Request Syntax Request Parameters Response Syntax Response Elements Errors See Also

DescribeInferenceRecommendationsJob

Provides the results of the Inference Recommender job. One or more recommendation jobs are returned.

Request Syntax


{
   "JobName": "string"
}

Request Parameters

For information about the parameters that are common to all actions, see Common Parameters.

The request accepts the following data in JSON format.

JobName

The name of the job. The name must be unique within an AWS Region in the AWS account.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 64.

Pattern: ^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,63}

Required: Yes

Response Syntax


{
   "CompletionTime": number,
   "CreationTime": number,
   "EndpointPerformances": [ 
      { 
         "EndpointInfo": { 
            "EndpointName": "string"
         },
         "Metrics": { 
            "MaxInvocations": number,
            "ModelLatency": number
         }
      }
   ],
   "FailureReason": "string",
   "InferenceRecommendations": [ 
      { 
         "EndpointConfiguration": { 
            "EndpointName": "string",
            "InitialInstanceCount": number,
            "InstanceType": "string",
            "ServerlessConfig": { 
               "MaxConcurrency": number,
               "MemorySizeInMB": number,
               "ProvisionedConcurrency": number
            },
            "VariantName": "string"
         },
         "InvocationEndTime": number,
         "InvocationStartTime": number,
         "Metrics": { 
            "CostPerHour": number,
            "CostPerInference": number,
            "CpuUtilization": number,
            "MaxInvocations": number,
            "MemoryUtilization": number,
            "ModelLatency": number,
            "ModelSetupTime": number
         },
         "ModelConfiguration": { 
            "CompilationJobName": "string",
            "EnvironmentParameters": [ 
               { 
                  "Key": "string",
                  "Value": "string",
                  "ValueType": "string"
               }
            ],
            "InferenceSpecificationName": "string"
         },
         "RecommendationId": "string"
      }
   ],
   "InputConfig": { 
      "ContainerConfig": { 
         "DataInputConfig": "string",
         "Domain": "string",
         "Framework": "string",
         "FrameworkVersion": "string",
         "NearestModelName": "string",
         "PayloadConfig": { 
            "SamplePayloadUrl": "string",
            "SupportedContentTypes": [ "string" ]
         },
         "SupportedEndpointType": "string",
         "SupportedInstanceTypes": [ "string" ],
         "SupportedResponseMIMETypes": [ "string" ],
         "Task": "string"
      },
      "EndpointConfigurations": [ 
         { 
            "EnvironmentParameterRanges": { 
               "CategoricalParameterRanges": [ 
                  { 
                     "Name": "string",
                     "Value": [ "string" ]
                  }
               ]
            },
            "InferenceSpecificationName": "string",
            "InstanceType": "string",
            "ServerlessConfig": { 
               "MaxConcurrency": number,
               "MemorySizeInMB": number,
               "ProvisionedConcurrency": number
            }
         }
      ],
      "Endpoints": [ 
         { 
            "EndpointName": "string"
         }
      ],
      "JobDurationInSeconds": number,
      "ModelName": "string",
      "ModelPackageVersionArn": "string",
      "ResourceLimit": { 
         "MaxNumberOfTests": number,
         "MaxParallelOfTests": number
      },
      "TrafficPattern": { 
         "Phases": [ 
            { 
               "DurationInSeconds": number,
               "InitialNumberOfUsers": number,
               "SpawnRate": number
            }
         ],
         "Stairs": { 
            "DurationInSeconds": number,
            "NumberOfSteps": number,
            "UsersPerStep": number
         },
         "TrafficType": "string"
      },
      "VolumeKmsKeyId": "string",
      "VpcConfig": { 
         "SecurityGroupIds": [ "string" ],
         "Subnets": [ "string" ]
      }
   },
   "JobArn": "string",
   "JobDescription": "string",
   "JobName": "string",
   "JobType": "string",
   "LastModifiedTime": number,
   "RoleArn": "string",
   "Status": "string",
   "StoppingConditions": { 
      "FlatInvocations": "string",
      "MaxInvocations": number,
      "ModelLatencyThresholds": [ 
         { 
            "Percentile": "string",
            "ValueInMilliseconds": number
         }
      ]
   }
}

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

CompletionTime

A timestamp that shows when the job completed.

Type: Timestamp

CreationTime

A timestamp that shows when the job was created.

Type: Timestamp

EndpointPerformances

The performance results from running an Inference Recommender job on an existing endpoint.

Type: Array of EndpointPerformance objects

Array Members: Maximum number of 1 item.

FailureReason

If the job fails, provides information why the job failed.

Type: String

Length Constraints: Maximum length of 1024.

InferenceRecommendations

The recommendations made by Inference Recommender.

Type: Array of InferenceRecommendation objects

Array Members: Minimum number of 1 item. Maximum number of 10 items.

InputConfig

Returns information about the versioned model package Amazon Resource Name (ARN), the traffic pattern, and endpoint configurations you provided when you initiated the job.

Type: RecommendationJobInputConfig object

JobArn