docx document parsing problem

[neverlatetolearn0]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain_community.document_loaders import UnstructuredWordDocumentLoader, UnstructuredFileLoader


file_path = "example.docx"
loader = UnstructuredWordDocumentLoader(file_path)
data = loader.load()
word_text = loader.load()
word_content = word_text[0].page_content

Description

When loading a docx/doc document, display the table contents in their original format in page_content, rather than reading strictly line by line, and mix everything up so that I can't see the structure of the table

System Info

111