The rpd_ml_stats table tracks the usage of
successful MySQL AI routines. These metrics reset whenever the
respective DB system restarts.
The following AutoML routines are tracked:
ML_TRAINML_EXPLAINML_PREDICT_ROWML_PREDICT_TABLEML_EXPLAIN_ROWML_EXPLAIN_TABLE
The following GenAI routines are tracked:
ML_GENERATEML_EMBED_ROW
The rpd_ml_stats table has these columns:
-
STATUS_NAMEIdentifies the type of meter tracking usage.
-
STATUS_VALUEDisplays metrics for metering. Content is displayed in JSON format.
Metrics in the table are entries as JSON values. The following metrics are used:
-
n_cellsThe total number of table cells processed by the AutoML routine for all invocations.
-
n_cells_user_excludedThe total number of table cells manually excluded for the AutoML routine.
-
n_blob_cellsThe total number of table BLOB cells processed by the AutoML routine for all invocations.
-
table_size_bytesThe total number of bytes of data processed by the AutoML routine for all invocations.
-
blob_size_bytesThe total number of bytes of BLOB/TEXT data processed by the AutoML routine for all invocations.
-
model_size_bytesThe total number of bytes of data for the AutoML model that is trained. This includes any explainer models. This metric only applies to the
ML_TRAINandML_EXPLAINAutoML routines. All other routines will display NULL values. -
input_size_bytesThe cumulative size in bytes of all input string/document invocations ingested by the GenAI routine.
-
context_size_bytesThe size in bytes of the context string referenced when generating the response. This metric only applies to the
ML_GENERATEGenAI routine since theML_EMBED_ROWroutine does not have context. The metric will still appear forML_EMBED_ROW, but will display a value of 0. -
output_size_bytesThe cumulative size in bytes of responses generated by all invocations for the GenAI routine.
-
n_invocationsThe total number of times the routine has been successfully invoked on the MySQL AI Engine.
-
last_updated_timestampThe POSIX timestamp of the last call.