Class AlloyDBVectorStore (0.14.0)

AlloyDBVectorStore(
    key: object,
    engine: langchain_postgres.v2.engine.PGEngine,
    vs: langchain_postgres.v2.async_vectorstore.AsyncPGVectorStore,
)

Google AlloyDB Vector Store class

Methods

AlloyDBVectorStore

AlloyDBVectorStore(
    key: object,
    engine: langchain_postgres.v2.engine.PGEngine,
    vs: langchain_postgres.v2.async_vectorstore.AsyncPGVectorStore,
)

PGVectorStore constructor.

Parameters
Name	Description
`key`	`object` Prevent direct constructor usage.
`engine`	`PGEngine` Connection pool engine for managing connections to Postgres database.
`vs`	`AsyncPGVectorStore` The async only VectorStore implementation

Exceptions
Type	Description
`Exception`	If called directly by user.

aadd_images

aadd_images(
    uris: list[str],
    metadatas: typing.Optional[list[dict]] = None,
    ids: typing.Optional[list[str]] = None,
    store_uri_only: bool = False,
    **kwargs: typing.Any
) -> list[str]

Embed images and add to the table.

add_images

add_images(
    uris: list[str],
    metadatas: typing.Optional[list[dict]] = None,
    ids: typing.Optional[list[str]] = None,
    store_uri_only: bool = False,
    **kwargs: typing.Any
) -> list[str]

Embed images and add to the table.

aset_maintenance_work_mem

aset_maintenance_work_mem(num_leaves: int, vector_size: int) -> None

Set database maintenance work memory (for ScaNN index creation).

asimilarity_search_image

asimilarity_search_image(
    image_uri: str,
    k: typing.Optional[int] = None,
    filter: typing.Optional[dict] = None,
    **kwargs: typing.Any
) -> list[langchain_core.documents.base.Document]

Return docs selected by similarity search on image_uri.

create

create(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    embedding_service: langchain_core.embeddings.embeddings.Embeddings,
    table_name: str,
    schema_name: str = "public",
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.Optional[list[str]] = None,
    ignore_metadata_columns: typing.Optional[list[str]] = None,
    id_column: str = "langchain_id",
    metadata_json_column: typing.Optional[str] = "langchain_metadata",
    distance_strategy: langchain_postgres.v2.indexes.DistanceStrategy = DistanceStrategy.COSINE_DISTANCE,
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    index_query_options: typing.Optional[
        langchain_postgres.v2.indexes.QueryOptions
    ] = None,
    hybrid_search_config: typing.Optional[
        langchain_postgres.v2.hybrid_search_config.HybridSearchConfig
    ] = None,
) -> langchain_google_alloydb_pg.vectorstore.AlloyDBVectorStore

Create an PGVectorStore instance.

Parameters
Name	Description
`engine`	`AlloyDBEngine` Connection pool engine for managing connections to postgres database.
`embedding_service`	`Embeddings` Text embedding model to use.
`table_name`	`str` Name of an existing table.
`schema_name`	`str, optional` Name of the database schema. Defaults to "public".
`content_column`	`str` Column that represent a Document's page_content. Defaults to "content".
`embedding_column`	`str` Column for embedding vectors. The embedding is generated from the document value. Defaults to "embedding".
`metadata_columns`	`list[str]` Column(s) that represent a document's metadata.
`ignore_metadata_columns`	`list[str]` Column(s) to ignore in pre-existing tables for a document's metadata. Can not be used with metadata_columns. Defaults to None.
`id_column`	`str` Column that represents the Document's id. Defaults to "langchain_id".
`metadata_json_column`	`str` Column to store metadata as JSON. Defaults to "langchain_metadata".
`distance_strategy`	`DistanceStrategy` Distance strategy to use for vector similarity search. Defaults to COSINE_DISTANCE.
`k`	`int` Number of Documents to return from search. Defaults to 4.
`fetch_k`	`int` Number of Documents to fetch to pass to MMR algorithm.
`lambda_mult`	`float` Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.
`index_query_options`	`QueryOptions` Index query option.
`hybrid_search_config`	`HybridSearchConfig` Hybrid search configuration. Defaults to None.

create_sync

create_sync(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    embedding_service: langchain_core.embeddings.embeddings.Embeddings,
    table_name: str,
    schema_name: str = "public",
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.Optional[list[str]] = None,
    ignore_metadata_columns: typing.Optional[list[str]] = None,
    id_column: str = "langchain_id",
    metadata_json_column: str = "langchain_metadata",
    distance_strategy: langchain_postgres.v2.indexes.DistanceStrategy = DistanceStrategy.COSINE_DISTANCE,
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    index_query_options: typing.Optional[
        langchain_postgres.v2.indexes.QueryOptions
    ] = None,
    hybrid_search_config: typing.Optional[
        langchain_postgres.v2.hybrid_search_config.HybridSearchConfig
    ] = None,
) -> langchain_google_alloydb_pg.vectorstore.AlloyDBVectorStore

Create an AlloyDBVectorStore instance.

Parameters
Name	Description
`key`	`object` Prevent direct constructor usage.
`engine`	`AlloyDBEngine` Connection pool engine for managing connections to AlloyDB database.
`embedding_service`	`Embeddings` Text embedding model to use.
`table_name`	`str` Name of an existing table.
`schema_name`	`str, optional` Name of the database schema. Defaults to "public".
`content_column`	`str, optional` Column that represent a Document’s page_content. Defaults to "content".
`embedding_column`	`str, optional` Column for embedding vectors. The embedding is generated from the document value. Defaults to "embedding".
`metadata_columns`	`list[str]` Column(s) that represent a document's metadata. Defaults to an empty list.
`ignore_metadata_columns`	`Optional[list[str]]` Column(s) to ignore in pre-existing tables for a document's metadata. Can not be used with metadata_columns. Defaults to None.
`id_column`	`str, optional` Column that represents the Document's id. Defaults to "langchain_id".
`metadata_json_column`	`str, optional` Column to store metadata as JSON. Defaults to "langchain_metadata".
`distance_strategy`	`DistanceStrategy, optional` Distance strategy to use for vector similarity search. Defaults to COSINE_DISTANCE.
`k`	`int, optional` Number of Documents to return from search. Defaults to 4.
`fetch_k`	`int, optional` Number of Documents to fetch to pass to MMR algorithm. Defaults to 20.
`lambda_mult`	`float, optional` Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.
`index_query_options`	`Optional[QueryOptions], optional` Index query option. Defaults to None.
`hybrid_search_config`	`HybridSearchConfig` Hybrid search configuration. Defaults to None.

set_maintenance_work_mem

set_maintenance_work_mem(num_leaves: int, vector_size: int) -> None