Source code for langchain_community.document_loaders.notion

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):
    """加载`Notion目录`转储。"""

    def __init__(self, path: Union[str, Path], *, encoding: str = "utf-8") -> None:
        """使用文件路径进行初始化。"""
        self.file_path = path
        self.encoding = encoding

    def load(self) -> List[Document]:
        """加载文档。"""
        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