AstraDBLoader

AstraDBLoader(
  self,
  collection_name: str,
  *,
  token: Optional[str]

Bases

BaseLoader

async_astra_db_client

Name	Type	Description
`collection_name`*	`str`	name of the Astra DB collection to use.
`token`	`Optional[str]`	Default:`None` API token for Astra DB usage.
`api_endpoint`	`Optional[str]`	Default:`None`
`astra_db_client`	`Optional[AstraDB]`	Default:`None`
`async_astra_db_client`	`Optional[AsyncAstraDB]`	Default:`None`
`namespace`	`Optional[str]`	Default:`None`
`filter_criteria`	`Optional[Dict[str, Any]]`	Default:`None`
`projection`	`Optional[Dict[str, Any]]`	Default:`None`
`find_options`	`Optional[Dict[str, Any]]`	Default:`None`
`nb_prefetched`	`int`	Default:`1000`
`extraction_function`	`Callable[[Dict], str]`	Default:`json.dumps`

constructor

__init__

full URL to the API endpoint, such as https://<DB-ID>-us-east1.apps.astra.datastax.com.

alternative to token+api_endpoint, you can pass an already-created 'astrapy.db.AstraDB' instance.

alternative to token+api_endpoint, you can pass an already-created 'astrapy.db.AsyncAstraDB' instance.

namespace (aka keyspace) where the collection is. Defaults to the database's "default namespace".

Criteria to filter documents.

Specifies the fields to return.

Additional options for the query.

Max number of documents to pre-fetch. Defaults to 1000.

Function applied to collection documents to create the page_content of the LangChain Document. Defaults to json.dumps.