Wrong types on MlTrainedModelInferenceStats and MlTrainedModelDeploymentStats

[svalbuena]

🐛 Wrong type

The _ml/trained_models/<model_id>/_stats fails when deserializing the response. In a previous issue I reported and fixed another wrong type in the types of this response, but there are a couple more left. These types cause a deserialization error in the .NET client.

The timestamp field of MlTrainedModelInferenceStats needs to be a long:

export interface MlTrainedModelInferenceStats {
  cache_miss_count: integer
  failure_count: integer
  inference_count: integer
  missing_all_fields_count: integer
- timestamp: DateTime
+ timestamp: EpochTime<UnitMillis>
}

The nodes field of MlTrainedModelDeploymentStatsneeds to be an array:

export interface MlTrainedModelDeploymentStats {
  allocation_status: MlTrainedModelDeploymentAllocationStatus
  cache_size?: ByteSize
  deployment_id: Id
  error_count: integer
  inference_count: integer
  model_id: Id
- nodes: MlTrainedModelDeploymentNodesStats
+ nodes: MlTrainedModelDeploymentNodesStats[]
  number_of_allocations: integer
  queue_capacity: integer
  rejected_execution_count: integer
  reason: string
  start_time: EpochTime<UnitMillis>
  state: MlDeploymentState
  threads_per_allocation: integer
  timeout_count: integer
}

Sample response of GET http://localhost:9200/_ml/trained_models/intfloat__e5-small-v2/_stats

{
    "count": 1,
    "trained_model_stats": [
        {
            "model_id": "intfloat__e5-small-v2",
            "model_size_stats": {
                "model_size_bytes": 132921240,
                "required_native_memory_bytes": 734682164
            },
            "pipeline_count": 1,
            "ingest": {
                "total": {
                    "count": 0,
                    "time_in_millis": 0,
                    "current": 0,
                    "failed": 0
                },
                "pipelines": {
                    "custom_embedding": {
                        "count": 0,
                        "time_in_millis": 0,
                        "current": 0,
                        "failed": 0,
                        "processors": [
                            {
                                "script": {
                                    "type": "script",
                                    "stats": {
                                        "count": 0,
                                        "time_in_millis": 0,
                                        "current": 0,
                                        "failed": 0
                                    }
                                }
                            },
                            {
                                "foreach": {
                                    "type": "foreach",
                                    "stats": {
                                        "count": 0,
                                        "time_in_millis": 0,
                                        "current": 0,
                                        "failed": 0
                                    }
                                }
                            }
                        ]
                    }
                }
            },
            "inference_stats": {
                "failure_count": 0,
                "inference_count": 13,
                "cache_miss_count": 0,
                "missing_all_fields_count": 0,
                "timestamp": 1722591230386
            },
            "deployment_stats": {
                "deployment_id": "intfloat__e5-small-v2",
                "model_id": "intfloat__e5-small-v2",
                "threads_per_allocation": 1,
                "number_of_allocations": 1,
                "queue_capacity": 1024,
                "state": "started",
                "allocation_status": {
                    "allocation_count": 1,
                    "target_allocation_count": 1,
                    "state": "fully_allocated"
                },
                "cache_size": "126.7mb",
                "priority": "normal",
                "start_time": 1722254553506,
                "inference_count": 13,
                "peak_throughput_per_minute": 5,
                "nodes": [
                    {
                        "node": {
                            "u8L8FqPtSb-eBsbz3yroew": {
                                "name": "d2acd1f5a58c",
                                "ephemeral_id": "q6hDvPcpQJaab7lSOE4sZw",
                                "transport_address": "172.18.0.2:9300",
                                "external_id": "d2acd1f5a58c",
                                "attributes": {
                                    "ml.max_jvm_size": "1073741824",
                                    "ml.allocated_processors_double": "16.0",
                                    "ml.allocated_processors": "16",
                                    "ml.machine_memory": "56860405760",
                                    "transform.config_version": "10.0.0",
                                    "xpack.installed": "true",
                                    "ml.config_version": "12.0.0"
                                },
                                "roles": [
                                    "data",
                                    "data_cold",
                                    "data_content",
                                    "data_frozen",
                                    "data_hot",
                                    "data_warm",
                                    "ingest",
                                    "master",
                                    "ml",
                                    "remote_cluster_client",
                                    "transform"
                                ],
                                "version": "8.12.0",
                                "min_index_version": 7000099,
                                "max_index_version": 8500008
                            }
                        },
                        "routing_state": {
                            "routing_state": "started"
                        },
                        "inference_count": 13,
                        "average_inference_time_ms": 14.615384615384615,
                        "average_inference_time_ms_excluding_cache_hits": 95,
                        "inference_cache_hit_count": 11,
                        "last_access": 1722591142606,
                        "number_of_pending_requests": 0,
                        "start_time": 1722588669854,
                        "threads_per_allocation": 1,
                        "number_of_allocations": 1,
                        "peak_throughput_per_minute": 5,
                        "throughput_last_minute": 2,
                        "average_inference_time_ms_last_minute": 0,
                        "inference_cache_hit_count_last_minute": 2
                    }
                ]
            }
        }
    ]
}