mirror of
https://github.com/hwchase17/langchain
synced 2024-11-02 09:40:22 +00:00
f7a1fd91b8
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
27 lines
834 B
Python
27 lines
834 B
Python
from pathlib import Path
|
|
from typing import List, Union
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
|
|
|
|
class NotionDirectoryLoader(BaseLoader):
|
|
"""Load `Notion directory` dump."""
|
|
|
|
def __init__(self, path: Union[str, Path], *, encoding: str = "utf-8") -> None:
|
|
"""Initialize with a file path."""
|
|
self.file_path = path
|
|
self.encoding = encoding
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load documents."""
|
|
paths = list(Path(self.file_path).glob("**/*.md"))
|
|
docs = []
|
|
for p in paths:
|
|
with open(p, encoding=self.encoding) as f:
|
|
text = f.read()
|
|
metadata = {"source": str(p)}
|
|
docs.append(Document(page_content=text, metadata=metadata))
|
|
return docs
|