mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-08-26 16:55:38 -04:00
Leonid Ganeline
5eec74d9a5
- Updated docstrings for `document_loaders` - Mass update `"""Loader that loads` to `"""Loads` @baskaryan - please, review
39 lines
1.3 KiB
Python
39 lines
1.3 KiB
Python
"""Loads rich text files."""
|
|
from typing import Any, List
|
|
|
|
from langchain.document_loaders.unstructured import (
|
|
UnstructuredFileLoader,
|
|
satisfies_min_unstructured_version,
|
|
)
|
|
|
|
|
|
class UnstructuredRTFLoader(UnstructuredFileLoader):
|
|
"""Loader that uses unstructured to load rtf files."""
|
|
|
|
def __init__(
|
|
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
|
):
|
|
"""
|
|
Initialize with a file path.
|
|
|
|
Args:
|
|
file_path: The path to the file to load.
|
|
mode: The mode to use for partitioning. See unstructured for details.
|
|
Defaults to "single".
|
|
**unstructured_kwargs: Additional keyword arguments to pass
|
|
to unstructured.
|
|
"""
|
|
min_unstructured_version = "0.5.12"
|
|
if not satisfies_min_unstructured_version(min_unstructured_version):
|
|
raise ValueError(
|
|
"Partitioning rtf files is only supported in "
|
|
f"unstructured>={min_unstructured_version}."
|
|
)
|
|
|
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.rtf import partition_rtf
|
|
|
|
return partition_rtf(filename=self.file_path, **self.unstructured_kwargs)
|