RagMetricsResponseMetrics

pydantic model openapi_client.models.rag_metrics_response_metrics.RagMetricsResponseMetrics

CloudWatch metrics for the lookback window. Always carries StartTime and EndTime, formatted as “YYYY-MM-DD HH:MM:SS”; each remaining key is a metric name whose value is a LabelAndDatapoints object. Empty when metrics collection failed. Which metric names appear depends on the vector store. Aurora reports CPUUtilization, ReadIOPS, WriteIOPS, ACUUtilization, DatabaseConnections and EngineUptime. OpenSearch Serverless reports SearchRequestRate, SearchRequestLatency, IngestionRequestRate, IngestionRequestLatency, SearchOCU, IndexingOCU, ActiveSearchOCU and ActiveIndexingOCU.

Fields:
field start_time: Optional[StrictStr] = None (alias 'StartTime')

Start of the metrics window.

field end_time: Optional[StrictStr] = None (alias 'EndTime')

End of the metrics window.

field additional_properties: Dict[str, Any] = {}
to_str()

Returns the string representation of the model using alias

Return type:

str

to_json()

Returns the JSON representation of the model using alias

Return type:

str

classmethod from_json(json_str)

Create an instance of RagMetricsResponseMetrics from a JSON string

Return type:

Optional[Self]

to_dict()

Return the dictionary representation of the model using alias.

This has the following differences from calling pydantic’s self.model_dump(by_alias=True):

  • None is only added to the output dict for nullable fields that were set at model initialization. Other fields with value None are ignored.

  • Fields in self.additional_properties are added to the output dict.

Return type:

Dict[str, Any]

classmethod from_dict(obj)

Create an instance of RagMetricsResponseMetrics from a dict

Return type:

Optional[Self]