langchain_community.document_loaders.astradb.AstraDBLoader

class langchain_community.document_loaders.astradb.AstraDBLoader(collection_name: str, token: ~typing.Optional[str] = None, api_endpoint: ~typing.Optional[str] = None, astra_db_client: ~typing.Optional[~typing.Any] = None, namespace: ~typing.Optional[str] = None, filter_criteria: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None, projection: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None, find_options: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None, nb_prefetched: int = 1000, extraction_function: ~typing.Callable[[~typing.Dict], str] = <function dumps>)

Load DataStax Astra DB documents.

Methods

__init__(collection_name[, token, ...])
fetch_page_result(queue)
fetch_results(queue)
lazy_load()	A lazy loader for Documents.
load()	Eagerly load the content.
load_and_split([text_splitter])	Load Documents and split into chunks.

__init__(collection_name: str, token: ~typing.Optional[str] = None, api_endpoint: ~typing.Optional[str] = None, astra_db_client: ~typing.Optional[~typing.Any] = None, namespace: ~typing.Optional[str] = None, filter_criteria: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None, projection: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None, find_options: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None, nb_prefetched: int = 1000, extraction_function: ~typing.Callable[[~typing.Dict], str] = <function dumps>) → None

fetch_page_result(queue: Queue)

fetch_results(queue: Queue)

lazy_load() → Iterator[Document]

A lazy loader for Documents.

load() → List[Document]

Eagerly load the content.

load_and_split(text_splitter: Optional[TextSplitter] = None) → List[Document]

Load Documents and split into chunks. Chunks are returned as Documents.

Parameters

text_splitter – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.

Returns

List of Documents.