Package Methods (0.5.0)

_aget_messages(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    session_id: str,
    table_name: str,
) -> typing.List[langchain_core.messages.base.BaseMessage]

_get_iam_principal_email(credentials: google.auth.credentials.Credentials) -> str

_parse_doc_from_row(content_columns: typing.Iterable[str], metadata_columns: typing.Iterable[str], row: typing.Dict[str, typing.Any], metadata_json_column: typing.Optional[str] = 'langchain_metadata', formatter: typing.Callable[[typing.Dict[str, typing.Any], typing.Iterable[str]], str] = 

_parse_row_from_doc(
    doc: langchain_core.documents.base.Document,
    column_names: typing.Iterable[str],
    content_column: str = "page_content",
    metadata_json_column: typing.Optional[str] = "langchain_metadata",
) -> typing.Dict[str, typing.Any]

csv_formatter(
    row: typing.Dict[str, typing.Any], content_columns: typing.Iterable[str]
) -> str

json_formatter(
    row: typing.Dict[str, typing.Any], content_columns: typing.Iterable[str]
) -> str

text_formatter(
    row: typing.Dict[str, typing.Any], content_columns: typing.Iterable[str]
) -> str

yaml_formatter(
    row: typing.Dict[str, typing.Any], content_columns: typing.Iterable[str]
) -> str

cosine_similarity(
    X: typing.Union[
        typing.List[typing.List[float]], typing.List[numpy.ndarray], numpy.ndarray
    ],
    Y: typing.Union[
        typing.List[typing.List[float]], typing.List[numpy.ndarray], numpy.ndarray
    ],
) -> numpy.ndarray

maximal_marginal_relevance(
    query_embedding: numpy.ndarray,
    embedding_list: list,
    lambda_mult: float = 0.5,
    k: int = 4,
) -> typing.List[int]

AlloyDBChatMessageHistory(
    key: object,
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    session_id: str,
    table_name: str,
    messages: typing.List[langchain_core.messages.base.BaseMessage],
)

aadd_message(message: langchain_core.messages.base.BaseMessage) -> None

aadd_messages(
    messages: typing.Sequence[langchain_core.messages.base.BaseMessage],
) -> None

aclear() -> None

add_message(message: langchain_core.messages.base.BaseMessage) -> None

add_messages(
    messages: typing.Sequence[langchain_core.messages.base.BaseMessage],
) -> None

async_messages() -> None

clear() -> None

create(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    session_id: str,
    table_name: str,
) -> langchain_google_alloydb_pg.chat_message_history.AlloyDBChatMessageHistory

create_sync(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    session_id: str,
    table_name: str,
) -> langchain_google_alloydb_pg.chat_message_history.AlloyDBChatMessageHistory

sync_messages() -> None

AlloyDBEngine(
    key: object,
    engine: sqlalchemy.ext.asyncio.engine.AsyncEngine,
    loop: typing.Optional[asyncio.events.AbstractEventLoop],
    thread: typing.Optional[threading.Thread],
)

_aexecute(query: str, params: typing.Optional[dict] = None) -> None

_aexecute_outside_tx(query: str) -> None

_afetch(
    query: str, params: typing.Optional[dict] = None
) -> typing.Sequence[sqlalchemy.engine.row.RowMapping]

_aload_table_schema(table_name: str) -> sqlalchemy.sql.schema.Table

_create(
    project_id: str,
    region: str,
    cluster: str,
    instance: str,
    database: str,
    ip_type: typing.Union[str, google.cloud.alloydb.connector.enums.IPTypes],
    user: typing.Optional[str] = None,
    password: typing.Optional[str] = None,
    loop: typing.Optional[asyncio.events.AbstractEventLoop] = None,
    thread: typing.Optional[threading.Thread] = None,
    iam_account_email: typing.Optional[str] = None,
) -> langchain_google_alloydb_pg.engine.AlloyDBEngine

_execute(query: str, params: typing.Optional[dict] = None) -> None

_fetch(
    query: str, params: typing.Optional[dict] = None
) -> typing.Sequence[sqlalchemy.engine.row.RowMapping]

_run_as_sync(
    coro: typing.Awaitable[langchain_google_alloydb_pg.engine.T],
) -> langchain_google_alloydb_pg.engine.T

afrom_instance(
    project_id: str,
    region: str,
    cluster: str,
    instance: str,
    database: str,
    user: typing.Optional[str] = None,
    password: typing.Optional[str] = None,
    ip_type: typing.Union[
        str, google.cloud.alloydb.connector.enums.IPTypes
    ] = IPTypes.PUBLIC,
    iam_account_email: typing.Optional[str] = None,
) -> langchain_google_alloydb_pg.engine.AlloyDBEngine

ainit_chat_history_table(table_name: str) -> None

ainit_document_table(
    table_name: str,
    content_column: str = "page_content",
    metadata_columns: typing.List[langchain_google_alloydb_pg.engine.Column] = [],
    metadata_json_column: str = "langchain_metadata",
    store_metadata: bool = True,
) -> None

ainit_vectorstore_table(
    table_name: str,
    vector_size: int,
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.List[langchain_google_alloydb_pg.engine.Column] = [],
    metadata_json_column: str = "langchain_metadata",
    id_column: str = "langchain_id",
    overwrite_existing: bool = False,
    store_metadata: bool = True,
) -> None

from_engine(
    engine: sqlalchemy.ext.asyncio.engine.AsyncEngine,
) -> langchain_google_alloydb_pg.engine.AlloyDBEngine

from_instance(
    project_id: str,
    region: str,
    cluster: str,
    instance: str,
    database: str,
    user: typing.Optional[str] = None,
    password: typing.Optional[str] = None,
    ip_type: typing.Union[
        str, google.cloud.alloydb.connector.enums.IPTypes
    ] = IPTypes.PUBLIC,
    iam_account_email: typing.Optional[str] = None,
) -> langchain_google_alloydb_pg.engine.AlloyDBEngine

init_chat_history_table(table_name: str) -> None

init_document_table(
    table_name: str,
    content_column: str = "page_content",
    metadata_columns: typing.List[langchain_google_alloydb_pg.engine.Column] = [],
    metadata_json_column: str = "langchain_metadata",
    store_metadata: bool = True,
) -> None

init_vectorstore_table(
    table_name: str,
    vector_size: int,
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.List[langchain_google_alloydb_pg.engine.Column] = [],
    metadata_json_column: str = "langchain_metadata",
    id_column: str = "langchain_id",
    overwrite_existing: bool = False,
    store_metadata: bool = True,
) -> None

__post_init__() -> None

index_options() -> str

_generate_next_value_(start, count, last_values)

index_options() -> str

to_string() -> str

index_options() -> str

to_string() -> str

index_options() -> str

to_string() -> str

to_string() -> str

index_options() -> str

AlloyDBDocumentSaver(
    key: object,
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    table_name: str,
    content_column: str,
    metadata_columns: typing.List[str] = [],
    metadata_json_column: typing.Optional[str] = None,
)

aadd_documents(docs: typing.List[langchain_core.documents.base.Document]) -> None

add_documents(docs: typing.List[langchain_core.documents.base.Document]) -> None

adelete(docs: typing.List[langchain_core.documents.base.Document]) -> None

create(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    table_name: str,
    content_column: str = "page_content",
    metadata_columns: typing.List[str] = [],
    metadata_json_column: typing.Optional[str] = "langchain_metadata",
) -> langchain_google_alloydb_pg.loader.AlloyDBDocumentSaver

create_sync(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    table_name: str,
    content_column: str = "page_content",
    metadata_columns: typing.List[str] = [],
    metadata_json_column: str = "langchain_metadata",
) -> langchain_google_alloydb_pg.loader.AlloyDBDocumentSaver

delete(docs: typing.List[langchain_core.documents.base.Document]) -> None

AlloyDBLoader(
    key: object,
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    query: str,
    content_columns: typing.List[str],
    metadata_columns: typing.List[str],
    formatter: typing.Callable[
        [typing.Dict[str, typing.Any], typing.Iterable[str]], str
    ],
    metadata_json_column: typing.Optional[str] = None,
)

_collect_async_items(
    docs_generator: typing.AsyncIterator[langchain_core.documents.base.Document],
) -> typing.List[langchain_core.documents.base.Document]

alazy_load() -> typing.AsyncIterator[langchain_core.documents.base.Document]

aload() -> typing.List[langchain_core.documents.base.Document]

create(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    query: typing.Optional[str] = None,
    table_name: typing.Optional[str] = None,
    content_columns: typing.Optional[typing.List[str]] = None,
    metadata_columns: typing.Optional[typing.List[str]] = None,
    metadata_json_column: typing.Optional[str] = None,
    format: typing.Optional[str] = None,
    formatter: typing.Optional[typing.Callable] = None,
) -> langchain_google_alloydb_pg.loader.AlloyDBLoader

create_sync(
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    query: typing.Optional[str] = None,
    table_name: typing.Optional[str] = None,
    content_columns: typing.Optional[typing.List[str]] = None,
    metadata_columns: typing.Optional[typing.List[str]] = None,
    metadata_json_column: typing.Optional[str] = None,
    format: typing.Optional[str] = None,
    formatter: typing.Optional[typing.Callable] = None,
) -> langchain_google_alloydb_pg.loader.AlloyDBLoader

lazy_load() -> typing.Iterator[langchain_core.documents.base.Document]

load() -> typing.List[langchain_core.documents.base.Document]

AlloyDBVectorStore(
    key: object,
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    embedding_service: langchain_core.embeddings.embeddings.Embeddings,
    table_name: str,
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.List[str] = [],
    id_column: str = "langchain_id",
    metadata_json_column: typing.Optional[str] = "langchain_metadata",
    distance_strategy: langchain_google_alloydb_pg.indexes.DistanceStrategy = DistanceStrategy.COSINE_DISTANCE,
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    index_query_options: typing.Optional[
        langchain_google_alloydb_pg.indexes.QueryOptions
    ] = None,
)

__query_collection(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.Sequence[sqlalchemy.engine.row.RowMapping]

_aadd_embeddings(
    texts: typing.Iterable[str],
    embeddings: typing.List[typing.List[float]],
    metadatas: typing.Optional[typing.List[dict]] = None,
    ids: typing.Optional[typing.List[str]] = None,
    **kwargs: typing.Any
) -> typing.List[str]

_select_relevance_score_fn() -> typing.Callable[[float], float]

aadd_documents(
    documents: typing.List[langchain_core.documents.base.Document],
    ids: typing.Optional[typing.List[str]] = None,
    **kwargs: typing.Any
) -> typing.List[str]

aadd_texts(
    texts: typing.Iterable[str],
    metadatas: typing.Optional[typing.List[dict]] = None,
    ids: typing.Optional[typing.List[str]] = None,
    **kwargs: typing.Any
) -> typing.List[str]

aapply_vector_index(
    index: langchain_google_alloydb_pg.indexes.BaseIndex,
    name: typing.Optional[str] = None,
    concurrently: bool = False,
) -> None

add_documents(
    documents: typing.List[langchain_core.documents.base.Document],
    ids: typing.Optional[typing.List[str]] = None,
    **kwargs: typing.Any
) -> typing.List[str]

add_texts(
    texts: typing.Iterable[str],
    metadatas: typing.Optional[typing.List[dict]] = None,
    ids: typing.Optional[typing.List[str]] = None,
    **kwargs: typing.Any
) -> typing.List[str]

adelete(
    ids: typing.Optional[typing.List[str]] = None, **kwargs: typing.Any
) -> typing.Optional[bool]

adrop_vector_index(index_name: typing.Optional[str] = None) -> None

afrom_documents(
    documents: typing.List[langchain_core.documents.base.Document],
    embedding: langchain_core.embeddings.embeddings.Embeddings,
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    table_name: str,
    ids: typing.Optional[typing.List[str]] = None,
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.List[str] = [],
    ignore_metadata_columns: typing.Optional[typing.List[str]] = None,
    id_column: str = "langchain_id",
    metadata_json_column: str = "langchain_metadata",
    **kwargs: typing.Any
) -> langchain_google_alloydb_pg.vectorstore.AlloyDBVectorStore

afrom_texts(
    texts: typing.List[str],
    embedding: langchain_core.embeddings.embeddings.Embeddings,
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    table_name: str,
    metadatas: typing.Optional[typing.List[dict]] = None,
    ids: typing.Optional[typing.List[str]] = None,
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.List[str] = [],
    ignore_metadata_columns: typing.Optional[typing.List[str]] = None,
    id_column: str = "langchain_id",
    metadata_json_column: str = "langchain_metadata",
    **kwargs: typing.Any
) -> langchain_google_alloydb_pg.vectorstore.AlloyDBVectorStore

amax_marginal_relevance_search(
    query: str,
    k: typing.Optional[int] = None,
    fetch_k: typing.Optional[int] = None,
    lambda_mult: typing.Optional[float] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

amax_marginal_relevance_search_by_vector(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    fetch_k: typing.Optional[int] = None,
    lambda_mult: typing.Optional[float] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

amax_marginal_relevance_search_with_score_by_vector(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    fetch_k: typing.Optional[int] = None,
    lambda_mult: typing.Optional[float] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]

areindex(index_name: typing.Optional[str] = None) -> None

asimilarity_search(
    query: str,
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

asimilarity_search_by_vector(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

asimilarity_search_with_score(
    query: str,
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]

asimilarity_search_with_score_by_vector(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]

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

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

delete(
    ids: typing.Optional[typing.List[str]] = None, **kwargs: typing.Any
) -> typing.Optional[bool]

from_documents(
    documents: typing.List[langchain_core.documents.base.Document],
    embedding: langchain_core.embeddings.embeddings.Embeddings,
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    table_name: str,
    ids: typing.Optional[typing.List[str]] = None,
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.List[str] = [],
    ignore_metadata_columns: typing.Optional[typing.List[str]] = None,
    id_column: str = "langchain_id",
    metadata_json_column: str = "langchain_metadata",
    **kwargs: typing.Any
) -> langchain_google_alloydb_pg.vectorstore.AlloyDBVectorStore

from_texts(
    texts: typing.List[str],
    embedding: langchain_core.embeddings.embeddings.Embeddings,
    engine: langchain_google_alloydb_pg.engine.AlloyDBEngine,
    table_name: str,
    metadatas: typing.Optional[typing.List[dict]] = None,
    ids: typing.Optional[typing.List[str]] = None,
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.List[str] = [],
    ignore_metadata_columns: typing.Optional[typing.List[str]] = None,
    id_column: str = "langchain_id",
    metadata_json_column: str = "langchain_metadata",
    **kwargs: typing.Any
) -> langchain_google_alloydb_pg.vectorstore.AlloyDBVectorStore

is_valid_index(index_name: typing.Optional[str] = None) -> bool

max_marginal_relevance_search(
    query: str,
    k: typing.Optional[int] = None,
    fetch_k: typing.Optional[int] = None,
    lambda_mult: typing.Optional[float] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

max_marginal_relevance_search_by_vector(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    fetch_k: typing.Optional[int] = None,
    lambda_mult: typing.Optional[float] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

max_marginal_relevance_search_with_score_by_vector(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    fetch_k: typing.Optional[int] = None,
    lambda_mult: typing.Optional[float] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]

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

similarity_search(
    query: str,
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

similarity_search_by_vector(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

similarity_search_with_score(
    query: str,
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]

similarity_search_with_score_by_vector(
    embedding: typing.List[float],
    k: typing.Optional[int] = None,
    filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]