langchain_community.document_loaders.obsidian
.ObsidianLoader¶
- class langchain_community.document_loaders.obsidian.ObsidianLoader(path: str, encoding: str = 'UTF-8', collect_metadata: bool = True)[source]¶
Load Obsidian files from directory.
Initialize with a path.
- Parameters
path – Path to the directory containing the Obsidian files.
encoding – Charset encoding, defaults to “UTF-8”
collect_metadata – Whether to collect metadata from the front matter. Defaults to True.
Attributes
DATAVIEW_INLINE_BRACKET_REGEX
DATAVIEW_INLINE_PAREN_REGEX
DATAVIEW_LINE_REGEX
FRONT_MATTER_REGEX
TAG_REGEX
TEMPLATE_VARIABLE_REGEX
Methods
__init__
(path[, encoding, collect_metadata])Initialize with a path.
A lazy loader for Documents.
load
()Load documents.
load_and_split
([text_splitter])Load Documents and split into chunks.
- __init__(path: str, encoding: str = 'UTF-8', collect_metadata: bool = True)[source]¶
Initialize with a path.
- Parameters
path – Path to the directory containing the Obsidian files.
encoding – Charset encoding, defaults to “UTF-8”
collect_metadata – Whether to collect metadata from the front matter. Defaults to True.
- load_and_split(text_splitter: Optional[TextSplitter] = None) List[Document] ¶
Load Documents and split into chunks. Chunks are returned as Documents.
- Parameters
text_splitter – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.
- Returns
List of Documents.