diff --git a/rag/app/laws.py b/rag/app/laws.py index 4478696f5744763463063f57635a51133cc15008..ce0d1747197c7c875768cf01e8c168fb3a487505 100644 --- a/rag/app/laws.py +++ b/rag/app/laws.py @@ -25,8 +25,7 @@ from rag.settings import cron_logger class Docx(DocxParser): def __init__(self): - self.model_speciess = ParserType.LAWS.value - super().__init__() + pass def __clean(self, line): line = re.sub(r"\u3000", " ", line).strip() @@ -52,6 +51,10 @@ class Docx(DocxParser): class Pdf(PdfParser): + def __init__(self): + self.model_speciess = ParserType.LAWS.value + super().__init__() + def __call__(self, filename, binary=None, from_page=0, to_page=100000, zoomin=3, callback=None): callback(msg="OCR is running...")