langchain_community.document_loaders.tsv.UnstructuredTSVLoader¶

class langchain_community.document_loaders.tsv.UnstructuredTSVLoader(file_path: str, mode: str = 'single', **unstructured_kwargs: Any)[source]¶

Load TSV files using Unstructured.

Like other Unstructured loaders, UnstructuredTSVLoader can be used in both “single” and “elements” mode. If you use the loader in “elements” mode, the TSV file will be a single Unstructured Table element. If you use the loader in “elements” 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.tsv import UnstructuredTSVLoader

loader = UnstructuredTSVLoader(“stanley-cups.tsv”, mode=”elements”) docs = loader.load()

Initialize with file path.

Methods

__init__(file_path[, mode])

Initialize with file path.

alazy_load()

A lazy loader for Documents.

lazy_load()

Load file.

load()

Load data into Document objects.

load_and_split([text_splitter])

Load Documents and split into chunks.

Parameters
  • file_path (str) –

  • mode (str) –

  • unstructured_kwargs (Any) –

__init__(file_path: str, mode: str = 'single', **unstructured_kwargs: Any)[source]¶

Initialize with file path.

Parameters
  • file_path (str) –

  • mode (str) –

  • unstructured_kwargs (Any) –

async alazy_load() AsyncIterator[Document]¶

A lazy loader for Documents.

Return type

AsyncIterator[Document]

lazy_load() Iterator[Document]¶

Load file.

Return type

Iterator[Document]

load() List[Document]¶

Load data into Document objects.

Return type

List[Document]

load_and_split(text_splitter: Optional[TextSplitter] = 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.

Returns

List of Documents.

Return type

List[Document]

Examples using UnstructuredTSVLoader¶