDto = {
|
||||
metadataExtraction: JobStatusDto;
|
||||
migration: JobStatusDto;
|
||||
notifications: JobStatusDto;
|
||||
ocr: JobStatusDto;
|
||||
search: JobStatusDto;
|
||||
sidecar: JobStatusDto;
|
||||
smartSearch: JobStatusDto;
|
||||
@@ -926,6 +927,7 @@ export type MetadataSearchDto = {
|
||||
libraryId?: string | null;
|
||||
make?: string;
|
||||
model?: string | null;
|
||||
ocr?: string;
|
||||
order?: AssetOrder;
|
||||
originalFileName?: string;
|
||||
originalPath?: string;
|
||||
@@ -998,6 +1000,7 @@ export type RandomSearchDto = {
|
||||
libraryId?: string | null;
|
||||
make?: string;
|
||||
model?: string | null;
|
||||
ocr?: string;
|
||||
personIds?: string[];
|
||||
rating?: number;
|
||||
size?: number;
|
||||
@@ -1033,6 +1036,7 @@ export type SmartSearchDto = {
|
||||
libraryId?: string | null;
|
||||
make?: string;
|
||||
model?: string | null;
|
||||
ocr?: string;
|
||||
page?: number;
|
||||
personIds?: string[];
|
||||
query?: string;
|
||||
@@ -1069,6 +1073,7 @@ export type StatisticsSearchDto = {
|
||||
libraryId?: string | null;
|
||||
make?: string;
|
||||
model?: string | null;
|
||||
ocr?: string;
|
||||
personIds?: string[];
|
||||
rating?: number;
|
||||
state?: string | null;
|
||||
@@ -1135,6 +1140,7 @@ export type ServerFeaturesDto = {
|
||||
map: boolean;
|
||||
oauth: boolean;
|
||||
oauthAutoLaunch: boolean;
|
||||
ocr: boolean;
|
||||
passwordLogin: boolean;
|
||||
reverseGeocoding: boolean;
|
||||
search: boolean;
|
||||
@@ -1371,6 +1377,7 @@ export type SystemConfigJobDto = {
|
||||
metadataExtraction: JobSettingsDto;
|
||||
migration: JobSettingsDto;
|
||||
notifications: JobSettingsDto;
|
||||
ocr: JobSettingsDto;
|
||||
search: JobSettingsDto;
|
||||
sidecar: JobSettingsDto;
|
||||
smartSearch: JobSettingsDto;
|
||||
@@ -1412,12 +1419,20 @@ export type FacialRecognitionConfig = {
|
||||
minScore: number;
|
||||
modelName: string;
|
||||
};
|
||||
export type OcrConfig = {
|
||||
enabled: boolean;
|
||||
maxResolution: number;
|
||||
minDetectionScore: number;
|
||||
minRecognitionScore: number;
|
||||
modelName: string;
|
||||
};
|
||||
export type SystemConfigMachineLearningDto = {
|
||||
availabilityChecks: MachineLearningAvailabilityChecksDto;
|
||||
clip: ClipConfig;
|
||||
duplicateDetection: DuplicateDetectionConfig;
|
||||
enabled: boolean;
|
||||
facialRecognition: FacialRecognitionConfig;
|
||||
ocr: OcrConfig;
|
||||
urls: string[];
|
||||
};
|
||||
export type SystemConfigMapDto = {
|
||||
@@ -3399,7 +3414,7 @@ export function getExploreData(opts?: Oazapfts.RequestOpts) {
|
||||
/**
|
||||
* This endpoint requires the `asset.read` permission.
|
||||
*/
|
||||
export function searchLargeAssets({ albumIds, city, country, createdAfter, createdBefore, deviceId, isEncoded, isFavorite, isMotion, isNotInAlbum, isOffline, lensModel, libraryId, make, minFileSize, model, personIds, rating, size, state, tagIds, takenAfter, takenBefore, trashedAfter, trashedBefore, $type, updatedAfter, updatedBefore, visibility, withDeleted, withExif }: {
|
||||
export function searchLargeAssets({ albumIds, city, country, createdAfter, createdBefore, deviceId, isEncoded, isFavorite, isMotion, isNotInAlbum, isOffline, lensModel, libraryId, make, minFileSize, model, ocr, personIds, rating, size, state, tagIds, takenAfter, takenBefore, trashedAfter, trashedBefore, $type, updatedAfter, updatedBefore, visibility, withDeleted, withExif }: {
|
||||
albumIds?: string[];
|
||||
city?: string | null;
|
||||
country?: string | null;
|
||||
@@ -3416,6 +3431,7 @@ export function searchLargeAssets({ albumIds, city, country, createdAfter, creat
|
||||
make?: string;
|
||||
minFileSize?: number;
|
||||
model?: string | null;
|
||||
ocr?: string;
|
||||
personIds?: string[];
|
||||
rating?: number;
|
||||
size?: number;
|
||||
@@ -3452,6 +3468,7 @@ export function searchLargeAssets({ albumIds, city, country, createdAfter, creat
|
||||
make,
|
||||
minFileSize,
|
||||
model,
|
||||
ocr,
|
||||
personIds,
|
||||
rating,
|
||||
size,
|
||||
@@ -4901,7 +4918,8 @@ export enum JobName {
|
||||
Sidecar = "sidecar",
|
||||
Library = "library",
|
||||
Notifications = "notifications",
|
||||
BackupDatabase = "backupDatabase"
|
||||
BackupDatabase = "backupDatabase",
|
||||
Ocr = "ocr"
|
||||
}
|
||||
export enum JobCommand {
|
||||
Start = "start",
|
||||
|
||||
Reference in New Issue
Block a user