_utils/langchain_utils/Document_class.py

from setup.easy_imports import PyPDFLoader


class Document_Class:
    def load_pdf(self, pdf, ocr=False):
        return PyPDFLoader(pdf, extract_images=ocr).load()

    def load_and_split_pdf(self, pdf, ocr=False):
        return PyPDFLoader(pdf, extract_images=ocr).load_and_split()

    def get_pdf_text(self, pdf, ocr=False):
        document = self.load_pdf(pdf, ocr)
        texto = ""
        for x in document:
            texto += x.page_content
        return texto


document = Document_Class()