CubeSemanticLoader#

class langchain_community.document_loaders.cube_semantic.CubeSemanticLoader( cube_api_url: str, cube_api_token: str, load_dimension_values: bool = True, dimension_values_limit: int = 10000, dimension_values_max_retries: int = 10, dimension_values_retry_delay: int = 3, )[source]#

Load Cube semantic layer metadata.

Parameters:

cube_api_url (str) – REST API endpoint. Use the REST API of your Cube’s deployment. Please find out more information here: https://cube.dev/docs/http-api/rest#configuration-base-path
cube_api_token (str) – Cube API token. Authentication tokens are generated based on your Cube’s API secret. Please find out more information here: https://cube.dev/docs/security#generating-json-web-tokens-jwt
load_dimension_values (bool) – Whether to load dimension values for every string dimension or not.
dimension_values_limit (int) – Maximum number of dimension values to load.
dimension_values_max_retries (int) – Maximum number of retries to load dimension values.
dimension_values_retry_delay (int) – Delay between retries to load dimension values.

Methods

`__init__`(cube_api_url, cube_api_token[, ...])
`alazy_load`()	A lazy loader for Documents.
`aload`()	Load data into Document objects.
`lazy_load`()	Makes a call to Cube's REST API metadata endpoint.
`load`()	Load data into Document objects.
`load_and_split`([text_splitter])	Load Documents and split into chunks.

__init__( cube_api_url: str, cube_api_token: str, load_dimension_values: bool = True, dimension_values_limit: int = 10000, dimension_values_max_retries: int = 10, dimension_values_retry_delay: int = 3, )[source]#

Parameters:

cube_api_url (str)
cube_api_token (str)
load_dimension_values (bool)
dimension_values_limit (int)
dimension_values_max_retries (int)
dimension_values_retry_delay (int)

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]#

Makes a call to Cube’s REST API metadata endpoint.

Returns:

page_content=column_title + column_description
metadata
- table_name
- column_name
- column_data_type
- column_member_type
- column_title
- column_description
- column_values
- cube_data_obj_type

Return type:

A list of documents with attributes

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 CubeSemanticLoader