Package Methods (0.12.1)

Summary of entries of Methods for langchain-google-cloud-sql-pg.

langchain_google_cloud_sql_pg.engine._get_iam_principal_email

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

Get email address associated with current authenticated IAM principal.

See more: langchain_google_cloud_sql_pg.engine._get_iam_principal_email

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory

PostgresChatMessageHistory(
 key: object,
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 history: langchain_google_cloud_sql_pg.async_chat_message_history.AsyncPostgresChatMessageHistory,
)

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.aadd_message

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

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.aadd_messages

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

Append a list of messages to the record in PostgreSQL.

See more: langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.aadd_messages

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.aclear

aclear() -> None

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.add_message

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

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.add_messages

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

Append a list of messages to the record in PostgreSQL.

See more: langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.add_messages

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.clear

clear() -> None

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.create

create(
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 session_id: str,
 table_name: str,
 schema_name: str = "public",
) -> langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory

Create a new PostgresChatMessageHistory instance.

See more: langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.create

langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.create_sync

create_sync(
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 session_id: str,
 table_name: str,
 schema_name: str = "public",
) -> langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory

Create a new PostgresChatMessageHistory instance.

See more: langchain_google_cloud_sql_pg.chat_message_history.PostgresChatMessageHistory.create_sync

langchain_google_cloud_sql_pg.engine.Column.__post_init__

__post_init__()

Check if initialization parameters are valid.

See more: langchain_google_cloud_sql_pg.engine.Column.post_init

langchain_google_cloud_sql_pg.engine.PostgresEngine

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

PostgresEngine constructor.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine

langchain_google_cloud_sql_pg.engine.PostgresEngine._ainit_chat_history_table

_ainit_chat_history_table(table_name: str, schema_name: str = "public") -> None

Create a Cloud SQL table to store chat history.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine._ainit_chat_history_table

langchain_google_cloud_sql_pg.engine.PostgresEngine._ainit_vectorstore_table

_ainit_vectorstore_table(
 table_name: str,
 vector_size: int,
 schema_name: str = "public",
 content_column: str = "content",
 embedding_column: str = "embedding",
 metadata_columns: list[langchain_google_cloud_sql_pg.engine.Column] = [],
 metadata_json_column: str = "langchain_metadata",
 id_column: typing.Union[
 str, langchain_google_cloud_sql_pg.engine.Column
 ] = "langchain_id",
 overwrite_existing: bool = False,
 store_metadata: bool = True,
) -> None

Create a table for saving of vectors to be used with PostgresVectorStore.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine._ainit_vectorstore_table

langchain_google_cloud_sql_pg.engine.PostgresEngine._aload_table_schema

_aload_table_schema(
 table_name: str, schema_name: str = "public"
) -> sqlalchemy.sql.schema.Table

Load table schema from existing table in PgSQL database.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine._aload_table_schema

langchain_google_cloud_sql_pg.engine.PostgresEngine._create

_create(
 project_id: str,
 region: str,
 instance: str,
 database: str,
 ip_type: typing.Union[str, google.cloud.sql.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,
 quota_project: typing.Optional[str] = None,
 iam_account_email: typing.Optional[str] = None,
 engine_args: typing.Mapping = {},
) -> langchain_google_cloud_sql_pg.engine.PostgresEngine

Create a PostgresEngine instance.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine._create

langchain_google_cloud_sql_pg.engine.PostgresEngine._run_as_async

_run_as_async(
 coro: typing.Awaitable[langchain_google_cloud_sql_pg.engine.T],
) -> langchain_google_cloud_sql_pg.engine.T

Run an async coroutine asynchronously.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine._run_as_async

langchain_google_cloud_sql_pg.engine.PostgresEngine._run_as_sync

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

Run an async coroutine synchronously.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine._run_as_sync

langchain_google_cloud_sql_pg.engine.PostgresEngine.afrom_instance

afrom_instance(
 project_id: str,
 region: str,
 instance: str,
 database: str,
 user: typing.Optional[str] = None,
 password: typing.Optional[str] = None,
 ip_type: typing.Union[
 str, google.cloud.sql.connector.enums.IPTypes
 ] = IPTypes.PUBLIC,
 quota_project: typing.Optional[str] = None,
 iam_account_email: typing.Optional[str] = None,
 engine_args: typing.Mapping = {},
) -> langchain_google_cloud_sql_pg.engine.PostgresEngine

Create a PostgresEngine from a Postgres instance.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.afrom_instance

langchain_google_cloud_sql_pg.engine.PostgresEngine.ainit_chat_history_table

ainit_chat_history_table(table_name: str, schema_name: str = "public") -> None

Create a Cloud SQL table to store chat history.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.ainit_chat_history_table

langchain_google_cloud_sql_pg.engine.PostgresEngine.ainit_document_table

ainit_document_table(
 table_name: str,
 schema_name: str = "public",
 content_column: str = "page_content",
 metadata_columns: list[langchain_google_cloud_sql_pg.engine.Column] = [],
 metadata_json_column: str = "langchain_metadata",
 store_metadata: bool = True,
) -> None

Create a table for saving of langchain documents.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.ainit_document_table

langchain_google_cloud_sql_pg.engine.PostgresEngine.ainit_vectorstore_table

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

Create a table for saving of vectors to be used with PostgresVectorStore.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.ainit_vectorstore_table

langchain_google_cloud_sql_pg.engine.PostgresEngine.close

close() -> None

Dispose of connection pool.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.close

langchain_google_cloud_sql_pg.engine.PostgresEngine.from_engine

from_engine(
 engine: sqlalchemy.ext.asyncio.engine.AsyncEngine,
 loop: typing.Optional[asyncio.events.AbstractEventLoop] = None,
) -> langchain_google_cloud_sql_pg.engine.PostgresEngine

Create an PostgresEngine instance from an AsyncEngine.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.from_engine

langchain_google_cloud_sql_pg.engine.PostgresEngine.from_engine_args

from_engine_args(
 url: str | sqlalchemy.engine.url.URL, **kwargs: typing.Any
) -> langchain_google_cloud_sql_pg.engine.PostgresEngine

Create an PostgresEngine instance from arguments.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.from_engine_args

langchain_google_cloud_sql_pg.engine.PostgresEngine.from_instance

from_instance(
 project_id: str,
 region: str,
 instance: str,
 database: str,
 user: typing.Optional[str] = None,
 password: typing.Optional[str] = None,
 ip_type: typing.Union[
 str, google.cloud.sql.connector.enums.IPTypes
 ] = IPTypes.PUBLIC,
 quota_project: typing.Optional[str] = None,
 iam_account_email: typing.Optional[str] = None,
 engine_args: typing.Mapping = {},
) -> langchain_google_cloud_sql_pg.engine.PostgresEngine

Create a PostgresEngine from a Postgres instance.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.from_instance

langchain_google_cloud_sql_pg.engine.PostgresEngine.init_chat_history_table

init_chat_history_table(table_name: str, schema_name: str = "public") -> None

Create a Cloud SQL table to store chat history.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.init_chat_history_table

langchain_google_cloud_sql_pg.engine.PostgresEngine.init_document_table

init_document_table(
 table_name: str,
 schema_name: str = "public",
 content_column: str = "page_content",
 metadata_columns: list[langchain_google_cloud_sql_pg.engine.Column] = [],
 metadata_json_column: str = "langchain_metadata",
 store_metadata: bool = True,
) -> None

Create a table for saving of langchain documents.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.init_document_table

langchain_google_cloud_sql_pg.engine.PostgresEngine.init_vectorstore_table

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

Create a table for saving of vectors to be used with PostgresVectorStore.

See more: langchain_google_cloud_sql_pg.engine.PostgresEngine.init_vectorstore_table

langchain_google_cloud_sql_pg.indexes.BaseIndex.index_options

index_options() -> str

Set index query options for vector store initialization.

See more: langchain_google_cloud_sql_pg.indexes.BaseIndex.index_options

langchain_google_cloud_sql_pg.indexes.DistanceStrategy._generate_next_value_

_generate_next_value_(start, count, last_values)

Generate the next value when not given.

See more: langchain_google_cloud_sql_pg.indexes.DistanceStrategy.generate_next_value

langchain_google_cloud_sql_pg.indexes.HNSWIndex.index_options

index_options() -> str

Set index query options for vector store initialization.

See more: langchain_google_cloud_sql_pg.indexes.HNSWIndex.index_options

langchain_google_cloud_sql_pg.indexes.HNSWQueryOptions.to_string

to_string()

Convert index attributes to string.

See more: langchain_google_cloud_sql_pg.indexes.HNSWQueryOptions.to_string

langchain_google_cloud_sql_pg.indexes.IVFFlatIndex.index_options

index_options() -> str

Set index query options for vector store initialization.

See more: langchain_google_cloud_sql_pg.indexes.IVFFlatIndex.index_options

langchain_google_cloud_sql_pg.indexes.IVFFlatQueryOptions.to_string

to_string()

Convert index attributes to string.

See more: langchain_google_cloud_sql_pg.indexes.IVFFlatQueryOptions.to_string

langchain_google_cloud_sql_pg.indexes.QueryOptions.to_string

to_string() -> str

Convert index attributes to string.

See more: langchain_google_cloud_sql_pg.indexes.QueryOptions.to_string

langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver

PostgresDocumentSaver(
 key: object,
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 saver: langchain_google_cloud_sql_pg.async_loader.AsyncPostgresDocumentSaver,
)

PostgresDocumentSaver constructor.

See more: langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver

langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.aadd_documents

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

Save documents in the DocumentSaver table.

See more: langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.aadd_documents

langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.add_documents

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

Save documents in the DocumentSaver table.

See more: langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.add_documents

langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.adelete

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

Delete all instances of a document from the DocumentSaver table by matching the entire Document object.

See more: langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.adelete

langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.create

create(
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 table_name: str,
 schema_name: str = "public",
 content_column: str = "page_content",
 metadata_columns: list[str] = [],
 metadata_json_column: typing.Optional[str] = "langchain_metadata",
) -> langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver

Create an PostgresDocumentSaver instance.

See more: langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.create

langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.create_sync

create_sync(
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 table_name: str,
 schema_name: str = "public",
 content_column: str = "page_content",
 metadata_columns: list[str] = [],
 metadata_json_column: str = "langchain_metadata",
) -> langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver

Create an PostgresDocumentSaver instance.

See more: langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.create_sync

langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.delete

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

Delete all instances of a document from the DocumentSaver table by matching the entire Document object.

See more: langchain_google_cloud_sql_pg.loader.PostgresDocumentSaver.delete

langchain_google_cloud_sql_pg.loader.PostgresLoader

PostgresLoader(
 key: object,
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 loader: langchain_google_cloud_sql_pg.async_loader.AsyncPostgresLoader,
)

PostgresLoader constructor.

See more: langchain_google_cloud_sql_pg.loader.PostgresLoader

langchain_google_cloud_sql_pg.loader.PostgresLoader.alazy_load

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

Load PostgreSQL data into Document objects lazily.

See more: langchain_google_cloud_sql_pg.loader.PostgresLoader.alazy_load

langchain_google_cloud_sql_pg.loader.PostgresLoader.aload

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

Load PostgreSQL data into Document objects.

See more: langchain_google_cloud_sql_pg.loader.PostgresLoader.aload

langchain_google_cloud_sql_pg.loader.PostgresLoader.create

create(
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 query: typing.Optional[str] = None,
 table_name: typing.Optional[str] = None,
 schema_name: str = "public",
 content_columns: typing.Optional[list[str]] = None,
 metadata_columns: typing.Optional[list[str]] = None,
 metadata_json_column: typing.Optional[str] = None,
 format: typing.Optional[str] = None,
 formatter: typing.Optional[typing.Callable] = None,
) -> langchain_google_cloud_sql_pg.loader.PostgresLoader

Create a new PostgresLoader instance.

See more: langchain_google_cloud_sql_pg.loader.PostgresLoader.create

langchain_google_cloud_sql_pg.loader.PostgresLoader.create_sync

create_sync(
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 query: typing.Optional[str] = None,
 table_name: typing.Optional[str] = None,
 schema_name: str = "public",
 content_columns: typing.Optional[list[str]] = None,
 metadata_columns: typing.Optional[list[str]] = None,
 metadata_json_column: typing.Optional[str] = None,
 format: typing.Optional[str] = None,
 formatter: typing.Optional[typing.Callable] = None,
) -> langchain_google_cloud_sql_pg.loader.PostgresLoader

Create a new PostgresLoader instance.

See more: langchain_google_cloud_sql_pg.loader.PostgresLoader.create_sync

langchain_google_cloud_sql_pg.loader.PostgresLoader.lazy_load

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

Load PostgreSQL data into Document objects lazily.

See more: langchain_google_cloud_sql_pg.loader.PostgresLoader.lazy_load

langchain_google_cloud_sql_pg.loader.PostgresLoader.load

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

Load PostgreSQL data into Document objects.

See more: langchain_google_cloud_sql_pg.loader.PostgresLoader.load

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore

PostgresVectorStore(
 key: object,
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 vs: langchain_google_cloud_sql_pg.async_vectorstore.AsyncPostgresVectorStore,
)

PostgresVectorStore constructor.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore._select_relevance_score_fn

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

Select a relevance function based on distance strategy.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore._select_relevance_score_fn

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.aadd_documents

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.aadd_texts

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.aapply_vector_index

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

Create an index on the vector store table.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.aapply_vector_index

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.add_documents

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.add_texts

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.adelete

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.adrop_vector_index

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.afrom_documents

afrom_documents(
 documents: list[langchain_core.documents.base.Document],
 embedding: langchain_core.embeddings.embeddings.Embeddings,
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 table_name: str,
 schema_name: str = "public",
 ids: typing.Optional[list] = None,
 content_column: str = "content",
 embedding_column: str = "embedding",
 metadata_columns: list[str] = [],
 ignore_metadata_columns: typing.Optional[list[str]] = None,
 id_column: str = "langchain_id",
 metadata_json_column: str = "langchain_metadata",
 distance_strategy: langchain_google_cloud_sql_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_cloud_sql_pg.indexes.QueryOptions
 ] = None,
) -> langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore

Create an PostgresVectorStore instance from documents.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.afrom_documents

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.afrom_texts

afrom_texts(
 texts: list[str],
 embedding: langchain_core.embeddings.embeddings.Embeddings,
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 table_name: str,
 schema_name: str = "public",
 metadatas: typing.Optional[list[dict]] = None,
 ids: typing.Optional[list] = None,
 content_column: str = "content",
 embedding_column: str = "embedding",
 metadata_columns: list[str] = [],
 ignore_metadata_columns: typing.Optional[list[str]] = None,
 id_column: str = "langchain_id",
 metadata_json_column: str = "langchain_metadata",
 distance_strategy: langchain_google_cloud_sql_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_cloud_sql_pg.indexes.QueryOptions
 ] = None,
) -> langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore

Create an PostgresVectorStore instance from texts.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.afrom_texts

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.ais_valid_index

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.amax_marginal_relevance_search

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
) -> list[langchain_core.documents.base.Document]

Return docs selected using the maximal marginal relevance.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.amax_marginal_relevance_search

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.amax_marginal_relevance_search_by_vector

amax_marginal_relevance_search_by_vector(
 embedding: 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
) -> list[langchain_core.documents.base.Document]

Return docs selected using the maximal marginal relevance.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.amax_marginal_relevance_search_by_vector

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.amax_marginal_relevance_search_with_score_by_vector

amax_marginal_relevance_search_with_score_by_vector(
 embedding: 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
) -> list[tuple[langchain_core.documents.base.Document, float]]

Return docs and distance scores selected using the maximal marginal relevance.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.amax_marginal_relevance_search_with_score_by_vector

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.apply_vector_index

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

Create an index on the vector store table.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.apply_vector_index

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.areindex

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.asimilarity_search

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

Return docs selected by similarity search on query.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.asimilarity_search

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.asimilarity_search_by_vector

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

Return docs selected by vector similarity search.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.asimilarity_search_by_vector

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.asimilarity_search_with_score

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

Return docs and distance scores selected by similarity search on query.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.asimilarity_search_with_score

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.asimilarity_search_with_score_by_vector

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

Return docs and distance scores selected by vector similarity search.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.asimilarity_search_with_score_by_vector

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.create

create(
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 embedding_service: langchain_core.embeddings.embeddings.Embeddings,
 table_name: str,
 schema_name: str = "public",
 content_column: str = "content",
 embedding_column: str = "embedding",
 metadata_columns: list[str] = [],
 ignore_metadata_columns: typing.Optional[list[str]] = None,
 id_column: str = "langchain_id",
 metadata_json_column: typing.Optional[str] = "langchain_metadata",
 distance_strategy: langchain_google_cloud_sql_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_cloud_sql_pg.indexes.QueryOptions
 ] = None,
) -> langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore

Create a new PostgresVectorStore instance.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.create

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.create_sync

create_sync(
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 embedding_service: langchain_core.embeddings.embeddings.Embeddings,
 table_name: str,
 schema_name: str = "public",
 content_column: str = "content",
 embedding_column: str = "embedding",
 metadata_columns: list[str] = [],
 ignore_metadata_columns: typing.Optional[list[str]] = None,
 id_column: str = "langchain_id",
 metadata_json_column: str = "langchain_metadata",
 distance_strategy: langchain_google_cloud_sql_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_cloud_sql_pg.indexes.QueryOptions
 ] = None,
) -> langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore

Create a new PostgresVectorStore instance.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.create_sync

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.delete

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.drop_vector_index

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.from_documents

from_documents(
 documents: list[langchain_core.documents.base.Document],
 embedding: langchain_core.embeddings.embeddings.Embeddings,
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 table_name: str,
 schema_name: str = "public",
 ids: typing.Optional[list] = None,
 content_column: str = "content",
 embedding_column: str = "embedding",
 metadata_columns: list[str] = [],
 ignore_metadata_columns: typing.Optional[list[str]] = None,
 id_column: str = "langchain_id",
 metadata_json_column: str = "langchain_metadata",
 distance_strategy: langchain_google_cloud_sql_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_cloud_sql_pg.indexes.QueryOptions
 ] = None,
) -> langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore

Create an PostgresVectorStore instance from documents.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.from_documents

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.from_texts

from_texts(
 texts: list[str],
 embedding: langchain_core.embeddings.embeddings.Embeddings,
 engine: langchain_google_cloud_sql_pg.engine.PostgresEngine,
 table_name: str,
 schema_name: str = "public",
 metadatas: typing.Optional[list[dict]] = None,
 ids: typing.Optional[list] = None,
 content_column: str = "content",
 embedding_column: str = "embedding",
 metadata_columns: list[str] = [],
 ignore_metadata_columns: typing.Optional[list[str]] = None,
 id_column: str = "langchain_id",
 metadata_json_column: str = "langchain_metadata",
 distance_strategy: langchain_google_cloud_sql_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_cloud_sql_pg.indexes.QueryOptions
 ] = None,
) -> langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore

Create an PostgresVectorStore instance from texts.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.from_texts

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.is_valid_index

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.max_marginal_relevance_search

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
) -> list[langchain_core.documents.base.Document]

Return docs selected using the maximal marginal relevance.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.max_marginal_relevance_search

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.max_marginal_relevance_search_by_vector

max_marginal_relevance_search_by_vector(
 embedding: 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
) -> list[langchain_core.documents.base.Document]

Return docs selected using the maximal marginal relevance.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.max_marginal_relevance_search_by_vector

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.max_marginal_relevance_search_with_score_by_vector

max_marginal_relevance_search_with_score_by_vector(
 embedding: 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
) -> list[tuple[langchain_core.documents.base.Document, float]]

Return docs and distance scores selected using the maximal marginal relevance.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.max_marginal_relevance_search_with_score_by_vector

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.reindex

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

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.similarity_search

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

Return docs selected by similarity search on query.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.similarity_search

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.similarity_search_by_vector

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

Return docs selected by vector similarity search.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.similarity_search_by_vector

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.similarity_search_with_score

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

Return docs and distance scores selected by similarity search on query.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.similarity_search_with_score

langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.similarity_search_with_score_by_vector

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

Return docs and distance scores selected by similarity search on vector.

See more: langchain_google_cloud_sql_pg.vectorstore.PostgresVectorStore.similarity_search_with_score_by_vector

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025年10月30日 UTC.