forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
14 lines
429 B
Python
14 lines
429 B
Python
"""Loader that loads Microsoft Word files."""
|
|
from typing import List
|
|
|
|
from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
|
|
|
|
|
class UnstructuredDocxLoader(UnstructuredFileLoader):
|
|
"""Loader that uses unstructured to load Microsoft Word files."""
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.docx import partition_docx
|
|
|
|
return partition_docx(filename=self.file_path)
|