github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-12 22:28:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

add encoding parameter to ObsidianLoader (#1752)

Browse Source
This commit is contained in:
Huang Chongdi 2023-03-20 00:48:31 +08:00 committed by GitHub
parent 3cf493b089
commit 08f23c95d9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
langchain/document_loaders/obsidian.py
View File

@ -9,16 +9,17 @@ from langchain.document_loaders.base import BaseLoader
class ObsidianLoader(BaseLoader): class ObsidianLoader(BaseLoader):
"""Loader that loads Obsidian files from disk.""" """Loader that loads Obsidian files from disk."""
def __init__(self, path: str): def __init__(self, path: str, encoding: str = "UTF-8"):
"""Initialize with path.""" """Initialize with path."""
self.file_path = path self.file_path = path
self.encoding = encoding
def load(self) -> List[Document]: def load(self) -> List[Document]:
"""Load documents.""" """Load documents."""
ps = list(Path(self.file_path).glob("**/*.md")) ps = list(Path(self.file_path).glob("**/*.md"))
docs = [] docs = []
for p in ps: for p in ps:
with open(p) as f: with open(p, encoding=self.encoding) as f:
text = f.read() text = f.read()
metadata = {"source": str(p)} metadata = {"source": str(p)}
docs.append(Document(page_content=text, metadata=metadata)) docs.append(Document(page_content=text, metadata=metadata))