ninte commited on
Commit
b24d8fa
·
verified ·
1 Parent(s): ffbad7e

Update tools/ocr.py

Browse files
Files changed (1) hide show
  1. tools/ocr.py +12 -0
tools/ocr.py CHANGED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ def ocr_tool(image_path: str) -> str:
2
+ """Extracts text from images or scanned documents using OCR.
3
+ Args:
4
+ image_path: Path to the image file
5
+ """
6
+ try:
7
+ ocr_engine = PaddleOCR(use_angle_cls=True, lang='en')
8
+ result = ocr_engine.ocr(image_path, cls=True)
9
+ texts = [line[1][0] for line in result[0]] if result else []
10
+ return "\n".join(texts)
11
+ except Exception as e:
12
+ return f"OCR Error: {str(e)}"