UnstructuredExcelLoader#

class langchain_community.document_loaders.excel.UnstructuredExcelLoader(
file_path: str | Path,
mode: str = 'single',
**unstructured_kwargs: Any,
)[source]#

Load Microsoft Excel files using Unstructured.

Like other Unstructured loaders, UnstructuredExcelLoader can be used in both “single” and “elements” mode. If you use the loader in “elements” mode, each sheet in the Excel file will be an Unstructured Table element. If you use the loader in “single” mode, an HTML representation of the table will be available in the “text_as_html” key in the document metadata.

Examples

from langchain_community.document_loaders.excel import UnstructuredExcelLoader

loader = UnstructuredExcelLoader(“stanley-cups.xlsx”, mode=”elements”) docs = loader.load()

Parameters:

  • file_path (str | Path) – The path to the Microsoft Excel file.

  • mode (str) – The mode to use when partitioning the file. See unstructured docs for more info. Optional. Defaults to “single”.

  • **unstructured_kwargs (Any) – Keyword arguments to pass to unstructured.

Methods

__init__(file_path[, mode])

alazy_load()

A lazy loader for Documents.

aload()

Load data into Document objects.

lazy_load()

Load file.

load()

Load data into Document objects.

load_and_split([text_splitter])

Load Documents and split into chunks.
__init__(
file_path: str | Path,
mode: str = 'single',
**unstructured_kwargs: Any,
)[source]#
Parameters:

  • file_path (str | Path) – The path to the Microsoft Excel file.

  • mode (str) – The mode to use when partitioning the file. See unstructured docs for more info. Optional. Defaults to “single”.

  • **unstructured_kwargs (Any) – Keyword arguments to pass to unstructured.

async alazy_load() → AsyncIterator[Document]#

A lazy loader for Documents.

Yields:

the documents.

Return type:

AsyncIterator[Document]

async aload() → list[Document]#

Load data into Document objects.

Returns:

the documents.

Return type:

list[Document]

lazy_load() → Iterator[Document]#

Load file.

Return type:

Iterator[Document]

load() → list[Document]#

Load data into Document objects.

Returns:

the documents.

Return type:

list[Document]

load_and_split(
text_splitter: TextSplitter | None = None,
) → list[Document]#

Load Documents and split into chunks. Chunks are returned as Documents.

Do not override this method. It should be considered to be deprecated!

Parameters:

text_splitter (Optional[TextSplitter]) – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.

Raises:

ImportError – If langchain-text-splitters is not installed and no text_splitter is provided.

Returns:

List of Documents.

Return type:

list[Document]

Examples using UnstructuredExcelLoader