mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-19 21:33:31 -04:00
Leonid Ganeline
1feac83323
updated docstring for the `document_loaders` Maintainer responsibilities: - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
31 lines
1.1 KiB
Python
31 lines
1.1 KiB
Python
"""Loader that loads Microsoft Excel files."""
|
|
from typing import Any, List
|
|
|
|
from langchain.document_loaders.unstructured import (
|
|
UnstructuredFileLoader,
|
|
validate_unstructured_version,
|
|
)
|
|
|
|
|
|
class UnstructuredExcelLoader(UnstructuredFileLoader):
|
|
"""Loader that uses unstructured to load Microsoft Excel files."""
|
|
|
|
def __init__(
|
|
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
|
):
|
|
"""
|
|
|
|
Args:
|
|
file_path: The path to the Microsoft Excel file.
|
|
mode: The mode to use when partitioning the file. See unstructured docs
|
|
for more info. Optional. Defaults to "single".
|
|
**unstructured_kwargs: Keyword arguments to pass to unstructured.
|
|
"""
|
|
validate_unstructured_version(min_unstructured_version="0.6.7")
|
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.xlsx import partition_xlsx
|
|
|
|
return partition_xlsx(filename=self.file_path, **self.unstructured_kwargs)
|