BaseBlobParser Class — langchain Architecture

Source Code

libs/core/langchain_core/document_loaders/base.py lines 117–155

class BaseBlobParser(ABC):
    """Abstract interface for blob parsers.

    A blob parser provides a way to parse raw data stored in a blob into one or more
    `Document` objects.

    The parser can be composed with blob loaders, making it easy to reuse a parser
    independent of how the blob was originally loaded.
    """

    @abstractmethod
    def lazy_parse(self, blob: Blob) -> Iterator[Document]:
        """Lazy parsing interface.

        Subclasses are required to implement this method.

        Args:
            blob: `Blob` instance

        Returns:
            Generator of `Document` objects
        """

    def parse(self, blob: Blob) -> list[Document]:
        """Eagerly parse the blob into a `Document` or list of `Document` objects.

        This is a convenience method for interactive development environment.

        Production applications should favor the `lazy_parse` method instead.

        Subclasses should generally not over-ride this parse method.

        Args:
            blob: `Blob` instance

        Returns:
            List of `Document` objects
        """
        return list(self.lazy_parse(blob))