Module remote (0.22.0)

BigFrames general remote models.

Classes

VertexAIModel

VertexAIModel(
    endpoint: str,
    input: typing.Mapping[str, str],
    output: typing.Mapping[str, str],
    *,
    session: typing.Optional[bigframes.session.Session] = None,
    connection_name: typing.Optional[str] = None
)

Remote model from a Vertex AI https endpoint. User must specify https endpoint, input schema and output schema. How to deploy a model in Vertex AI https://cloud.google.com/bigquery/docs/bigquery-ml-remote-model-tutorial#Deploy-Model-on-Vertex-AI.

Parameters
Name	Description
`endpoint`	`str` Vertex AI https endpoint.
`input`	`Mapping` Input schema: `{column_name: column_type}`. Supported types are "bool", "string", "int64", "float64", "array
`output`	`Mapping` Output label schema: `{column_name: column_type}`. Supported the same types as the input.
`session`	`bigframes.Session or None` BQ session to create the model. If None, use the global default session.
`connection_name`	`str or None` Connection to connect with remote service. str of the format <PROJECT_NUMBER/PROJECT_ID>.