Source code for langchain_community.document_loaders.markdown

from typing import List

from langchain_community.document_loaders.unstructured import UnstructuredFileLoader

[docs]class UnstructuredMarkdownLoader(UnstructuredFileLoader): """Load `Markdown` files using `Unstructured`. You can run the loader in one of two modes: "single" and "elements". If you use "single" mode, the document will be returned as a single langchain Document object. If you use "elements" mode, the unstructured library will split the document into elements such as Title and NarrativeText. You can pass in additional unstructured kwargs after mode to apply different unstructured settings. Examples -------- from langchain_community.document_loaders import UnstructuredMarkdownLoader loader = UnstructuredMarkdownLoader( "", mode="elements", strategy="fast", ) docs = loader.load() References ---------- """ def _get_elements(self) -> List: from unstructured.__version__ import __version__ as __unstructured_version__ from import partition_md # NOTE(MthwRobinson) - enables the loader to work when you're using pre-release # versions of unstructured like 0.4.17-dev1 _unstructured_version = __unstructured_version__.split("-")[0] unstructured_version = tuple([int(x) for x in _unstructured_version.split(".")]) if unstructured_version < (0, 4, 16): raise ValueError( f"You are on unstructured version {__unstructured_version__}. " "Partitioning markdown files is only supported in unstructured>=0.4.16." ) return partition_md(filename=self.file_path, **self.unstructured_kwargs)