Class PredictRequestResponseLoggingConfig (1.101.0)

PredictRequestResponseLoggingConfig(
    mapping=None, *, ignore_unknown_fields=False, **kwargs
)

Configuration for logging request-response to a BigQuery table.

Attributes

Name Description
enabled bool
If logging is enabled or not.
sampling_rate float
Percentage of requests to be logged, expressed as a fraction in range(0,1].
bigquery_destination google.cloud.aiplatform_v1beta1.types.BigQueryDestination
BigQuery table for logging. If only given a project, a new dataset will be created with name logging_ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
request_response_logging_schema_version str
Output only. The schema version used in creating the BigQuery table for the request response logging. The versions are "v1" and "v2". The current default version is "v1".
enable_otel_logging bool
This field is used for large models. If true, in addition to the original large model logs, logs will be converted in OTel schema format, and saved in otel_log column. Default value is false.

Methods

PredictRequestResponseLoggingConfig

PredictRequestResponseLoggingConfig(
    mapping=None, *, ignore_unknown_fields=False, **kwargs
)

Configuration for logging request-response to a BigQuery table.