Source code for langchain_core.documents.base

from __future__ import annotations

from typing import Any, List, Literal

from langchain_core.load.serializable import Serializable
from langchain_core.pydantic_v1 import Field


class Document(Serializable):
    """用于存储文本片段和相关元数据的类。"""

    page_content: str
    """字符串文本。"""
    metadata: dict = Field(default_factory=dict)
    """页面内容的任意元数据（例如，来源、与其他文档的关系等）。"""
    type: Literal["Document"] = "Document"

    def __init__(self, page_content: str, **kwargs: Any) -> None:
        """将page_content作为位置参数或命名参数传入。"""
        super().__init__(page_content=page_content, **kwargs)

    @classmethod
    def is_lc_serializable(cls) -> bool:
        """返回此类是否可序列化。"""
        return True

    @classmethod
    def get_lc_namespace(cls) -> List[str]:
        """获取langchain对象的命名空间。"""
        return ["langchain", "schema", "document"]