mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 04:55:14 +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 @@
|
||||
import logging
|
||||
from typing import Iterator, Optional
|
||||
from pathlib import Path
|
||||
from typing import Iterator, Optional, Union
|
||||
|
||||
from langchain_core.documents import Document
|
||||
|
||||
@@ -25,7 +26,7 @@ class TextLoader(BaseLoader):
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
file_path: str,
|
||||
file_path: Union[str, Path],
|
||||
encoding: Optional[str] = None,
|
||||
autodetect_encoding: bool = False,
|
||||
):
|
||||
@@ -56,5 +57,5 @@ class TextLoader(BaseLoader):
|
||||
except Exception as e:
|
||||
raise RuntimeError(f"Error loading {self.file_path}") from e
|
||||
|
||||
metadata = {"source": self.file_path}
|
||||
metadata = {"source": str(self.file_path)}
|
||||
yield Document(page_content=text, metadata=metadata)
|
||||
|
Reference in New Issue
Block a user