github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-23 07:09:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Add AstraDBLoader docstring (#17873)

Browse Source
This commit is contained in:
Christophe Bornet 2024-02-21 17:41:34 +01:00 committed by GitHub
parent c1bb5fd498
commit e6311d953d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
libs/community/langchain_community/document_loaders/astradb.py
View File

@ -25,8 +25,6 @@ logger = logging.getLogger(__name__)
class AstraDBLoader(BaseLoader):
"""Load DataStax Astra DB documents."""
def __init__(
self,
collection_name: str,
@ -42,6 +40,26 @@ class AstraDBLoader(BaseLoader):
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://<DB-ID>-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 @@ class AstraDBLoader(BaseLoader):
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]: