mirror of
				https://github.com/immich-app/immich.git
				synced 2025-11-04 03:27:09 -05:00 
			
		
		
		
	* 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>
		
			
				
	
	
		
			29 lines
		
	
	
		
			813 B
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			29 lines
		
	
	
		
			813 B
		
	
	
	
		
			Python
		
	
	
	
	
	
from typing import Any, Iterable
 | 
						|
 | 
						|
import numpy as np
 | 
						|
import numpy.typing as npt
 | 
						|
from rapidocr.utils.typings import EngineType, LangRec
 | 
						|
from typing_extensions import TypedDict
 | 
						|
 | 
						|
 | 
						|
class TextDetectionOutput(TypedDict):
 | 
						|
    image: npt.NDArray[np.float32]
 | 
						|
    boxes: npt.NDArray[np.float32]
 | 
						|
    scores: npt.NDArray[np.float32]
 | 
						|
 | 
						|
 | 
						|
class TextRecognitionOutput(TypedDict):
 | 
						|
    box: npt.NDArray[np.float32]
 | 
						|
    boxScore: npt.NDArray[np.float32]
 | 
						|
    text: Iterable[str]
 | 
						|
    textScore: npt.NDArray[np.float32]
 | 
						|
 | 
						|
 | 
						|
# RapidOCR expects `engine_type`, `lang_type`, and `font_path` to be attributes
 | 
						|
class OcrOptions(dict[str, Any]):
 | 
						|
    def __init__(self, **options: Any) -> None:
 | 
						|
        super().__init__(**options)
 | 
						|
        self.engine_type = EngineType.ONNXRUNTIME
 | 
						|
        self.lang_type = LangRec.CH
 | 
						|
        self.font_path = None
 |