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
55 lines
1.8 KiB
Python
55 lines
1.8 KiB
Python
from pathlib import Path
|
|
from typing import Any, List, Union
|
|
|
|
from langchain_community.document_loaders.unstructured import (
|
|
UnstructuredFileLoader,
|
|
validate_unstructured_version,
|
|
)
|
|
|
|
|
|
class UnstructuredODTLoader(UnstructuredFileLoader):
|
|
"""Load `OpenOffice ODT` files using `Unstructured`.
|
|
|
|
You can run the loader in one of two modes: "single" and "elements".
|
|
If you use "single" mode, the document will be returned as a single
|
|
langchain Document object. If you use "elements" mode, the unstructured
|
|
library will split the document into elements such as Title and NarrativeText.
|
|
You can pass in additional unstructured kwargs after mode to apply
|
|
different unstructured settings.
|
|
|
|
Examples
|
|
--------
|
|
from langchain_community.document_loaders import UnstructuredODTLoader
|
|
|
|
loader = UnstructuredODTLoader(
|
|
"example.odt", mode="elements", strategy="fast",
|
|
)
|
|
docs = loader.load()
|
|
|
|
References
|
|
----------
|
|
https://unstructured-io.github.io/unstructured/bricks.html#partition-odt
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
file_path: Union[str, Path],
|
|
mode: str = "single",
|
|
**unstructured_kwargs: Any,
|
|
):
|
|
"""
|
|
|
|
Args:
|
|
file_path: The path to the file to load.
|
|
mode: The mode to use when loading the file. Can be one of "single",
|
|
"multi", or "all". Default is "single".
|
|
**unstructured_kwargs: Any kwargs to pass to the unstructured.
|
|
"""
|
|
validate_unstructured_version(min_unstructured_version="0.6.3")
|
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.odt import partition_odt
|
|
|
|
return partition_odt(filename=self.file_path, **self.unstructured_kwargs)
|