Obsidian

ObsidianReader

Bases: BaseReader

Utilities for loading data from an Obsidian Vault.

Parameters:

Name	Type	Description	Default
input_dir	str	Path to the vault.	required

Source code in llama-index-integrations/readers/llama-index-readers-obsidian/llama_index/readers/obsidian/base.py

class ObsidianReader(BaseReader):
    """Utilities for loading data from an Obsidian Vault.

    Args:
        input_dir (str): Path to the vault.

    """

    def __init__(self, input_dir: str):
        """Init params."""
        self.input_dir = Path(input_dir)

    def load_data(self, *args: Any, **load_kwargs: Any) -> List[Document]:
        """Load data from the input directory."""
        docs: List[Document] = []
        for dirpath, dirnames, filenames in os.walk(self.input_dir):
            dirnames[:] = [d for d in dirnames if not d.startswith(".")]
            for filename in filenames:
                if filename.endswith(".md"):
                    filepath = os.path.join(dirpath, filename)
                    content = MarkdownReader().load_data(Path(filepath))
                    docs.extend(content)
        return docs

    def load_langchain_documents(self, **load_kwargs: Any) -> List["LCDocument"]:
        """Load data in LangChain document format."""
        docs = self.load_data(**load_kwargs)
        return [d.to_langchain_format() for d in docs]

load_data

load_data(*args: Any, **load_kwargs: Any) -> List[Document]

Load data from the input directory.

Source code in llama-index-integrations/readers/llama-index-readers-obsidian/llama_index/readers/obsidian/base.py

def load_data(self, *args: Any, **load_kwargs: Any) -> List[Document]:
    """Load data from the input directory."""
    docs: List[Document] = []
    for dirpath, dirnames, filenames in os.walk(self.input_dir):
        dirnames[:] = [d for d in dirnames if not d.startswith(".")]
        for filename in filenames:
            if filename.endswith(".md"):
                filepath = os.path.join(dirpath, filename)
                content = MarkdownReader().load_data(Path(filepath))
                docs.extend(content)
    return docs

load_langchain_documents

load_langchain_documents(**load_kwargs: Any) -> List[Document]

Load data in LangChain document format.

Source code in llama-index-integrations/readers/llama-index-readers-obsidian/llama_index/readers/obsidian/base.py

def load_langchain_documents(self, **load_kwargs: Any) -> List["LCDocument"]:
    """Load data in LangChain document format."""
    docs = self.load_data(**load_kwargs)
    return [d.to_langchain_format() for d in docs]