mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 21:12:48 +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:
@@ -1,7 +1,8 @@
|
||||
import os
|
||||
import tempfile
|
||||
from abc import ABC
|
||||
from typing import List
|
||||
from pathlib import Path
|
||||
from typing import List, Union
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import requests
|
||||
@@ -13,9 +14,9 @@ from langchain_community.document_loaders.parsers import VsdxParser
|
||||
|
||||
|
||||
class VsdxLoader(BaseLoader, ABC):
|
||||
def __init__(self, file_path: str):
|
||||
def __init__(self, file_path: Union[str, Path]):
|
||||
"""Initialize with file path."""
|
||||
self.file_path = file_path
|
||||
self.file_path = str(file_path)
|
||||
if "~" in self.file_path:
|
||||
self.file_path = os.path.expanduser(self.file_path)
|
||||
|
||||
|
Reference in New Issue
Block a user