CassandraLoader#

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

Document Loader for Apache Cassandra.

Parameters:

  • table (Optional[str]) – The table to load the data from. (do not use together with the query parameter)

  • session (Optional[Session]) – The cassandra driver session. If not provided, the cassio resolved session will be used.

  • keyspace (Optional[str]) – The keyspace of the table. If not provided, the cassio resolved keyspace will be used.

  • query (Union[str, Statement, None]) – The query used to load the data. (do not use together with the table parameter)

  • page_content_mapper (Callable[[Any], str]) – a function to convert a row to string page content. Defaults to the str representation of the row.

  • metadata_mapper (Callable[[Any], dict]) – a function to convert a row to document metadata.

  • query_parameters (Union[dict, Sequence, None]) – The query parameters used when calling session.execute .

  • query_timeout (Optional[float]) – The query timeout used when calling session.execute .

  • query_trace (bool) – Whether to use tracing when calling session.execute .

  • query_custom_payload (Optional[dict]) – The query custom_payload used when calling session.execute .

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

  • query_host (Optional[Host]) – The query host used when calling session.execute .

  • query_execute_as (Optional[str]) – The query execute_as used when calling session.execute .

  • query_paging_state (Any)

Methods

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

Document Loader for Apache Cassandra.

alazy_load()

A lazy loader for Documents.

aload()

Load data into Document objects.

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: Optional[str] = None, session: Optional[Session] = None, keyspace: Optional[str] = None, query: Union[str, Statement, None] = None, page_content_mapper: Callable[[Any], str] = <class 'str'>, metadata_mapper: Callable[[Any], dict] = <function CassandraLoader.<lambda>>, *, query_parameters: Union[dict, Sequence, None] = None, query_timeout: Optional[float] = <object object>, query_trace: bool = False, query_custom_payload: Optional[dict] = None, query_execution_profile: Any = <object object>, query_paging_state: Any = None, query_host: Optional[Host] = None, query_execute_as: Optional[str] = None) → None[source]#

Document Loader for Apache Cassandra.

Parameters:

  • table (Optional[str]) – The table to load the data from. (do not use together with the query parameter)

  • session (Optional[Session]) – The cassandra driver session. If not provided, the cassio resolved session will be used.

  • keyspace (Optional[str]) – The keyspace of the table. If not provided, the cassio resolved keyspace will be used.

  • query (Union[str, Statement, None]) – The query used to load the data. (do not use together with the table parameter)

  • page_content_mapper (Callable[[Any], str]) – a function to convert a row to string page content. Defaults to the str representation of the row.

  • metadata_mapper (Callable[[Any], dict]) – a function to convert a row to document metadata.

  • query_parameters (Union[dict, Sequence, None]) – The query parameters used when calling session.execute .

  • query_timeout (Optional[float]) – The query timeout used when calling session.execute .

  • query_trace (bool) – Whether to use tracing when calling session.execute .

  • query_custom_payload (Optional[dict]) – The query custom_payload used when calling session.execute .

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

  • query_host (Optional[Host]) – The query host used when calling session.execute .

  • query_execute_as (Optional[str]) – The query execute_as used when calling session.execute .

  • query_paging_state (Any)

Return type:

None

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

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]#

A lazy loader for Documents.

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 CassandraLoader

On this page