Package Classes (0.5.0)

Chat message history stored in an AlloyDB.

A class for managing connections to a AlloyDB database.

Column(name: 'str', data_type: 'str', nullable: 'bool' = True)

BaseIndex(name: Optional[str] = None, index_type: str = 'base', distance_strategy: langchain_google_alloydb_pg.indexes.DistanceStrategy =

Enumerator of the Distance strategies.

ExactNearestNeighbor(name: Optional[str] = None, index_type: str = 'exactnearestneighbor', distance_strategy: langchain_google_alloydb_pg.indexes.DistanceStrategy =

HNSWIndex(name: Optional[str] = None, index_type: str = 'hnsw', distance_strategy: langchain_google_alloydb_pg.indexes.DistanceStrategy =

HNSWQueryOptions(ef_search: int = 40)

IVFFlatIndex(name: Optional[str] = None, index_type: str = 'ivfflat', distance_strategy: langchain_google_alloydb_pg.indexes.DistanceStrategy =

IVFFlatQueryOptions(probes: int = 1)

IVFIndex(name: Optional[str] = None, index_type: str = 'ivf', distance_strategy: langchain_google_alloydb_pg.indexes.DistanceStrategy =

IVFQueryOptions(probes: int = 1)

QueryOptions()

ScaNNIndex(name: Optional[str] = None, index_type: str = 'ScaNN', distance_strategy: langchain_google_alloydb_pg.indexes.DistanceStrategy =

StrategyMixin(operator: str, search_function: str, index_function: str, scann_index_function: str)

A class for saving langchain documents into a AlloyDB database table.

Load documents from AlloyDB`.

Each document represents one row of the result. The content_columns are written into the content_columns of the document. The metadata_columns are written into the metadata_columns of the document. By default, first columns is written into the page_content and everything else into the metadata.

Google AlloyDB Vector Store class

API documentation for chat_message_history module.

API documentation for engine module.

API documentation for indexes module.

API documentation for loader module.

API documentation for vectorstore module.