init() — langchain Function Reference

Architecture documentation for the __init__() function in html.py from the langchain codebase.

Function python DocumentProcessing TextSplitters

Entity Profile

DocumentProcessing→ TextSplitters→ __init__() — langchain Function Reference

Dependency Diagram

graph TD
  884c7870_4829_e49a_c22a_6f89bea245e3["__init__()"]
  0c8a5f97_7cb0_fe24_746d_9689c4e5426c["HTMLSectionSplitter"]
  884c7870_4829_e49a_c22a_6f89bea245e3 -->|defined in| 0c8a5f97_7cb0_fe24_746d_9689c4e5426c
  style 884c7870_4829_e49a_c22a_6f89bea245e3 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/text-splitters/langchain_text_splitters/html.py lines 354–374

    def __init__(
        self,
        headers_to_split_on: list[tuple[str, str]],
        **kwargs: Any,
    ) -> None:
        """Create a new `HTMLSectionSplitter`.

        Args:
            headers_to_split_on: List of tuples of headers we want to track mapped to
                (arbitrary) keys for metadata.

                Allowed header values: `h1`, `h2`, `h3`, `h4`, `h5`, `h6`, e.g.:
                `[("h1", "Header 1"), ("h2", "Header 2"]`.
            **kwargs: Additional optional arguments for customizations.

        """
        self.headers_to_split_on = dict(headers_to_split_on)
        self.xslt_path = (
            pathlib.Path(__file__).parent / "xsl/converting_to_header.xslt"
        ).absolute()
        self.kwargs = kwargs