langchain_community.document_loaders.cassandra.CassandraLoader¶

class langchain_community.document_loaders.cassandra.CassandraLoader(table: ~typing.Optional[str] = None, session: ~typing.Optional[Session] = None, keyspace: ~typing.Optional[str] = None, query: ~typing.Optional[~typing.Union[str, Statement]] = None, page_content_mapper: ~typing.Callable[[~typing.Any], str] = <function default_page_content_mapper>, metadata_mapper: ~typing.Callable[[~typing.Any], dict] = <function CassandraLoader.<lambda>>, *, query_parameters: ~typing.Union[dict, ~typing.Sequence] = None, query_timeout: ~typing.Optional[float] = <object object>, query_trace: bool = False, query_custom_payload: dict = None, query_execution_profile: ~typing.Any = <object object>, query_paging_state: ~typing.Any = None, query_host: Host = None, query_execute_as: str = None)[source]¶

Document Loader for Apache Cassandra.

Parameters
  • table – The table to load the data from. (do not use together with the query parameter)

  • session – The cassandra driver session. If not provided, the cassio resolved session will be used.

  • keyspace – The keyspace of the table. If not provided, the cassio resolved keyspace will be used.

  • query – The query used to load the data. (do not use together with the table parameter)

  • page_content_mapper – a function to convert a row to string page content.

  • query_parameters – The query parameters used when calling session.execute .

  • query_timeout – The query timeout used when calling session.execute .

  • query_custom_payload – The query custom_payload used when calling session.execute .

  • query_execution_profile – The query execution_profile used when calling session.execute .

  • query_host – The query host used when calling session.execute .

  • query_execute_as – The query execute_as used when calling session.execute .

Methods

__init__([table, session, keyspace, query, ...])

Document Loader for Apache Cassandra.

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__(table: ~typing.Optional[str] = None, session: ~typing.Optional[Session] = None, keyspace: ~typing.Optional[str] = None, query: ~typing.Optional[~typing.Union[str, Statement]] = None, page_content_mapper: ~typing.Callable[[~typing.Any], str] = <function default_page_content_mapper>, metadata_mapper: ~typing.Callable[[~typing.Any], dict] = <function CassandraLoader.<lambda>>, *, query_parameters: ~typing.Union[dict, ~typing.Sequence] = None, query_timeout: ~typing.Optional[float] = <object object>, query_trace: bool = False, query_custom_payload: dict = None, query_execution_profile: ~typing.Any = <object object>, query_paging_state: ~typing.Any = None, query_host: Host = None, query_execute_as: str = None) None[source]¶

Document Loader for Apache Cassandra.

Parameters
  • table – The table to load the data from. (do not use together with the query parameter)

  • session – The cassandra driver session. If not provided, the cassio resolved session will be used.

  • keyspace – The keyspace of the table. If not provided, the cassio resolved keyspace will be used.

  • query – The query used to load the data. (do not use together with the table parameter)

  • page_content_mapper – a function to convert a row to string page content.

  • query_parameters – The query parameters used when calling session.execute .

  • query_timeout – The query timeout used when calling session.execute .

  • query_custom_payload – The query custom_payload used when calling session.execute .

  • query_execution_profile – The query execution_profile used when calling session.execute .

  • query_host – The query host used when calling session.execute .

  • query_execute_as – The query execute_as used when calling session.execute .

lazy_load() Iterator[Document][source]¶

A lazy loader for Documents.

load() List[Document][source]¶

Load data into Document objects.

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.