mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
f7a1fd91b8
So this arose from the https://github.com/langchain-ai/langchain/pull/18397 problem of document loaders not supporting `pathlib.Path`. This pull request provides more uniform support for Path as an argument. The core ideas for this upgrade: - if there is a local file path used as an argument, it should be supported as `pathlib.Path` - if there are some external calls that may or may not support Pathlib, the argument is immidiately converted to `str` - if there `self.file_path` is used in a way that it allows for it to stay pathlib without conversion, is is only converted for the metadata. Twitter handle: https://twitter.com/mwmajewsk
51 lines
1.7 KiB
Python
51 lines
1.7 KiB
Python
"""Loads Microsoft Excel files."""
|
|
from pathlib import Path
|
|
from typing import Any, List, Union
|
|
|
|
from langchain_community.document_loaders.unstructured import (
|
|
UnstructuredFileLoader,
|
|
validate_unstructured_version,
|
|
)
|
|
|
|
|
|
class UnstructuredExcelLoader(UnstructuredFileLoader):
|
|
"""Load Microsoft Excel files using `Unstructured`.
|
|
|
|
Like other
|
|
Unstructured loaders, UnstructuredExcelLoader can be used in both
|
|
"single" and "elements" mode. If you use the loader in "elements"
|
|
mode, each sheet in the Excel file will be an Unstructured Table
|
|
element. If you use the loader in "single" mode, an
|
|
HTML representation of the table will be available in the
|
|
"text_as_html" key in the document metadata.
|
|
|
|
Examples
|
|
--------
|
|
from langchain_community.document_loaders.excel import UnstructuredExcelLoader
|
|
|
|
loader = UnstructuredExcelLoader("stanley-cups.xlsx", mode="elements")
|
|
docs = loader.load()
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
file_path: Union[str, Path],
|
|
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)
|