Package Methods (0.3.0)

Summary of entries of Methods for langchain-google-spanner.

langchain_google_spanner.loader._load_doc_to_row

_load_doc_to_row(
    table_fields: typing.List[str],
    doc: langchain_core.documents.base.Document,
    content_column: str,
    metadata_json_column: str,
    parse_json: bool = True,
) -> tuple

Load document to row.

See more: langchain_google_spanner.loader._load_doc_to_row

langchain_google_spanner.chat_message_history.SpannerChatMessageHistory._verify_schema

_verify_schema() -> None

Verify table exists with required schema for SpannerChatMessageHistory class.

See more: langchain_google_spanner.chat_message_history.SpannerChatMessageHistory._verify_schema

langchain_google_spanner.chat_message_history.SpannerChatMessageHistory.add_message

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

Append the message to the record in Cloud Spanner.

See more: langchain_google_spanner.chat_message_history.SpannerChatMessageHistory.add_message

langchain_google_spanner.chat_message_history.SpannerChatMessageHistory.clear

clear() -> None

Clear session memory from Cloud Spanner.

See more: langchain_google_spanner.chat_message_history.SpannerChatMessageHistory.clear

langchain_google_spanner.chat_message_history.SpannerChatMessageHistory.create_chat_history_table

create_chat_history_table(
    instance_id: str,
    database_id: str,
    table_name: str,
    client: typing.Optional[google.cloud.spanner_v1.client.Client] = None,
) -> None

Create a chat history table in a Cloud Spanner database.

See more: langchain_google_spanner.chat_message_history.SpannerChatMessageHistory.create_chat_history_table

langchain_google_spanner.loader.SpannerDocumentSaver

SpannerDocumentSaver(
    instance_id: str,
    database_id: str,
    table_name: str,
    content_column: str = "page_content",
    metadata_columns: typing.List[str] = [],
    metadata_json_column: str = "langchain_metadata",
    primary_key: typing.Optional[str] = None,
    client: typing.Optional[google.cloud.spanner_v1.client.Client] = None,
)

Initialize Spanner document saver.

See more: langchain_google_spanner.loader.SpannerDocumentSaver

langchain_google_spanner.loader.SpannerDocumentSaver.add_documents

add_documents(documents: typing.List[langchain_core.documents.base.Document])

Add documents to the Spanner table.

See more: langchain_google_spanner.loader.SpannerDocumentSaver.add_documents

langchain_google_spanner.loader.SpannerDocumentSaver.create_table

create_table(
    client: google.cloud.spanner_v1.client.Client,
    instance_id: str,
    database_id: str,
    table_name: str,
    primary_key: str,
    metadata_json_column: str,
    content_column: str,
    metadata_columns: typing.List[langchain_google_spanner.loader.Column],
)

Create a new table in Spanner database.

See more: langchain_google_spanner.loader.SpannerDocumentSaver.create_table

langchain_google_spanner.loader.SpannerDocumentSaver.delete

delete(documents: typing.List[langchain_core.documents.base.Document])

Delete documents from the table.

See more: langchain_google_spanner.loader.SpannerDocumentSaver.delete

langchain_google_spanner.loader.SpannerDocumentSaver.init_document_table

init_document_table(
    instance_id: str,
    database_id: str,
    table_name: str,
    content_column: str = "page_content",
    metadata_columns: typing.List[langchain_google_spanner.loader.Column] = [],
    primary_key: str = "",
    store_metadata: bool = True,
    metadata_json_column: str = "langchain_metadata",
)

Create a new table to store docs with a custom schema.

See more: langchain_google_spanner.loader.SpannerDocumentSaver.init_document_table

langchain_google_spanner.loader.SpannerLoader

SpannerLoader(
    instance_id: str,
    database_id: str,
    query: str,
    content_columns: typing.List[str] = [],
    metadata_columns: typing.List[str] = [],
    format: str = "text",
    databoost: bool = False,
    metadata_json_column: str = "langchain_metadata",
    staleness: typing.Union[float, datetime.datetime] = 0.0,
    client: typing.Optional[google.cloud.spanner_v1.client.Client] = None,
)

Initialize Spanner document loader.

See more: langchain_google_spanner.loader.SpannerLoader

langchain_google_spanner.loader.SpannerLoader.lazy_load

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

A lazy loader for langchain documents from a Spanner database.

See more: langchain_google_spanner.loader.SpannerLoader.lazy_load

langchain_google_spanner.loader.SpannerLoader.load

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

Load langchain documents from a Spanner database.

See more: langchain_google_spanner.loader.SpannerLoader.load

langchain_google_spanner.vector_store.DialectSemantics.getDistanceFunction

getDistanceFunction(distance_strategy=DistanceStrategy.EUCLIDEIAN) -> str

Abstract method to get the distance function based on the provided distance strategy.

See more: langchain_google_spanner.vector_store.DialectSemantics.getDistanceFunction

langchain_google_spanner.vector_store.GoogleSqlSemnatics.getDistanceFunction

getDistanceFunction(distance_strategy=DistanceStrategy.EUCLIDEIAN) -> str

Abstract method to get the distance function based on the provided distance strategy.

See more: langchain_google_spanner.vector_store.GoogleSqlSemnatics.getDistanceFunction

langchain_google_spanner.vector_store.PGSqlSemnatics.getDistanceFunction

getDistanceFunction(distance_strategy=DistanceStrategy.EUCLIDEIAN) -> str

Abstract method to get the distance function based on the provided distance strategy.

See more: langchain_google_spanner.vector_store.PGSqlSemnatics.getDistanceFunction

langchain_google_spanner.vector_store.QueryParameters

QueryParameters(
    algorithm=NearestNeighborsAlgorithm.EXACT_NEAREST_NEIGHBOR,
    distance_strategy=DistanceStrategy.EUCLIDEIAN,
    read_timestamp: typing.Optional[datetime.datetime] = None,
    min_read_timestamp: typing.Optional[datetime.datetime] = None,
    max_staleness: typing.Optional[datetime.timedelta] = None,
    exact_staleness: typing.Optional[datetime.timedelta] = None,
)

Initialize query parameters.

See more: langchain_google_spanner.vector_store.QueryParameters

langchain_google_spanner.vector_store.SpannerVectorStore._generate_sql

_generate_sql(
    dialect,
    table_name,
    id_column,
    content_column,
    embedding_column,
    column_configs,
    primary_key,
    secondary_indexes: typing.Optional[
        typing.List[langchain_google_spanner.vector_store.SecondaryIndex]
    ] = None,
)

Generate SQL for creating the vector store table.

See more: langchain_google_spanner.vector_store.SpannerVectorStore._generate_sql

langchain_google_spanner.vector_store.SpannerVectorStore._select_relevance_score_fn

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

The 'correct' relevance function may differ depending on a few things, including:

  • the distance / similarity metric used by the VectorStore
  • the scale of your embeddings (OpenAI's are unit normed.

See more: langchain_google_spanner.vector_store.SpannerVectorStore._select_relevance_score_fn

langchain_google_spanner.vector_store.SpannerVectorStore.add_documents

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

Add documents to the vector store.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.add_documents

langchain_google_spanner.vector_store.SpannerVectorStore.add_texts

add_texts(
    texts: typing.Iterable[str],
    metadatas: typing.Optional[typing.List[dict]] = None,
    ids: typing.Optional[typing.List[str]] = None,
    batch_size: int = 5000,
    **kwargs: typing.Any
) -> typing.List[str]

Add texts to the vector store index.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.add_texts

langchain_google_spanner.vector_store.SpannerVectorStore.delete

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

Delete records from the vector store.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.delete

langchain_google_spanner.vector_store.SpannerVectorStore.from_documents

from_documents(documents: typing.List[langchain_core.documents.base.Document], embedding: langchain_core.embeddings.embeddings.Embeddings, instance_id: str, database_id: str, table_name: str, id_column: str = 'langchain_id', content_column: str = 'content', embedding_column: str = 'embedding', ids: typing.Optional[typing.List[str]] = None, client: typing.Optional[google.cloud.spanner_v1.client.Client] = None, metadata_columns: typing.Optional[typing.List[str]] = None, ignore_metadata_columns: typing.Optional[typing.List[str]] = None, metadata_json_column: typing.Optional[str] = None, query_parameter: langchain_google_spanner.vector_store.QueryParameters =

Initialize SpannerVectorStore from a list of documents.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.from_documents

langchain_google_spanner.vector_store.SpannerVectorStore.from_texts

from_texts(texts: typing.List[str], embedding: langchain_core.embeddings.embeddings.Embeddings, instance_id: str, database_id: str, table_name: str, metadatas: typing.Optional[typing.List[dict]] = None, id_column: str = 'langchain_id', content_column: str = 'content', embedding_column: str = 'embedding', ids: typing.Optional[typing.List[str]] = None, client: typing.Optional[google.cloud.spanner_v1.client.Client] = None, metadata_columns: typing.Optional[typing.List[str]] = None, ignore_metadata_columns: typing.Optional[typing.List[str]] = None, metadata_json_column: typing.Optional[str] = None, query_parameter: langchain_google_spanner.vector_store.QueryParameters =

Initialize SpannerVectorStore from a list of texts.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.from_texts

langchain_google_spanner.vector_store.SpannerVectorStore.init_vector_store_table

init_vector_store_table(
    instance_id: str,
    database_id: str,
    table_name: str,
    client: typing.Optional[google.cloud.spanner_v1.client.Client] = None,
    id_column: typing.Union[
        str, langchain_google_spanner.vector_store.TableColumn
    ] = "langchain_id",
    content_column: str = "content",
    embedding_column: str = "embedding",
    metadata_columns: typing.Optional[
        typing.List[langchain_google_spanner.vector_store.TableColumn]
    ] = None,
    primary_key: typing.Optional[str] = None,
    vector_size: typing.Optional[int] = None,
    secondary_indexes: typing.Optional[
        typing.List[langchain_google_spanner.vector_store.SecondaryIndex]
    ] = None,
) -> bool

Initialize the vector store new table in Google Cloud Spanner.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.init_vector_store_table

langchain_google_spanner.vector_store.SpannerVectorStore.max_marginal_relevance_search

max_marginal_relevance_search(
    query: str,
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    pre_filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

Return docs selected using the maximal marginal relevance.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.max_marginal_relevance_search

langchain_google_spanner.vector_store.SpannerVectorStore.max_marginal_relevance_search_by_vector

max_marginal_relevance_search_by_vector(
    embedding: typing.List[float],
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    pre_filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

Return docs selected using the maximal marginal relevance.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.max_marginal_relevance_search_by_vector

langchain_google_spanner.vector_store.SpannerVectorStore.max_marginal_relevance_search_with_score_by_vector

max_marginal_relevance_search_with_score_by_vector(
    embedding: typing.List[float],
    k: int = 4,
    fetch_k: int = 20,
    lambda_mult: float = 0.5,
    pre_filter: typing.Optional[str] = None,
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]

Return docs and their similarity scores selected using the maximal marginal relevance.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.max_marginal_relevance_search_with_score_by_vector

langchain_google_spanner.vector_store.SpannerVectorStore.similarity_search

similarity_search(
    query: str,
    k: int = 4,
    pre_filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

Perform similarity search for a given query.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.similarity_search

langchain_google_spanner.vector_store.SpannerVectorStore.similarity_search_by_vector

similarity_search_by_vector(
    embedding: typing.List[float],
    k: int = 4,
    pre_filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]

Perform similarity search by vector.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.similarity_search_by_vector

langchain_google_spanner.vector_store.SpannerVectorStore.similarity_search_with_score

similarity_search_with_score(
    query: str,
    k: int = 4,
    pre_filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]

Perform similarity search for a given query with scores.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.similarity_search_with_score

langchain_google_spanner.vector_store.SpannerVectorStore.similarity_search_with_score_by_vector

similarity_search_with_score_by_vector(
    embedding: typing.List[float],
    k: int = 4,
    pre_filter: typing.Optional[str] = None,
    **kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]

Perform similarity search for a given query.

See more: langchain_google_spanner.vector_store.SpannerVectorStore.similarity_search_with_score_by_vector