langchain_community.document_loaders.tensorflow_datasets.TensorflowDatasetLoader

class langchain_community.document_loaders.tensorflow_datasets.TensorflowDatasetLoader(dataset_name: str, split_name: str, load_max_docs: Optional[int] = 100, sample_to_document_function: Optional[Callable[[Dict], Document]] = None)

Load from TensorFlow Dataset.

dataset_name

the name of the dataset to load

split_name

the name of the split to load.

load_max_docs

a limit to the number of loaded documents. Defaults to 100.

sample_to_document_function

a function that converts a dataset sample into a Document

Example

from langchain_community.document_loaders import TensorflowDatasetLoader

def mlqaen_example_to_document(example: dict) -> Document:
    return Document(
        page_content=decode_to_str(example["context"]),
        metadata={
            "id": decode_to_str(example["id"]),
            "title": decode_to_str(example["title"]),
            "question": decode_to_str(example["question"]),
            "answer": decode_to_str(example["answers"]["text"][0]),
        },
    )

tsds_client = TensorflowDatasetLoader(
        dataset_name="mlqa/en",
        split_name="test",
        load_max_docs=100,
        sample_to_document_function=mlqaen_example_to_document,
    )

Initialize the TensorflowDatasetLoader.

Parameters

• dataset_name (str) – the name of the dataset to load

• split_name (str) – the name of the split to load.

• load_max_docs (Optional[int]) – a limit to the number of loaded documents. Defaults to 100.

• sample_to_document_function (Optional[Callable[[Dict], Document]]) – a function that converts a dataset sample into a Document.

Attributes

load_max_docs	The maximum number of documents to load.
sample_to_document_function	Custom function that transform a dataset sample into a Document.

Methods

__init__(dataset_name, split_name[, ...])	Initialize the TensorflowDatasetLoader.
alazy_load()	A lazy loader for Documents.
lazy_load()	A lazy loader for Documents.
load()	Load data into Document objects.
load_and_split([text_splitter])	Load Documents and split into chunks.

__init__(dataset_name: str, split_name: str, load_max_docs: Optional[int] = 100, sample_to_document_function: Optional[Callable[[Dict], Document]] = None)

Initialize the TensorflowDatasetLoader.

Parameters

• dataset_name (str) – the name of the dataset to load

• split_name (str) – the name of the split to load.

• load_max_docs (Optional[int]) – a limit to the number of loaded documents. Defaults to 100.

• sample_to_document_function (Optional[Callable[[Dict], Document]]) – a function that converts a dataset sample into a Document.

async alazy_load() → AsyncIterator[Document]

A lazy loader for Documents.

Return type

AsyncIterator[Document]

lazy_load() → Iterator[Document]

A lazy loader for Documents.

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 TensorflowDatasetLoader

• TensorFlow Datasets