jk-rag-python/rag/document_load/office_load.py

# import os

# from magic_pdf.data.data_reader_writer import FileBasedDataWriter, FileBasedDataReader
# from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
# from magic_pdf.data.read_api import read_local_office


# class MinerUParseOffice():
#     # def __init__(self, knowledge_id):
#     #     self.knowledge_id = knowledge_id

#     async def extract_text(self, file_path):
#         local_image_dir = "./tmp_file/images"
#         image_dir = str(os.path.basename(local_image_dir))

#         os.makedirs(local_image_dir, exist_ok=True)

#         image_writer = FileBasedDataWriter(local_image_dir)


#         ds = read_local_office(file_path)[0]  # 
#         infer_result = ds.apply(doc_analyze, ocr=True)
#         pipe_result = infer_result.pipe_ocr_mode(image_writer)
#         content_list_content = pipe_result.get_content_list(image_dir)

#         return content_list_content