mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-06 13:33:37 +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:
@@ -1,4 +1,5 @@
|
||||
from typing import List
|
||||
from pathlib import Path
|
||||
from typing import List, Union
|
||||
|
||||
from langchain_core.documents import Document
|
||||
|
||||
@@ -8,7 +9,7 @@ from langchain_community.document_loaders.base import BaseLoader
|
||||
class SRTLoader(BaseLoader):
|
||||
"""Load `.srt` (subtitle) files."""
|
||||
|
||||
def __init__(self, file_path: str):
|
||||
def __init__(self, file_path: Union[str, Path]):
|
||||
"""Initialize with a file path."""
|
||||
try:
|
||||
import pysrt # noqa:F401
|
||||
@@ -16,7 +17,7 @@ class SRTLoader(BaseLoader):
|
||||
raise ImportError(
|
||||
"package `pysrt` not found, please install it with `pip install pysrt`"
|
||||
)
|
||||
self.file_path = file_path
|
||||
self.file_path = str(file_path)
|
||||
|
||||
def load(self) -> List[Document]:
|
||||
"""Load using pysrt file."""
|
||||
|
Reference in New Issue
Block a user