MergedDataLoader#

class langchain_community.document_loaders.merge.MergedDataLoader(loaders: List)[source]#

Merge documents from a list of loaders

Initialize with a list of loaders

Methods

__init__(loaders)

Initialize with a list of loaders

alazy_load()

Lazy load docs from each individual loader.

aload()

Load data into Document objects.

lazy_load()

Lazy load docs from each individual loader.

load()

Load data into Document objects.

load_and_split([text_splitter])

Load Documents and split into chunks.
Parameters:

loaders (List)

__init__(loaders: List)[source]#

Initialize with a list of loaders

Parameters:

loaders (List)

async alazy_load() → AsyncIterator[Document][source]#

Lazy load docs from each individual loader.

Return type:

AsyncIterator[Document]

async aload() → list[Document]#

Load data into Document objects.

Returns:

the documents.

Return type:

list[Document]

lazy_load() → Iterator[Document][source]#

Lazy load docs from each individual loader.

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 MergedDataLoader