Langchain

节点解析器。

LangchainNodeParser

基础： TextSplitter

Langchain 文本分割器的基本包装器。

TODO: 弄清楚如何使其支持元数据。

源代码位于 llama-index-core/llama_index/core/node_parser/text/langchain.py

class LangchainNodeParser(TextSplitter):
    """
    Basic wrapper around langchain's text splitter.

    TODO: Figure out how to make this metadata aware.
    """

    _lc_splitter: "LC_TextSplitter" = PrivateAttr()

    def __init__(
        self,
        lc_splitter: "LC_TextSplitter",
        callback_manager: Optional[CallbackManager] = None,
        include_metadata: bool = True,
        include_prev_next_rel: bool = True,
        id_func: Optional[Callable[[int, Document], str]] = None,
    ):
        """Initialize with parameters."""
        id_func = id_func or default_id_func

        super().__init__(
            callback_manager=callback_manager or CallbackManager(),
            include_metadata=include_metadata,
            include_prev_next_rel=include_prev_next_rel,
            id_func=id_func,
        )
        self._lc_splitter = lc_splitter

    def split_text(self, text: str) -> List[str]:
        """Split text into sentences."""
        return self._lc_splitter.split_text(text)

split_text

split_text(text: str) -> List[str]

将文本分割成句子。

源代码位于 llama-index-core/llama_index/core/node_parser/text/langchain.py

def split_text(self, text: str) -> List[str]:
    """Split text into sentences."""
    return self._lc_splitter.split_text(text)