mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-03 20:16:52 +00:00
community: better support of pathlib paths in document loaders (#18396)
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
This commit is contained in:
@@ -1,5 +1,6 @@
|
||||
"""Loads RST files."""
|
||||
from typing import Any, List
|
||||
from pathlib import Path
|
||||
from typing import Any, List, Union
|
||||
|
||||
from langchain_community.document_loaders.unstructured import (
|
||||
UnstructuredFileLoader,
|
||||
@@ -32,7 +33,10 @@ class UnstructuredRSTLoader(UnstructuredFileLoader):
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
||||
self,
|
||||
file_path: Union[str, Path],
|
||||
mode: str = "single",
|
||||
**unstructured_kwargs: Any,
|
||||
):
|
||||
"""
|
||||
Initialize with a file path.
|
||||
|
Reference in New Issue
Block a user