PolarsDataFrameLoader#

class langchain_community.document_loaders.polars_dataframe.PolarsDataFrameLoader(data_frame: Any, *, page_content_column: str = 'text')[source]#

Load Polars DataFrame.

Initialize with dataframe object.

Parameters:

  • data_frame (Any) – Polars DataFrame object.

  • page_content_column (str) – Name of the column containing the page content. Defaults to “text”.

Methods

__init__(data_frame, *[, page_content_column])

Initialize with dataframe object.

alazy_load()

A lazy loader for Documents.

aload()

Load data into Document objects.

lazy_load()

Lazy load records from dataframe.

load()

Load data into Document objects.

load_and_split([text_splitter])

Load Documents and split into chunks.
__init__(data_frame: Any, *, page_content_column: str = 'text')[source]#

Initialize with dataframe object.

Parameters:

  • data_frame (Any) – Polars DataFrame object.

  • page_content_column (str) – Name of the column containing the page content. Defaults to “text”.

async alazy_load() → AsyncIterator[Document]#

A lazy loader for Documents.

Return type:

AsyncIterator[Document]

async aload() → list[Document]#

Load data into Document objects.

Return type:

list[Document]

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

Lazy load records from dataframe.

Return type:

Iterator[Document]

load() → list[Document]#

Load data into Document objects.

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.

Returns:

List of Documents.

Return type:

list[Document]

Examples using PolarsDataFrameLoader

On this page