Class SpannerDocumentSaver (0.3.0)

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,
)

Save docs to Google Cloud Spanner.

Methods

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.

Parameters
Name	Description
`instance_id`	`str` The Spanner instance to load data to.
`database_id`	`str` The Spanner database to load data to.
`table_name`	`str` The table name to load data to.
`content_column`	`str` The name of the content column. Defaulted to the first column.
`metadata_columns`	`typing.List[str]` This is for user to opt-in a selection of columns to use. Defaulted to use all columns.
`metadata_json_column`	`str` The name of the special JSON column. Defaulted to use "langchain_metadata".
`client`	`typing.Optional[google.cloud.spanner_v1.client.Client]` The connection object to use. This can be used to customized project id and credentials.

add_documents

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

Add documents to the Spanner table.

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.

Parameters
Name	Description
`client`	`Client` The connection object to use.
`instance_id`	`str` The Spanner instance to load data to.
`database_id`	`str` The Spanner database to load data to.
`table_name`	`str` The table name to load data to.
`primary_key`	`str` The name of the primary key for the table.
`metadata_json_column`	`str` The name of the special JSON column.
`content_column`	`str` The name of the content column.
`metadata_columns`	`typing.List[langchain_google_spanner.loader.Column]` The metadata columns for custom schema.

delete

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

Delete documents from the table.

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.

Parameters
Name	Description
`instance_id`	`str` The Spanner instance to load data to.
`database_id`	`str` The Spanner database to load data to.
`table_name`	`str` The table name to load data to.
`content_column`	`str` The name of the content column.
`metadata_columns`	`typing.List[langchain_google_spanner.loader.Column]` The metadata columns for custom schema.
`primary_key`	`str` The name of the primary key.
`store_metadata`	`bool` If true, extra metadata will be stored in the "langchain_metadata" column. Defaulted to true.
`metadata_json_column`	`str` The name of the special JSON column. Defaulted to use "langchain_metadata".

Class SpannerDocumentSaver (0.3.0) Stay organized with collections Save and categorize content based on your preferences.