From a0309bb9d75162ad04f42e8b0197cf62321d006e Mon Sep 17 00:00:00 2001 From: Laura Trotta Date: Thu, 21 Nov 2024 17:11:36 +0100 Subject: [PATCH] fixes around ml --- output/openapi/elasticsearch-openapi.json | 114 +++-- .../elasticsearch-serverless-openapi.json | 90 ++-- output/schema/schema-serverless.json | 311 ++++++++++---- output/schema/schema.json | 399 +++++++++++++----- output/typescript/types.ts | 67 +-- specification/ml/_types/Datafeed.ts | 4 +- specification/ml/_types/DataframeAnalytics.ts | 2 + specification/ml/_types/Job.ts | 2 +- specification/ml/_types/Model.ts | 3 +- specification/ml/_types/TrainedModel.ts | 68 ++- 10 files changed, 765 insertions(+), 295 deletions(-) diff --git a/output/openapi/elasticsearch-openapi.json b/output/openapi/elasticsearch-openapi.json index 2bfba13f48..b8066625f9 100644 --- a/output/openapi/elasticsearch-openapi.json +++ b/output/openapi/elasticsearch-openapi.json @@ -73574,6 +73574,9 @@ }, "version": { "$ref": "#/components/schemas/_types:VersionString" + }, + "_meta": { + "$ref": "#/components/schemas/_types:Metadata" } }, "required": [ @@ -73961,7 +73964,11 @@ "$ref": "#/components/schemas/_types:Id" }, "node": { - "$ref": "#/components/schemas/ml._types:DiscoveryNode" + "description": "For started datafeeds only, this information pertains to the node upon which the datafeed is started.", + "type": "object", + "additionalProperties": { + "$ref": "#/components/schemas/ml._types:DiscoveryNode" + } }, "state": { "$ref": "#/components/schemas/ml._types:DatafeedState" @@ -73975,8 +73982,7 @@ }, "required": [ "datafeed_id", - "state", - "timing_stats" + "state" ] }, "ml._types:DiscoveryNode": { @@ -74355,7 +74361,11 @@ "$ref": "#/components/schemas/ml._types:ModelSizeStats" }, "node": { - "$ref": "#/components/schemas/ml._types:DiscoveryNode" + "description": "Contains properties for the node that runs the job.\nThis information is available only for open jobs.", + "type": "object", + "additionalProperties": { + "$ref": "#/components/schemas/ml._types:DiscoveryNode" + } }, "open_time": { "$ref": "#/components/schemas/_types:DateTime" @@ -74958,7 +74968,10 @@ "$ref": "#/components/schemas/ml._types:SnapshotUpgradeState" }, "node": { - "$ref": "#/components/schemas/ml._types:DiscoveryNode" + "type": "object", + "additionalProperties": { + "$ref": "#/components/schemas/ml._types:DiscoveryNode" + } }, "assignment_explanation": { "type": "string" @@ -75960,6 +75973,9 @@ "ml._types:TrainedModelDeploymentStats": { "type": "object", "properties": { + "adaptive_allocations": { + "$ref": "#/components/schemas/ml._types:AdaptiveAllocationsSettings" + }, "allocation_status": { "$ref": "#/components/schemas/ml._types:TrainedModelDeploymentAllocationStatus" }, @@ -75991,6 +76007,9 @@ "description": "The number of allocations requested.", "type": "number" }, + "priority": { + "$ref": "#/components/schemas/ml._types:TrainingPriority" + }, "queue_capacity": { "description": "The number of inference requests that can be queued before new requests are rejected.", "type": "number" @@ -76021,18 +76040,28 @@ "required": [ "allocation_status", "deployment_id", - "error_count", - "inference_count", "model_id", "nodes", - "number_of_allocations", - "queue_capacity", - "rejected_execution_count", - "reason", + "priority", "start_time", - "state", - "threads_per_allocation", - "timeout_count" + "state" + ] + }, + "ml._types:AdaptiveAllocationsSettings": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "min_number_of_allocations": { + "type": "number" + }, + "max_number_of_allocations": { + "type": "number" + } + }, + "required": [ + "enabled" ] }, "ml._types:TrainedModelDeploymentAllocationStatus": { @@ -76070,6 +76099,12 @@ "average_inference_time_ms": { "$ref": "#/components/schemas/_types:DurationValueUnitFloatMillis" }, + "average_inference_time_ms_last_minute": { + "$ref": "#/components/schemas/_types:DurationValueUnitFloatMillis" + }, + "average_inference_time_ms_excluding_cache_hits": { + "$ref": "#/components/schemas/_types:DurationValueUnitFloatMillis" + }, "error_count": { "description": "The number of errors when evaluating the trained model.", "type": "number" @@ -76078,12 +76113,22 @@ "description": "The total number of inference calls made against this node for this model.", "type": "number" }, + "inference_cache_hit_count": { + "type": "number" + }, + "inference_cache_hit_count_last_minute": { + "type": "number" + }, "last_access": { "description": "The epoch time stamp of the last inference call for the model on this node.", "type": "number" }, "node": { - "$ref": "#/components/schemas/ml._types:DiscoveryNode" + "description": "Information pertaining to the node.", + "type": "object", + "additionalProperties": { + "$ref": "#/components/schemas/ml._types:DiscoveryNode" + } }, "number_of_allocations": { "description": "The number of allocations assigned to this node.", @@ -76093,6 +76138,9 @@ "description": "The number of inference requests queued to be processed.", "type": "number" }, + "peak_throughput_per_minute": { + "type": "number" + }, "rejection_execution_count": { "description": "The number of inference requests that were not processed because the queue was full.", "type": "number" @@ -76107,24 +76155,17 @@ "description": "The number of threads used by each allocation during inference.", "type": "number" }, + "throughput_last_minute": { + "type": "number" + }, "timeout_count": { "description": "The number of inference requests that timed out before being processed.", "type": "number" } }, "required": [ - "average_inference_time_ms", - "error_count", - "inference_count", - "last_access", - "node", - "number_of_allocations", - "number_of_pending_requests", - "rejection_execution_count", - "routing_state", - "start_time", - "threads_per_allocation", - "timeout_count" + "peak_throughput_per_minute", + "routing_state" ] }, "ml._types:TrainedModelAssignmentRoutingTable": { @@ -76147,10 +76188,7 @@ } }, "required": [ - "reason", - "routing_state", - "current_allocations", - "target_allocations" + "routing_state" ] }, "ml._types:RoutingState": { @@ -76163,6 +76201,13 @@ "stopping" ] }, + "ml._types:TrainingPriority": { + "type": "string", + "enum": [ + "normal", + "low" + ] + }, "ml._types:DeploymentAssignmentState": { "type": "string", "enum": [ @@ -77167,13 +77212,6 @@ "field_names" ] }, - "ml._types:TrainingPriority": { - "type": "string", - "enum": [ - "normal", - "low" - ] - }, "ml._types:TrainedModelAssignment": { "type": "object", "properties": { diff --git a/output/openapi/elasticsearch-serverless-openapi.json b/output/openapi/elasticsearch-serverless-openapi.json index c81e5061fa..c1ef877196 100644 --- a/output/openapi/elasticsearch-serverless-openapi.json +++ b/output/openapi/elasticsearch-serverless-openapi.json @@ -48773,6 +48773,9 @@ }, "version": { "$ref": "#/components/schemas/_types:VersionString" + }, + "_meta": { + "$ref": "#/components/schemas/_types:Metadata" } }, "required": [ @@ -49508,8 +49511,7 @@ }, "required": [ "datafeed_id", - "state", - "timing_stats" + "state" ] }, "ml._types:DatafeedTimingStats": { @@ -50893,6 +50895,9 @@ "ml._types:TrainedModelDeploymentStats": { "type": "object", "properties": { + "adaptive_allocations": { + "$ref": "#/components/schemas/ml._types:AdaptiveAllocationsSettings" + }, "allocation_status": { "$ref": "#/components/schemas/ml._types:TrainedModelDeploymentAllocationStatus" }, @@ -50924,6 +50929,9 @@ "description": "The number of allocations requested.", "type": "number" }, + "priority": { + "$ref": "#/components/schemas/ml._types:TrainingPriority" + }, "queue_capacity": { "description": "The number of inference requests that can be queued before new requests are rejected.", "type": "number" @@ -50954,18 +50962,28 @@ "required": [ "allocation_status", "deployment_id", - "error_count", - "inference_count", "model_id", "nodes", - "number_of_allocations", - "queue_capacity", - "rejected_execution_count", - "reason", + "priority", "start_time", - "state", - "threads_per_allocation", - "timeout_count" + "state" + ] + }, + "ml._types:AdaptiveAllocationsSettings": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "min_number_of_allocations": { + "type": "number" + }, + "max_number_of_allocations": { + "type": "number" + } + }, + "required": [ + "enabled" ] }, "ml._types:TrainedModelDeploymentAllocationStatus": { @@ -51003,6 +51021,12 @@ "average_inference_time_ms": { "$ref": "#/components/schemas/_types:DurationValueUnitFloatMillis" }, + "average_inference_time_ms_last_minute": { + "$ref": "#/components/schemas/_types:DurationValueUnitFloatMillis" + }, + "average_inference_time_ms_excluding_cache_hits": { + "$ref": "#/components/schemas/_types:DurationValueUnitFloatMillis" + }, "error_count": { "description": "The number of errors when evaluating the trained model.", "type": "number" @@ -51011,6 +51035,12 @@ "description": "The total number of inference calls made against this node for this model.", "type": "number" }, + "inference_cache_hit_count": { + "type": "number" + }, + "inference_cache_hit_count_last_minute": { + "type": "number" + }, "last_access": { "description": "The epoch time stamp of the last inference call for the model on this node.", "type": "number" @@ -51023,6 +51053,9 @@ "description": "The number of inference requests queued to be processed.", "type": "number" }, + "peak_throughput_per_minute": { + "type": "number" + }, "rejection_execution_count": { "description": "The number of inference requests that were not processed because the queue was full.", "type": "number" @@ -51037,23 +51070,17 @@ "description": "The number of threads used by each allocation during inference.", "type": "number" }, + "throughput_last_minute": { + "type": "number" + }, "timeout_count": { "description": "The number of inference requests that timed out before being processed.", "type": "number" } }, "required": [ - "average_inference_time_ms", - "error_count", - "inference_count", - "last_access", - "number_of_allocations", - "number_of_pending_requests", - "rejection_execution_count", - "routing_state", - "start_time", - "threads_per_allocation", - "timeout_count" + "peak_throughput_per_minute", + "routing_state" ] }, "ml._types:TrainedModelAssignmentRoutingTable": { @@ -51076,10 +51103,7 @@ } }, "required": [ - "reason", - "routing_state", - "current_allocations", - "target_allocations" + "routing_state" ] }, "ml._types:RoutingState": { @@ -51092,6 +51116,13 @@ "stopping" ] }, + "ml._types:TrainingPriority": { + "type": "string", + "enum": [ + "normal", + "low" + ] + }, "ml._types:DeploymentAssignmentState": { "type": "string", "enum": [ @@ -52023,13 +52054,6 @@ } ] }, - "ml._types:TrainingPriority": { - "type": "string", - "enum": [ - "normal", - "low" - ] - }, "ml._types:TrainedModelAssignment": { "type": "object", "properties": { diff --git a/output/schema/schema-serverless.json b/output/schema/schema-serverless.json index a74bca737c..442466436e 100644 --- a/output/schema/schema-serverless.json +++ b/output/schema/schema-serverless.json @@ -94919,7 +94919,7 @@ "name": "CategorizationStatus", "namespace": "ml._types" }, - "specLocation": "ml/_types/Model.ts#L83-L86" + "specLocation": "ml/_types/Model.ts#L84-L87" }, { "kind": "enum", @@ -95041,7 +95041,7 @@ "name": "DeploymentAllocationState", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L273-L286" + "specLocation": "ml/_types/TrainedModel.ts#L297-L310" }, { "kind": "enum", @@ -95067,7 +95067,7 @@ "name": "DeploymentAssignmentState", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L288-L305" + "specLocation": "ml/_types/TrainedModel.ts#L312-L329" }, { "kind": "enum", @@ -95203,7 +95203,7 @@ "name": "MemoryStatus", "namespace": "ml._types" }, - "specLocation": "ml/_types/Model.ts#L88-L92" + "specLocation": "ml/_types/Model.ts#L89-L93" }, { "kind": "type_alias", @@ -95263,7 +95263,7 @@ "name": "RoutingState", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L347-L368" + "specLocation": "ml/_types/TrainedModel.ts#L371-L392" }, { "kind": "enum", @@ -95303,7 +95303,7 @@ "name": "SnapshotUpgradeState", "namespace": "ml._types" }, - "specLocation": "ml/_types/Model.ts#L94-L99" + "specLocation": "ml/_types/Model.ts#L95-L100" }, { "kind": "enum", @@ -95344,7 +95344,7 @@ "name": "TrainedModelType", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L257-L271" + "specLocation": "ml/_types/TrainedModel.ts#L281-L295" }, { "kind": "enum", @@ -95360,7 +95360,7 @@ "name": "TrainingPriority", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L307-L310" + "specLocation": "ml/_types/TrainedModel.ts#L331-L334" }, { "codegenNames": [ @@ -128095,9 +128095,20 @@ "namespace": "_types" } } + }, + { + "name": "_meta", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "Metadata", + "namespace": "_types" + } + } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L305-L321" + "specLocation": "ml/_types/DataframeAnalytics.ts#L306-L323" }, { "kind": "interface", @@ -128149,7 +128160,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L83-L100", + "specLocation": "ml/_types/DataframeAnalytics.ts#L84-L101", "variants": { "kind": "container" } @@ -128192,7 +128203,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L226-L235" + "specLocation": "ml/_types/DataframeAnalytics.ts#L227-L236" }, { "kind": "interface", @@ -128427,7 +128438,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L133-L212" + "specLocation": "ml/_types/DataframeAnalytics.ts#L134-L213" }, { "kind": "interface", @@ -128497,7 +128508,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L245-L257", + "specLocation": "ml/_types/DataframeAnalytics.ts#L246-L258", "variants": { "kind": "container" } @@ -128556,7 +128567,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L259-L266" + "specLocation": "ml/_types/DataframeAnalytics.ts#L260-L267" }, { "kind": "interface", @@ -128581,7 +128592,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L268-L271" + "specLocation": "ml/_types/DataframeAnalytics.ts#L269-L272" }, { "kind": "interface", @@ -128665,7 +128676,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L273-L285" + "specLocation": "ml/_types/DataframeAnalytics.ts#L274-L286" }, { "kind": "interface", @@ -128699,7 +128710,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L287-L292" + "specLocation": "ml/_types/DataframeAnalytics.ts#L288-L293" }, { "kind": "interface", @@ -128764,7 +128775,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L294-L303" + "specLocation": "ml/_types/DataframeAnalytics.ts#L295-L304" }, { "kind": "interface", @@ -128850,7 +128861,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L102-L131" + "specLocation": "ml/_types/DataframeAnalytics.ts#L103-L132" }, { "inherits": { @@ -128891,7 +128902,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L214-L224" + "specLocation": "ml/_types/DataframeAnalytics.ts#L215-L225" }, { "kind": "interface", @@ -128932,7 +128943,7 @@ } ], "shortcutProperty": "includes", - "specLocation": "ml/_types/DataframeAnalytics.ts#L237-L243" + "specLocation": "ml/_types/DataframeAnalytics.ts#L238-L244" }, { "kind": "interface", @@ -129049,7 +129060,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L76-L81" + "specLocation": "ml/_types/DataframeAnalytics.ts#L77-L82" }, { "kind": "interface", @@ -129109,7 +129120,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L38-L52" + "specLocation": "ml/_types/DataframeAnalytics.ts#L39-L53" }, { "kind": "interface", @@ -129206,7 +129217,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L323-L343" + "specLocation": "ml/_types/DataframeAnalytics.ts#L325-L345" }, { "kind": "interface", @@ -129252,7 +129263,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L372-L380", + "specLocation": "ml/_types/DataframeAnalytics.ts#L374-L382", "variants": { "kind": "container" } @@ -129334,7 +129345,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L382-L401" + "specLocation": "ml/_types/DataframeAnalytics.ts#L384-L403" }, { "kind": "interface", @@ -129512,7 +129523,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L418-L524" + "specLocation": "ml/_types/DataframeAnalytics.ts#L420-L526" }, { "kind": "interface", @@ -129564,7 +129575,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L562-L567" + "specLocation": "ml/_types/DataframeAnalytics.ts#L564-L569" }, { "kind": "interface", @@ -129601,7 +129612,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L569-L574" + "specLocation": "ml/_types/DataframeAnalytics.ts#L571-L576" }, { "kind": "interface", @@ -129656,7 +129667,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L403-L416" + "specLocation": "ml/_types/DataframeAnalytics.ts#L405-L418" }, { "kind": "interface", @@ -129741,7 +129752,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L526-L560" + "specLocation": "ml/_types/DataframeAnalytics.ts#L528-L562" }, { "kind": "interface", @@ -129787,7 +129798,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L363-L370" + "specLocation": "ml/_types/DataframeAnalytics.ts#L365-L372" }, { "kind": "interface", @@ -129854,7 +129865,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L352-L361" + "specLocation": "ml/_types/DataframeAnalytics.ts#L354-L363" }, { "kind": "interface", @@ -129888,7 +129899,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L345-L350" + "specLocation": "ml/_types/DataframeAnalytics.ts#L347-L352" }, { "kind": "interface", @@ -129936,7 +129947,7 @@ { "description": "An object that provides statistical information about timing aspect of this datafeed.", "name": "timing_stats", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -131356,7 +131367,7 @@ } } ], - "specLocation": "ml/_types/Model.ts#L59-L81" + "specLocation": "ml/_types/Model.ts#L60-L82" }, { "kind": "interface", @@ -132377,7 +132388,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L164-L199" + "specLocation": "ml/_types/TrainedModel.ts#L188-L223" }, { "description": "Inference configuration provided when storing the model config", @@ -133279,7 +133290,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L201-L204" + "specLocation": "ml/_types/TrainedModel.ts#L225-L228" }, { "kind": "interface", @@ -133356,7 +133367,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L206-L214" + "specLocation": "ml/_types/TrainedModel.ts#L230-L238" }, { "kind": "interface", @@ -133428,7 +133439,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L216-L230" + "specLocation": "ml/_types/TrainedModel.ts#L240-L254" }, { "kind": "interface", @@ -133480,7 +133491,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L232-L239" + "specLocation": "ml/_types/TrainedModel.ts#L256-L263" }, { "kind": "interface", @@ -133526,7 +133537,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L248-L255" + "specLocation": "ml/_types/TrainedModel.ts#L272-L279" }, { "kind": "interface", @@ -133563,7 +133574,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L241-L246" + "specLocation": "ml/_types/TrainedModel.ts#L265-L270" }, { "kind": "interface", @@ -133584,7 +133595,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L416-L418" + "specLocation": "ml/_types/TrainedModel.ts#L440-L442" }, { "kind": "interface", @@ -133605,7 +133616,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L420-L422" + "specLocation": "ml/_types/TrainedModel.ts#L444-L446" }, { "kind": "interface", @@ -133639,7 +133650,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L424-L433" + "specLocation": "ml/_types/TrainedModel.ts#L448-L457" }, { "kind": "interface", @@ -133739,6 +133750,17 @@ "namespace": "ml._types" }, "properties": [ + { + "name": "adaptive_allocations", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "AdaptiveAllocationsSettings", + "namespace": "ml._types" + } + } + }, { "description": "The detailed allocation status for the deployment.", "name": "allocation_status", @@ -133777,7 +133799,7 @@ { "description": "The sum of `error_count` for all nodes in the deployment.", "name": "error_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -133789,7 +133811,7 @@ { "description": "The sum of `inference_count` for all nodes in the deployment.", "name": "inference_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -133828,7 +133850,7 @@ { "description": "The number of allocations requested.", "name": "number_of_allocations", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -133837,10 +133859,21 @@ } } }, + { + "name": "priority", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "TrainingPriority", + "namespace": "ml._types" + } + } + }, { "description": "The number of inference requests that can be queued before new requests are rejected.", "name": "queue_capacity", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -133852,7 +133885,7 @@ { "description": "The sum of `rejected_execution_count` for all nodes in the deployment.\nIndividual nodes reject an inference request if the inference queue is full.\nThe queue size is controlled by the `queue_capacity` setting in the start\ntrained model deployment API.", "name": "rejected_execution_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -133864,7 +133897,7 @@ { "description": "The reason for the current deployment state. Usually only populated when\nthe model is not deployed to a node.", "name": "reason", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -133909,7 +133942,7 @@ { "description": "The number of threads used be each allocation during inference.", "name": "threads_per_allocation", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -133921,7 +133954,50 @@ { "description": "The sum of `timeout_count` for all nodes in the deployment.", "name": "timeout_count", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + } + ], + "specLocation": "ml/_types/TrainedModel.ts#L61-L104" + }, + { + "kind": "interface", + "name": { + "name": "AdaptiveAllocationsSettings", + "namespace": "ml._types" + }, + "properties": [ + { + "name": "enabled", "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" + } + } + }, + { + "name": "min_number_of_allocations", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + }, + { + "name": "max_number_of_allocations", + "required": false, "type": { "kind": "instance_of", "type": { @@ -133931,7 +134007,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L61-L101" + "specLocation": "ml/_types/TrainedModel.ts#L106-L110" }, { "kind": "interface", @@ -133977,7 +134053,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L390-L397" + "specLocation": "ml/_types/TrainedModel.ts#L414-L421" }, { "kind": "interface", @@ -133989,7 +134065,48 @@ { "description": "The average time for each inference call to complete on this node.", "name": "average_inference_time_ms", - "required": true, + "required": false, + "type": { + "generics": [ + { + "kind": "instance_of", + "type": { + "name": "UnitFloatMillis", + "namespace": "_types" + } + } + ], + "kind": "instance_of", + "type": { + "name": "DurationValue", + "namespace": "_types" + } + } + }, + { + "name": "average_inference_time_ms_last_minute", + "required": false, + "type": { + "generics": [ + { + "kind": "instance_of", + "type": { + "name": "UnitFloatMillis", + "namespace": "_types" + } + } + ], + "kind": "instance_of", + "type": { + "name": "DurationValue", + "namespace": "_types" + } + } + }, + { + "description": "The average time for each inference call to complete on this node, excluding cache", + "name": "average_inference_time_ms_excluding_cache_hits", + "required": false, "type": { "generics": [ { @@ -134010,7 +134127,7 @@ { "description": "The number of errors when evaluating the trained model.", "name": "error_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134022,11 +134139,33 @@ { "description": "The total number of inference calls made against this node for this model.", "name": "inference_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { - "name": "integer", + "name": "long", + "namespace": "_types" + } + } + }, + { + "name": "inference_cache_hit_count", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, + { + "name": "inference_cache_hit_count_last_minute", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "long", "namespace": "_types" } } @@ -134034,7 +134173,7 @@ { "description": "The epoch time stamp of the last inference call for the model on this node.", "name": "last_access", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134046,7 +134185,7 @@ { "description": "The number of allocations assigned to this node.", "name": "number_of_allocations", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134058,7 +134197,7 @@ { "description": "The number of inference requests queued to be processed.", "name": "number_of_pending_requests", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134067,10 +134206,21 @@ } } }, + { + "name": "peak_throughput_per_minute", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, { "description": "The number of inference requests that were not processed because the queue was full.", "name": "rejection_execution_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134094,7 +134244,7 @@ { "description": "The epoch timestamp when the allocation started.", "name": "start_time", - "required": true, + "required": false, "type": { "generics": [ { @@ -134115,7 +134265,18 @@ { "description": "The number of threads used by each allocation during inference.", "name": "threads_per_allocation", - "required": true, + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + }, + { + "name": "throughput_last_minute", + "required": false, "type": { "kind": "instance_of", "type": { @@ -134127,7 +134288,7 @@ { "description": "The number of inference requests that timed out before being processed.", "name": "timeout_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134137,7 +134298,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L132-L162" + "specLocation": "ml/_types/TrainedModel.ts#L141-L186" }, { "kind": "interface", @@ -134149,7 +134310,7 @@ { "description": "The reason for the current state. It is usually populated only when the\n`routing_state` is `failed`.", "name": "reason", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134173,7 +134334,7 @@ { "description": "Current number of allocations.", "name": "current_allocations", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134185,7 +134346,7 @@ { "description": "Target number of allocations.", "name": "target_allocations", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -134195,7 +134356,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L370-L388" + "specLocation": "ml/_types/TrainedModel.ts#L394-L412" }, { "kind": "interface", @@ -134276,7 +134437,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L103-L123" + "specLocation": "ml/_types/TrainedModel.ts#L112-L132" }, { "kind": "interface", @@ -134310,7 +134471,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L125-L130" + "specLocation": "ml/_types/TrainedModel.ts#L134-L139" }, { "kind": "interface", @@ -136728,7 +136889,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L399-L414" + "specLocation": "ml/_types/TrainedModel.ts#L423-L438" }, { "kind": "interface", @@ -136839,7 +137000,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L312-L345" + "specLocation": "ml/_types/TrainedModel.ts#L336-L369" }, { "kind": "interface", diff --git a/output/schema/schema.json b/output/schema/schema.json index dd7754c0fa..46c9550b12 100644 --- a/output/schema/schema.json +++ b/output/schema/schema.json @@ -149461,6 +149461,49 @@ }, "specLocation": "migration/post_feature_upgrade/PostFeatureUpgradeResponse.ts#L20-L25" }, + { + "kind": "interface", + "name": { + "name": "AdaptiveAllocationsSettings", + "namespace": "ml._types" + }, + "properties": [ + { + "name": "enabled", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "boolean", + "namespace": "_builtins" + } + } + }, + { + "name": "min_number_of_allocations", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + }, + { + "name": "max_number_of_allocations", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + } + ], + "specLocation": "ml/_types/TrainedModel.ts#L106-L110" + }, { "kind": "interface", "name": { @@ -151069,7 +151112,7 @@ "name": "CategorizationStatus", "namespace": "ml._types" }, - "specLocation": "ml/_types/Model.ts#L83-L86" + "specLocation": "ml/_types/Model.ts#L84-L87" }, { "kind": "interface", @@ -152273,10 +152316,21 @@ "name": "node", "required": false, "type": { - "kind": "instance_of", - "type": { - "name": "DiscoveryNode", - "namespace": "ml._types" + "kind": "dictionary_of", + "key": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + }, + "singleKey": false, + "value": { + "kind": "instance_of", + "type": { + "name": "DiscoveryNode", + "namespace": "ml._types" + } } } }, @@ -152295,7 +152349,7 @@ { "description": "An object that provides statistical information about timing aspect of this datafeed.", "name": "timing_stats", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -152661,7 +152715,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L133-L212" + "specLocation": "ml/_types/DataframeAnalytics.ts#L134-L213" }, { "kind": "interface", @@ -152702,7 +152756,7 @@ } ], "shortcutProperty": "includes", - "specLocation": "ml/_types/DataframeAnalytics.ts#L237-L243" + "specLocation": "ml/_types/DataframeAnalytics.ts#L238-L244" }, { "kind": "interface", @@ -152742,7 +152796,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L226-L235" + "specLocation": "ml/_types/DataframeAnalytics.ts#L227-L236" }, { "kind": "interface", @@ -152794,7 +152848,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L83-L100", + "specLocation": "ml/_types/DataframeAnalytics.ts#L84-L101", "variants": { "kind": "container" } @@ -152867,7 +152921,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L245-L257", + "specLocation": "ml/_types/DataframeAnalytics.ts#L246-L258", "variants": { "kind": "container" } @@ -152926,7 +152980,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L259-L266" + "specLocation": "ml/_types/DataframeAnalytics.ts#L260-L267" }, { "kind": "interface", @@ -152951,7 +153005,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L268-L271" + "specLocation": "ml/_types/DataframeAnalytics.ts#L269-L272" }, { "kind": "interface", @@ -153035,7 +153089,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L273-L285" + "specLocation": "ml/_types/DataframeAnalytics.ts#L274-L286" }, { "kind": "interface", @@ -153069,7 +153123,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L287-L292" + "specLocation": "ml/_types/DataframeAnalytics.ts#L288-L293" }, { "kind": "interface", @@ -153134,7 +153188,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L294-L303" + "specLocation": "ml/_types/DataframeAnalytics.ts#L295-L304" }, { "kind": "interface", @@ -153220,7 +153274,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L102-L131" + "specLocation": "ml/_types/DataframeAnalytics.ts#L103-L132" }, { "kind": "interface", @@ -153261,7 +153315,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L214-L224" + "specLocation": "ml/_types/DataframeAnalytics.ts#L215-L225" }, { "kind": "interface", @@ -153373,7 +153427,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L323-L343" + "specLocation": "ml/_types/DataframeAnalytics.ts#L325-L345" }, { "kind": "interface", @@ -153456,7 +153510,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L76-L81" + "specLocation": "ml/_types/DataframeAnalytics.ts#L77-L82" }, { "kind": "interface", @@ -153541,7 +153595,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L54-L67" + "specLocation": "ml/_types/DataframeAnalytics.ts#L55-L68" }, { "kind": "interface", @@ -153575,7 +153629,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L69-L74" + "specLocation": "ml/_types/DataframeAnalytics.ts#L70-L75" }, { "kind": "interface", @@ -153635,7 +153689,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L38-L52" + "specLocation": "ml/_types/DataframeAnalytics.ts#L39-L53" }, { "kind": "interface", @@ -153681,7 +153735,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L372-L380", + "specLocation": "ml/_types/DataframeAnalytics.ts#L374-L382", "variants": { "kind": "container" } @@ -153730,7 +153784,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L363-L370" + "specLocation": "ml/_types/DataframeAnalytics.ts#L365-L372" }, { "kind": "interface", @@ -153809,7 +153863,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L382-L401" + "specLocation": "ml/_types/DataframeAnalytics.ts#L384-L403" }, { "kind": "interface", @@ -153876,7 +153930,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L352-L361" + "specLocation": "ml/_types/DataframeAnalytics.ts#L354-L363" }, { "kind": "interface", @@ -153931,7 +153985,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L403-L416" + "specLocation": "ml/_types/DataframeAnalytics.ts#L405-L418" }, { "kind": "interface", @@ -153965,7 +154019,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L345-L350" + "specLocation": "ml/_types/DataframeAnalytics.ts#L347-L352" }, { "kind": "interface", @@ -154115,9 +154169,20 @@ "namespace": "_types" } } + }, + { + "name": "_meta", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "Metadata", + "namespace": "_types" + } + } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L305-L321" + "specLocation": "ml/_types/DataframeAnalytics.ts#L306-L323" }, { "kind": "interface", @@ -154699,7 +154764,7 @@ "name": "DeploymentAllocationState", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L273-L286" + "specLocation": "ml/_types/TrainedModel.ts#L297-L310" }, { "kind": "enum", @@ -154725,7 +154790,7 @@ "name": "DeploymentAssignmentState", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L288-L305" + "specLocation": "ml/_types/TrainedModel.ts#L312-L329" }, { "kind": "interface", @@ -155537,7 +155602,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L216-L230" + "specLocation": "ml/_types/TrainedModel.ts#L240-L254" }, { "kind": "interface", @@ -155715,7 +155780,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L418-L524" + "specLocation": "ml/_types/DataframeAnalytics.ts#L420-L526" }, { "kind": "enum", @@ -157206,10 +157271,21 @@ "name": "node", "required": false, "type": { - "kind": "instance_of", - "type": { - "name": "DiscoveryNode", - "namespace": "ml._types" + "kind": "dictionary_of", + "key": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + }, + "singleKey": false, + "value": { + "kind": "instance_of", + "type": { + "name": "DiscoveryNode", + "namespace": "ml._types" + } } } }, @@ -157433,7 +157509,7 @@ "name": "MemoryStatus", "namespace": "ml._types" }, - "specLocation": "ml/_types/Model.ts#L88-L92" + "specLocation": "ml/_types/Model.ts#L89-L93" }, { "kind": "interface", @@ -157734,7 +157810,7 @@ } } ], - "specLocation": "ml/_types/Model.ts#L59-L81" + "specLocation": "ml/_types/Model.ts#L60-L82" }, { "kind": "interface", @@ -157864,7 +157940,7 @@ } } ], - "specLocation": "ml/_types/Model.ts#L25-L46" + "specLocation": "ml/_types/Model.ts#L26-L47" }, { "kind": "interface", @@ -157913,10 +157989,21 @@ "name": "node", "required": true, "type": { - "kind": "instance_of", - "type": { - "name": "DiscoveryNode", - "namespace": "ml._types" + "kind": "dictionary_of", + "key": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + }, + "singleKey": false, + "value": { + "kind": "instance_of", + "type": { + "name": "DiscoveryNode", + "namespace": "ml._types" + } } } }, @@ -157932,7 +158019,7 @@ } } ], - "specLocation": "ml/_types/Model.ts#L48-L57" + "specLocation": "ml/_types/Model.ts#L49-L58" }, { "kind": "interface", @@ -158298,7 +158385,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L526-L560" + "specLocation": "ml/_types/DataframeAnalytics.ts#L528-L562" }, { "kind": "interface", @@ -158821,7 +158908,7 @@ "name": "RoutingState", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L347-L368" + "specLocation": "ml/_types/TrainedModel.ts#L371-L392" }, { "kind": "enum", @@ -158983,7 +159070,7 @@ "name": "SnapshotUpgradeState", "namespace": "ml._types" }, - "specLocation": "ml/_types/Model.ts#L94-L99" + "specLocation": "ml/_types/Model.ts#L95-L100" }, { "kind": "interface", @@ -159306,7 +159393,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L562-L567" + "specLocation": "ml/_types/DataframeAnalytics.ts#L564-L569" }, { "kind": "interface", @@ -159482,7 +159569,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L232-L239" + "specLocation": "ml/_types/TrainedModel.ts#L256-L263" }, { "kind": "interface", @@ -159519,7 +159606,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L241-L246" + "specLocation": "ml/_types/TrainedModel.ts#L265-L270" }, { "kind": "interface", @@ -159565,7 +159652,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L248-L255" + "specLocation": "ml/_types/TrainedModel.ts#L272-L279" }, { "kind": "interface", @@ -159644,7 +159731,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L399-L414" + "specLocation": "ml/_types/TrainedModel.ts#L423-L438" }, { "kind": "interface", @@ -159656,7 +159743,7 @@ { "description": "The reason for the current state. It is usually populated only when the\n`routing_state` is `failed`.", "name": "reason", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -159680,7 +159767,7 @@ { "description": "Current number of allocations.", "name": "current_allocations", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -159692,7 +159779,7 @@ { "description": "Target number of allocations.", "name": "target_allocations", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -159702,7 +159789,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L370-L388" + "specLocation": "ml/_types/TrainedModel.ts#L394-L412" }, { "kind": "interface", @@ -159813,7 +159900,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L312-L345" + "specLocation": "ml/_types/TrainedModel.ts#L336-L369" }, { "kind": "interface", @@ -160061,7 +160148,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L164-L199" + "specLocation": "ml/_types/TrainedModel.ts#L188-L223" }, { "kind": "interface", @@ -160086,7 +160173,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L201-L204" + "specLocation": "ml/_types/TrainedModel.ts#L225-L228" }, { "kind": "interface", @@ -160163,7 +160250,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L206-L214" + "specLocation": "ml/_types/TrainedModel.ts#L230-L238" }, { "kind": "interface", @@ -160209,7 +160296,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L390-L397" + "specLocation": "ml/_types/TrainedModel.ts#L414-L421" }, { "kind": "interface", @@ -160221,7 +160308,48 @@ { "description": "The average time for each inference call to complete on this node.", "name": "average_inference_time_ms", - "required": true, + "required": false, + "type": { + "kind": "instance_of", + "generics": [ + { + "kind": "instance_of", + "type": { + "name": "UnitFloatMillis", + "namespace": "_types" + } + } + ], + "type": { + "name": "DurationValue", + "namespace": "_types" + } + } + }, + { + "name": "average_inference_time_ms_last_minute", + "required": false, + "type": { + "kind": "instance_of", + "generics": [ + { + "kind": "instance_of", + "type": { + "name": "UnitFloatMillis", + "namespace": "_types" + } + } + ], + "type": { + "name": "DurationValue", + "namespace": "_types" + } + } + }, + { + "description": "The average time for each inference call to complete on this node, excluding cache", + "name": "average_inference_time_ms_excluding_cache_hits", + "required": false, "type": { "kind": "instance_of", "generics": [ @@ -160242,7 +160370,7 @@ { "description": "The number of errors when evaluating the trained model.", "name": "error_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160254,11 +160382,33 @@ { "description": "The total number of inference calls made against this node for this model.", "name": "inference_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { - "name": "integer", + "name": "long", + "namespace": "_types" + } + } + }, + { + "name": "inference_cache_hit_count", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, + { + "name": "inference_cache_hit_count_last_minute", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "long", "namespace": "_types" } } @@ -160266,7 +160416,7 @@ { "description": "The epoch time stamp of the last inference call for the model on this node.", "name": "last_access", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160281,19 +160431,30 @@ }, "description": "Information pertaining to the node.", "name": "node", - "required": true, + "required": false, "type": { - "kind": "instance_of", - "type": { - "name": "DiscoveryNode", - "namespace": "ml._types" + "kind": "dictionary_of", + "key": { + "kind": "instance_of", + "type": { + "name": "Id", + "namespace": "_types" + } + }, + "singleKey": false, + "value": { + "kind": "instance_of", + "type": { + "name": "DiscoveryNode", + "namespace": "ml._types" + } } } }, { "description": "The number of allocations assigned to this node.", "name": "number_of_allocations", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160305,7 +160466,7 @@ { "description": "The number of inference requests queued to be processed.", "name": "number_of_pending_requests", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160314,10 +160475,21 @@ } } }, + { + "name": "peak_throughput_per_minute", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "long", + "namespace": "_types" + } + } + }, { "description": "The number of inference requests that were not processed because the queue was full.", "name": "rejection_execution_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160341,7 +160513,7 @@ { "description": "The epoch timestamp when the allocation started.", "name": "start_time", - "required": true, + "required": false, "type": { "kind": "instance_of", "generics": [ @@ -160362,7 +160534,18 @@ { "description": "The number of threads used by each allocation during inference.", "name": "threads_per_allocation", - "required": true, + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "integer", + "namespace": "_types" + } + } + }, + { + "name": "throughput_last_minute", + "required": false, "type": { "kind": "instance_of", "type": { @@ -160374,7 +160557,7 @@ { "description": "The number of inference requests that timed out before being processed.", "name": "timeout_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160384,7 +160567,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L132-L162" + "specLocation": "ml/_types/TrainedModel.ts#L141-L186" }, { "kind": "interface", @@ -160393,6 +160576,17 @@ "namespace": "ml._types" }, "properties": [ + { + "name": "adaptive_allocations", + "required": false, + "type": { + "kind": "instance_of", + "type": { + "name": "AdaptiveAllocationsSettings", + "namespace": "ml._types" + } + } + }, { "description": "The detailed allocation status for the deployment.", "name": "allocation_status", @@ -160431,7 +160625,7 @@ { "description": "The sum of `error_count` for all nodes in the deployment.", "name": "error_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160443,7 +160637,7 @@ { "description": "The sum of `inference_count` for all nodes in the deployment.", "name": "inference_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160482,7 +160676,7 @@ { "description": "The number of allocations requested.", "name": "number_of_allocations", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160491,10 +160685,21 @@ } } }, + { + "name": "priority", + "required": true, + "type": { + "kind": "instance_of", + "type": { + "name": "TrainingPriority", + "namespace": "ml._types" + } + } + }, { "description": "The number of inference requests that can be queued before new requests are rejected.", "name": "queue_capacity", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160506,7 +160711,7 @@ { "description": "The sum of `rejected_execution_count` for all nodes in the deployment.\nIndividual nodes reject an inference request if the inference queue is full.\nThe queue size is controlled by the `queue_capacity` setting in the start\ntrained model deployment API.", "name": "rejected_execution_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160518,7 +160723,7 @@ { "description": "The reason for the current deployment state. Usually only populated when\nthe model is not deployed to a node.", "name": "reason", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160563,7 +160768,7 @@ { "description": "The number of threads used be each allocation during inference.", "name": "threads_per_allocation", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160575,7 +160780,7 @@ { "description": "The sum of `timeout_count` for all nodes in the deployment.", "name": "timeout_count", - "required": true, + "required": false, "type": { "kind": "instance_of", "type": { @@ -160585,7 +160790,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L61-L101" + "specLocation": "ml/_types/TrainedModel.ts#L61-L104" }, { "kind": "interface", @@ -160809,7 +161014,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L103-L123" + "specLocation": "ml/_types/TrainedModel.ts#L112-L132" }, { "kind": "interface", @@ -160830,7 +161035,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L416-L418" + "specLocation": "ml/_types/TrainedModel.ts#L440-L442" }, { "kind": "interface", @@ -160851,7 +161056,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L420-L422" + "specLocation": "ml/_types/TrainedModel.ts#L444-L446" }, { "kind": "interface", @@ -160885,7 +161090,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L424-L433" + "specLocation": "ml/_types/TrainedModel.ts#L448-L457" }, { "kind": "interface", @@ -160919,7 +161124,7 @@ } } ], - "specLocation": "ml/_types/TrainedModel.ts#L125-L130" + "specLocation": "ml/_types/TrainedModel.ts#L134-L139" }, { "kind": "interface", @@ -161032,7 +161237,7 @@ "name": "TrainedModelType", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L257-L271" + "specLocation": "ml/_types/TrainedModel.ts#L281-L295" }, { "kind": "enum", @@ -161048,7 +161253,7 @@ "name": "TrainingPriority", "namespace": "ml._types" }, - "specLocation": "ml/_types/TrainedModel.ts#L307-L310" + "specLocation": "ml/_types/TrainedModel.ts#L331-L334" }, { "kind": "interface", @@ -161134,7 +161339,7 @@ } } ], - "specLocation": "ml/_types/DataframeAnalytics.ts#L569-L574" + "specLocation": "ml/_types/DataframeAnalytics.ts#L571-L576" }, { "kind": "interface", diff --git a/output/typescript/types.ts b/output/typescript/types.ts index 54043a22b0..5d82410aea 100644 --- a/output/typescript/types.ts +++ b/output/typescript/types.ts @@ -13607,6 +13607,12 @@ export interface MigrationPostFeatureUpgradeResponse { features: MigrationPostFeatureUpgradeMigrationFeature[] } +export interface MlAdaptiveAllocationsSettings { + enabled: boolean + min_number_of_allocations?: integer + max_number_of_allocations?: integer +} + export interface MlAnalysisConfig { bucket_span?: Duration categorization_analyzer?: MlCategorizationAnalyzer @@ -13878,9 +13884,9 @@ export type MlDatafeedState = 'started' | 'stopped' | 'starting' | 'stopping' export interface MlDatafeedStats { assignment_explanation?: string datafeed_id: Id - node?: MlDiscoveryNode + node?: Record state: MlDatafeedState - timing_stats: MlDatafeedTimingStats + timing_stats?: MlDatafeedTimingStats running_state?: MlDatafeedRunningState } @@ -14078,6 +14084,7 @@ export interface MlDataframeAnalyticsSummary { model_memory_limit?: string source: MlDataframeAnalyticsSource version?: VersionString + _meta?: Metadata } export interface MlDataframeEvaluationClassification { @@ -14389,7 +14396,7 @@ export interface MlJobStats { forecasts_stats: MlJobForecastStatistics job_id: string model_size_stats: MlModelSizeStats - node?: MlDiscoveryNode + node?: Record open_time?: DateTime state: MlJobState timing_stats: MlJobTimingStats @@ -14456,7 +14463,7 @@ export interface MlModelSnapshotUpgrade { job_id: Id snapshot_id: Id state: MlSnapshotUpgradeState - node: MlDiscoveryNode + node: Record assignment_explanation: string } @@ -14659,10 +14666,10 @@ export interface MlTrainedModelAssignment { } export interface MlTrainedModelAssignmentRoutingTable { - reason: string + reason?: string routing_state: MlRoutingState - current_allocations: integer - target_allocations: integer + current_allocations?: integer + target_allocations?: integer } export interface MlTrainedModelAssignmentTaskParameters { @@ -14716,36 +14723,44 @@ export interface MlTrainedModelDeploymentAllocationStatus { } export interface MlTrainedModelDeploymentNodesStats { - average_inference_time_ms: DurationValue - error_count: integer - inference_count: integer - last_access: long - node: MlDiscoveryNode - number_of_allocations: integer - number_of_pending_requests: integer - rejection_execution_count: integer + average_inference_time_ms?: DurationValue + average_inference_time_ms_last_minute?: DurationValue + average_inference_time_ms_excluding_cache_hits?: DurationValue + error_count?: integer + inference_count?: long + inference_cache_hit_count?: long + inference_cache_hit_count_last_minute?: long + last_access?: long + node?: Record + number_of_allocations?: integer + number_of_pending_requests?: integer + peak_throughput_per_minute: long + rejection_execution_count?: integer routing_state: MlTrainedModelAssignmentRoutingTable - start_time: EpochTime - threads_per_allocation: integer - timeout_count: integer + start_time?: EpochTime + threads_per_allocation?: integer + throughput_last_minute?: integer + timeout_count?: integer } export interface MlTrainedModelDeploymentStats { + adaptive_allocations?: MlAdaptiveAllocationsSettings allocation_status: MlTrainedModelDeploymentAllocationStatus cache_size?: ByteSize deployment_id: Id - error_count: integer - inference_count: integer + error_count?: integer + inference_count?: integer model_id: Id nodes: MlTrainedModelDeploymentNodesStats[] - number_of_allocations: integer - queue_capacity: integer - rejected_execution_count: integer - reason: string + number_of_allocations?: integer + priority: MlTrainingPriority + queue_capacity?: integer + rejected_execution_count?: integer + reason?: string start_time: EpochTime state: MlDeploymentAssignmentState - threads_per_allocation: integer - timeout_count: integer + threads_per_allocation?: integer + timeout_count?: integer } export interface MlTrainedModelEntities { diff --git a/specification/ml/_types/Datafeed.ts b/specification/ml/_types/Datafeed.ts index c9df56e314..7b6c2d6981 100644 --- a/specification/ml/_types/Datafeed.ts +++ b/specification/ml/_types/Datafeed.ts @@ -154,7 +154,7 @@ export class DatafeedStats { * For started datafeeds only, this information pertains to the node upon which the datafeed is started. * @availability stack */ - node?: DiscoveryNode + node?: Dictionary /** * The status of the datafeed, which can be one of the following values: `starting`, `started`, `stopping`, `stopped`. */ @@ -162,7 +162,7 @@ export class DatafeedStats { /** * An object that provides statistical information about timing aspect of this datafeed. */ - timing_stats: DatafeedTimingStats + timing_stats?: DatafeedTimingStats /** * An object containing the running state for this datafeed. * It is only provided if the datafeed is started. diff --git a/specification/ml/_types/DataframeAnalytics.ts b/specification/ml/_types/DataframeAnalytics.ts index fbafef44ae..95d4b3e9db 100644 --- a/specification/ml/_types/DataframeAnalytics.ts +++ b/specification/ml/_types/DataframeAnalytics.ts @@ -25,6 +25,7 @@ import { Id, IndexName, Indices, + Metadata, Name, VersionString } from '@_types/common' @@ -318,6 +319,7 @@ export class DataframeAnalyticsSummary { model_memory_limit?: string source: DataframeAnalyticsSource version?: VersionString + _meta?: Metadata } export class DataframeAnalytics { diff --git a/specification/ml/_types/Job.ts b/specification/ml/_types/Job.ts index b15656ac05..364f70be8e 100644 --- a/specification/ml/_types/Job.ts +++ b/specification/ml/_types/Job.ts @@ -310,7 +310,7 @@ export class JobStats { * This information is available only for open jobs. * @availability stack */ - node?: DiscoveryNode + node?: Dictionary /** * For open jobs only, the elapsed time for which the job has been open. */ diff --git a/specification/ml/_types/Model.ts b/specification/ml/_types/Model.ts index 806d14faf2..ea47bedafc 100644 --- a/specification/ml/_types/Model.ts +++ b/specification/ml/_types/Model.ts @@ -18,6 +18,7 @@ */ import { DiscoveryNode } from '@ml/_types/DiscoveryNode' +import { Dictionary } from '@spec_utils/Dictionary' import { ByteSize, Id, VersionString } from '@_types/common' import { integer, long } from '@_types/Numeric' import { DateTime } from '@_types/Time' @@ -52,7 +53,7 @@ export class ModelSnapshotUpgrade { /** * @availability stack */ - node: DiscoveryNode + node: Dictionary assignment_explanation: string } diff --git a/specification/ml/_types/TrainedModel.ts b/specification/ml/_types/TrainedModel.ts index 439444e403..fe151089ef 100644 --- a/specification/ml/_types/TrainedModel.ts +++ b/specification/ml/_types/TrainedModel.ts @@ -59,15 +59,16 @@ export class TrainedModelStats { } export class TrainedModelDeploymentStats { + adaptive_allocations?: AdaptiveAllocationsSettings /** The detailed allocation status for the deployment. */ allocation_status: TrainedModelDeploymentAllocationStatus cache_size?: ByteSize /** The unique identifier for the trained model deployment. */ deployment_id: Id /** The sum of `error_count` for all nodes in the deployment. */ - error_count: integer + error_count?: integer /** The sum of `inference_count` for all nodes in the deployment. */ - inference_count: integer + inference_count?: integer /** The unique identifier for the trained model. */ model_id: Id /** @@ -76,28 +77,36 @@ export class TrainedModelDeploymentStats { */ nodes: TrainedModelDeploymentNodesStats[] /** The number of allocations requested. */ - number_of_allocations: integer + number_of_allocations?: integer + + priority: TrainingPriority /** The number of inference requests that can be queued before new requests are rejected. */ - queue_capacity: integer + queue_capacity?: integer /** * The sum of `rejected_execution_count` for all nodes in the deployment. * Individual nodes reject an inference request if the inference queue is full. * The queue size is controlled by the `queue_capacity` setting in the start * trained model deployment API. */ - rejected_execution_count: integer + rejected_execution_count?: integer /** The reason for the current deployment state. Usually only populated when * the model is not deployed to a node. */ - reason: string + reason?: string /** The epoch timestamp when the deployment started. */ start_time: EpochTime /** The overall state of the deployment. */ state: DeploymentAssignmentState /** The number of threads used be each allocation during inference. */ - threads_per_allocation: integer + threads_per_allocation?: integer /** The sum of `timeout_count` for all nodes in the deployment. */ - timeout_count: integer + timeout_count?: integer +} + +export class AdaptiveAllocationsSettings { + enabled: boolean + min_number_of_allocations?: integer + max_number_of_allocations?: integer } export class TrainedModelInferenceStats { @@ -131,34 +140,49 @@ export class TrainedModelSizeStats { export class TrainedModelDeploymentNodesStats { /** The average time for each inference call to complete on this node. */ - average_inference_time_ms: DurationValue + average_inference_time_ms?: DurationValue + + average_inference_time_ms_last_minute?: DurationValue + + /** The average time for each inference call to complete on this node, excluding cache */ + average_inference_time_ms_excluding_cache_hits?: DurationValue + /** The number of errors when evaluating the trained model. */ - error_count: integer + error_count?: integer /** The total number of inference calls made against this node for this model. */ - inference_count: integer + inference_count?: long + + inference_cache_hit_count?: long + + inference_cache_hit_count_last_minute?: long + /** The epoch time stamp of the last inference call for the model on this node. */ - last_access: long + last_access?: long /** * Information pertaining to the node. * @availability stack */ - node: DiscoveryNode + node?: Dictionary /** * The number of allocations assigned to this node. */ - number_of_allocations: integer + number_of_allocations?: integer /** The number of inference requests queued to be processed. */ - number_of_pending_requests: integer + number_of_pending_requests?: integer + + peak_throughput_per_minute: long /** The number of inference requests that were not processed because the queue was full. */ - rejection_execution_count: integer + rejection_execution_count?: integer /** The current routing state and reason for the current routing state for this allocation. */ routing_state: TrainedModelAssignmentRoutingTable /** The epoch timestamp when the allocation started. */ - start_time: EpochTime + start_time?: EpochTime /** The number of threads used by each allocation during inference. */ - threads_per_allocation: integer + threads_per_allocation?: integer + + throughput_last_minute?: integer /** The number of inference requests that timed out before being processed. */ - timeout_count: integer + timeout_count?: integer } export class TrainedModelConfig { @@ -372,7 +396,7 @@ export class TrainedModelAssignmentRoutingTable { * The reason for the current state. It is usually populated only when the * `routing_state` is `failed`. */ - reason: string + reason?: string /** * The current routing state. */ @@ -380,11 +404,11 @@ export class TrainedModelAssignmentRoutingTable { /** * Current number of allocations. */ - current_allocations: integer + current_allocations?: integer /** * Target number of allocations. */ - target_allocations: integer + target_allocations?: integer } export class TrainedModelDeploymentAllocationStatus {