From 1bd97d82ba85a8895262c4c9c7c5ea2820bfeb9e Mon Sep 17 00:00:00 2001 From: Christophe Bornet Date: Wed, 21 Feb 2024 17:41:34 +0100 Subject: [PATCH] community[patch]: Add AstraDBLoader docstring (#17873) --- .../document_loaders/astradb.py | 23 ++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/libs/community/langchain_community/document_loaders/astradb.py b/libs/community/langchain_community/document_loaders/astradb.py index 8dae5c4528a32..976b4a70da95b 100644 --- a/libs/community/langchain_community/document_loaders/astradb.py +++ b/libs/community/langchain_community/document_loaders/astradb.py @@ -25,8 +25,6 @@ class AstraDBLoader(BaseLoader): - """Load DataStax Astra DB documents.""" - def __init__( self, collection_name: str, @@ -42,6 +40,26 @@ def __init__( nb_prefetched: int = 1000, extraction_function: Callable[[Dict], str] = json.dumps, ) -> None: + """Load DataStax Astra DB documents. + + Args: + collection_name: name of the Astra DB collection to use. + token: API token for Astra DB usage. + api_endpoint: full URL to the API endpoint, + such as `https://-us-east1.apps.astra.datastax.com`. + astra_db_client: *alternative to token+api_endpoint*, + you can pass an already-created 'astrapy.db.AstraDB' instance. + async_astra_db_client: *alternative to token+api_endpoint*, + you can pass an already-created 'astrapy.db.AsyncAstraDB' instance. + namespace: namespace (aka keyspace) where the + collection is. Defaults to the database's "default namespace". + filter_criteria: Criteria to filter documents. + projection: Specifies the fields to return. + find_options: Additional options for the query. + nb_prefetched: Max number of documents to pre-fetch. Defaults to 1000. + extraction_function: Function applied to collection documents to create + the `page_content` of the LangChain Document. Defaults to `json.dumps`. + """ astra_env = _AstraDBEnvironment( token=token, api_endpoint=api_endpoint, @@ -59,7 +77,6 @@ def __init__( self.extraction_function = extraction_function def load(self) -> List[Document]: - """Eagerly load the content.""" return list(self.lazy_load()) def lazy_load(self) -> Iterator[Document]: