DataRobot Observability Service Health API

openapi: 3.2.0
info:
  contact:
    email: support@datarobot.com
    name: DataRobot Support
    url: https://support.datarobot.com
  description: DataRobot's Public facing API
  license:
    name: DataRobot Tool and Utility Agreement
    url: https://www.datarobot.com/wp-content/uploads/2021/07/DataRobot-Tool-and-Utility-Agreement.pdf
  title: Public Observability Service Health API
  version: 2.49.0
  x-datarobot-release-version: Latest
servers:
- url: https://app.datarobot.com/
security:
- BearerAuth: []
tags:
- description: Use the endpoints described below to manage service health. Service health tracks metrics about a deployment's ability to respond to prediction requests quickly and reliably. This helps identify bottlenecks and assess capacity, which is critical to proper provisioning.
  name: observability_service_health
paths:
  /api/v2/deployments/{deploymentId}/batchServiceStats/:
    get:
      description: Retrieve all deployment service health metrics over a set of batches.
      operationId: deploymentsBatchServiceStats_list
      parameters:
      - description: Quantile for executionTime metric.
        in: query
        name: executionTimeQuantile
        required: false
        schema:
          default: 0.5
          maximum: 1
          minimum: 0
          type: number
      - description: Quantile for responseTime metric.
        in: query
        name: responseTimeQuantile
        required: false
        schema:
          default: 0.5
          maximum: 1
          minimum: 0
          type: number
      - description: Threshold for slowRequests metric.
        in: query
        name: slowRequestsThreshold
        required: false
        schema:
          default: 1000
          minimum: 0
          type: integer
      - description: The name of a segment attribute used for segment analysis.
        in: query
        name: segmentAttribute
        required: false
        schema:
          enum:
          - DataRobot-Consumer
          - DataRobot-Remote-IP
          - DataRobot-Host-IP
          type: string
        x-versionadded: v2.20
      - description: The value of the `segmentAttribute` to segment on.
        in: query
        name: segmentValue
        required: false
        schema:
          default: ''
          type:
          - string
          - 'null'
        x-versionadded: v2.20
      - description: The id of the batch for which metrics are being retrieved.
        in: query
        name: batchId
        required: false
        schema:
          oneOf:
          - type: string
          - items:
              type: string
            maxItems: 25
            type: array
      - description: The id of the model for which metrics are being retrieved.
        in: query
        name: modelId
        required: false
        schema:
          type: string
      - description: Unique identifier of the deployment.
        in: path
        name: deploymentId
        required: true
        schema:
          type: string
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceStatsForBatchRetrieveResponse'
          description: Service health metric data retrieved.
      summary: Retrieve service health metrics by deployment ID
      tags:
      - observability_service_health
      x-versionadded: v2.33
  /api/v2/deployments/{deploymentId}/serviceStats/:
    get:
      description: Retrieve all deployment service health metrics over a single period of time.
      operationId: deploymentsServiceStats_list
      parameters:
      - description: 'Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: ``2019-08-01T00:00:00Z``.'
        in: query
        name: start
        required: false
        schema:
          format: date-time
          type:
          - string
          - 'null'
      - description: 'End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: ``2019-08-01T00:00:00Z``.'
        in: query
        name: end
        required: false
        schema:
          format: date-time
          type:
          - string
          - 'null'
      - description: Quantile for executionTime metric.
        in: query
        name: executionTimeQuantile
        required: false
        schema:
          default: 0.5
          maximum: 1
          minimum: 0
          type: number
      - description: Quantile for responseTime metric.
        in: query
        name: responseTimeQuantile
        required: false
        schema:
          default: 0.5
          maximum: 1
          minimum: 0
          type: number
      - description: Threshold for slowRequests metric.
        in: query
        name: slowRequestsThreshold
        required: false
        schema:
          default: 1000
          minimum: 0
          type: integer
      - description: The name of a segment attribute used for segment analysis.
        in: query
        name: segmentAttribute
        required: false
        schema:
          enum:
          - DataRobot-Consumer
          - DataRobot-Remote-IP
          - DataRobot-Host-IP
          type: string
        x-versionadded: v2.20
      - description: The value of the `segmentAttribute` to segment on.
        in: query
        name: segmentValue
        required: false
        schema:
          default: ''
          type:
          - string
          - 'null'
        x-versionadded: v2.20
      - description: The id of the model for which metrics are being retrieved.
        in: query
        name: modelId
        required: false
        schema:
          type: string
      - description: Unique identifier of the deployment.
        in: path
        name: deploymentId
        required: true
        schema:
          type: string
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceStatsForTimeRangeResponse'
          description: Service health metric data retrieved.
      summary: Retrieve service stats by ID
      tags:
      - observability_service_health
      x-versionadded: v2.18
  /api/v2/deployments/{deploymentId}/serviceStatsOverBatch/:
    get:
      description: Retrieve values for one single deployment service health metric over batch.
      operationId: deploymentsServiceStatsOverBatch_list
      parameters:
      - description: The name of a segment attribute used for segment analysis.
        in: query
        name: segmentAttribute
        required: false
        schema:
          enum:
          - DataRobot-Consumer
          - DataRobot-Remote-IP
          - DataRobot-Host-IP
          type: string
        x-versionadded: v2.20
      - description: The value of the `segmentAttribute` to segment on.
        in: query
        name: segmentValue
        required: false
        schema:
          default: ''
          type:
          - string
          - 'null'
        x-versionadded: v2.20
      - description: The id of the batch for which metrics are being retrieved.
        in: query
        name: batchId
        required: false
        schema:
          oneOf:
          - type: string
          - items:
              type: string
            maxItems: 25
            type: array
      - description: The id of the model for which metrics are being retrieved.
        in: query
        name: modelId
        required: false
        schema:
          type: string
      - description: A service health metric.
        in: query
        name: metric
        required: false
        schema:
          default: totalPredictions
          enum:
          - totalPredictions
          - totalRequests
          - slowRequests
          - executionTime
          - responseTime
          - userErrorRate
          - serverErrorRate
          - numConsumers
          - cacheHitRatio
          type: string
      - description: Quantile for executionTime and responseTime metrics
        in: query
        name: quantile
        required: false
        schema:
          default: 0.5
          maximum: 1
          minimum: 0
          type: number
      - description: Threshold for slowQueries metric.
        in: query
        name: threshold
        required: false
        schema:
          default: 1000
          minimum: 0
          type: integer
      - description: Unique identifier of the deployment.
        in: path
        name: deploymentId
        required: true
        schema:
          type: string
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceStatsOverBatchResponse'
          description: Service health metric data retrieved.
      summary: Retrieve service health metric over batch by deployment ID
      tags:
      - observability_service_health
      x-versionadded: v2.33
  /api/v2/deployments/{deploymentId}/serviceStatsOverTime/:
    get:
      description: Retrieve values for one single deployment service health metric over time.
      operationId: deploymentsServiceStatsOverTime_list
      parameters:
      - description: 'Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: ``2019-08-01T00:00:00Z``.'
        in: query
        name: start
        required: false
        schema:
          format: date-time
          type:
          - string
          - 'null'
      - description: 'End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: ``2019-08-01T00:00:00Z``.'
        in: query
        name: end
        required: false
        schema:
          format: date-time
          type:
          - string
          - 'null'
      - description: The time duration of a bucket. Needs to be multiple of one hour. Can not be longer than the total length of the period. If not set, a default value will be calculated based on the start and end time.
        in: query
        name: bucketSize
        required: false
        schema:
          format: duration
          type: string
      - description: The name of a segment attribute used for segment analysis.
        in: query
        name: segmentAttribute
        required: false
        schema:
          enum:
          - DataRobot-Consumer
          - DataRobot-Remote-IP
          - DataRobot-Host-IP
          type: string
        x-versionadded: v2.20
      - description: The value of the `segmentAttribute` to segment on.
        in: query
        name: segmentValue
        required: false
        schema:
          default: ''
          type:
          - string
          - 'null'
        x-versionadded: v2.20
      - description: The ID of the models for which metrics are being retrieved.
        in: query
        name: modelId
        required: false
        schema:
          oneOf:
          - type: string
          - items:
              type: string
            maxItems: 5
            type: array
      - description: Name of the metric. See below for a list of supported metrics.
        in: query
        name: metric
        required: false
        schema:
          default: totalPredictions
          enum:
          - totalPredictions
          - totalRequests
          - slowRequests
          - executionTime
          - responseTime
          - userErrorRate
          - serverErrorRate
          - numConsumers
          - cacheHitRatio
          - medianLoad
          - peakLoad
          type: string
      - description: A quantile for resulting data, used if `metric` is `executionTime` or `responseTime`, defaults to 0.5.
        in: query
        name: quantile
        required: false
        schema:
          maximum: 1
          minimum: 0
          type: number
      - description: A threshold for filtering results, used if `metric` is `slowQueries`, defaults to 1000.
        in: query
        name: threshold
        required: false
        schema:
          minimum: 0
          type: integer
      - description: Unique identifier of the deployment.
        in: path
        name: deploymentId
        required: true
        schema:
          type: string
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceStatsOverTimeResponse'
          description: Service health metric data retrieved.
      summary: Retrieve service health metric over time by deployment ID
      tags:
      - observability_service_health
      x-versionadded: v2.18
components:
  schemas:
    ServiceStatsForBatchRetrieveResponse:
      properties:
        batches:
          description: Info of the batches the metric is aggregated on.
          items:
            $ref: '#/components/schemas/Batch'
          type: array
          x-versionadded: v2.33
        metrics:
          $ref: '#/components/schemas/ServiceStatsMetricsForBatch'
          x-versionadded: v2.33
        segmentAttribute:
          description: The name of the segment on which segment analysis is being performed.
          type:
          - string
          - 'null'
          x-versionadded: v2.20
        segmentValue:
          default: ''
          description: The value of the `segmentAttribute` to segment on.
          type:
          - string
          - 'null'
          x-versionadded: v2.20
      required:
      - batches
      - metrics
      type: object
    ServiceStatsForTimeRangeResponse:
      properties:
        metrics:
          $ref: '#/components/schemas/ServiceStatsMetricsForTimeRange'
        modelId:
          description: The id of the model for which metrics are being retrieved.
          type: string
        period:
          $ref: '#/components/schemas/TimeRange'
        segmentAttribute:
          description: The name of the segment on which segment analysis is being performed.
          type:
          - string
          - 'null'
          x-versionadded: v2.20
        segmentValue:
          default: ''
          description: The value of the `segmentAttribute` to segment on.
          type:
          - string
          - 'null'
          x-versionadded: v2.20
      required:
      - metrics
      - period
      type: object
    ServiceStatsOverBatchBucket:
      description: Service health stats of the deployment over a batch.
      properties:
        batch:
          $ref: '#/components/schemas/Batch'
          x-versionadded: v2.33
        value:
          description: Value of the metric in the bucket.
          type:
          - number
          - 'null'
          x-versionadded: v2.33
      required:
      - batch
      - value
      type: object
    ServiceStatsOverTimeResponse:
      properties:
        buckets:
          description: An array of bucket, representing service health stats of the deployment over time.
          items:
            $ref: '#/components/schemas/ServiceStatsOverTimeBucket'
          type: array
        metric:
          description: Name of the metric requested.
          type: string
        modelId:
          description: The id of the model for which metrics are being retrieved. Deprecated, use modelId in each bucket instead.
          type: string
          x-versiondeprecated: v2.37
        segmentAttribute:
          description: The name of the segment on which segment analysis is being performed.
          type:
          - string
          - 'null'
          x-versionadded: v2.20
        segmentValue:
          default: ''
          description: The value of the `segmentAttribute` to segment on.
          type:
          - string
          - 'null'
          x-versionadded: v2.20
        summary:
          $ref: '#/components/schemas/ServiceStatsOverTimeBucket'
          x-versiondeprecated: v2.37
      required:
      - buckets
      - metric
      type: object
    ServiceStatsOverBatchResponse:
      properties:
        buckets:
          description: An array of buckets, representing service health stats of the deployment over selected batches.
          items:
            $ref: '#/components/schemas/ServiceStatsOverBatchBucket'
          type: array
          x-versionadded: v2.33
        metric:
          description: Name of the metric requested.
          type: string
          x-versionadded: v2.33
        segmentAttribute:
          description: The name of the segment on which segment analysis is being performed.
          type:
          - string
          - 'null'
          x-versionadded: v2.20
        segmentValue:
          default: ''
          description: The value of the `segmentAttribute` to segment on.
          type:
          - string
          - 'null'
          x-versionadded: v2.20
      required:
      - buckets
      - metric
      type: object
    ServiceStatsMetricsForBatch:
      description: Service health metrics of the deployment
      properties:
        cacheHitRatio:
          description: Number of cache hits.
          type:
          - number
          - 'null'
          x-versionadded: v2.33
        executionTime:
          description: Request execution time at executionTimeQuantile (in milliseconds).
          type:
          - number
          - 'null'
          x-versionadded: v2.33
        numConsumers:
          description: Number of unique users performing requests.
          type:
          - integer
          - 'null'
          x-versionadded: v2.33
        responseTime:
          description: Request response time at responseTimeQuantile (in milliseconds).
          type:
          - number
          - 'null'
          x-versionadded: v2.33
        serverErrorRate:
          description: Ratio of server errors to the total number of requests.
          type:
          - number
          - 'null'
          x-versionadded: v2.33
        slowRequests:
          description: Number of requests with response time greater than slowRequestsThreshold
          type:
          - integer
          - 'null'
          x-versionadded: v2.33
        totalPredictions:
          description: Total number of prediction rows.
          type:
          - integer
          - 'null'
          x-versionadded: v2.33
        totalRequests:
          description: Total number of prediction requests performed.
          type:
          - integer
          - 'null'
          x-versionadded: v2.33
        userErrorRate:
          description: Ratio of user errors to the total number of requests.
          type:
          - number
          - 'null'
          x-versionadded: v2.33
      required:
      - cacheHitRatio
      - executionTime
      - numConsumers
      - responseTime
      - serverErrorRate
      - slowRequests
      - totalPredictions
      - totalRequests
      - userErrorRate
      type: object
    ServiceStatsMetricsForTimeRange:
      description: Service health metrics of the deployment
      properties:
        cacheHitRatio:
          description: Number of cache hits.
          type:
          - number
          - 'null'
        executionTime:
          description: Request execution time at executionTimeQuantile (in milliseconds).
          type:
          - number
          - 'null'
        medianLoad:
          description: Median of the request rate (in requests per minute).
          type:
          - number
          - 'null'
        numConsumers:
          description: Number of unique users performing requests.
          type:
          - integer
          - 'null'
        peakLoad:
          description: Maximum of the request rate (in requests per minute).
          type:
          - number
          - 'null'
        responseTime:
          description: Request response time at responseTimeQuantile (in milliseconds).
          type:
          - number
          - 'null'
        serverErrorRate:
          description: Ratio of server errors to the total number of requests.
          type:
          - number
          - 'null'
        slowRequests:
          description: Number of requests with response time greater than slowRequestsThreshold
          type:
          - integer
          - 'null'
        totalPredictions:
          description: Total number of prediction rows.
          type:
          - integer
          - 'null'
        totalRequests:
          description: Total number of prediction requests performed.
          type:
          - integer
          - 'null'
        userErrorRate:
          description: Ratio of user errors to the total number of requests.
          type:
          - number
          - 'null'
      required:
      - cacheHitRatio
      - executionTime
      - medianLoad
      - numConsumers
      - peakLoad
      - responseTime
      - serverErrorRate
      - slowRequests
      - totalPredictions
      - totalRequests
      - userErrorRate
      type: object
    TimeRange:
      description: An object with the keys "start" and "end" defining the period.
      properties:
        end:
          description: 'End of the period to retrieve monitoring data, defaults to the next top of the hour. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: ``2019-08-01T00:00:00Z``.'
          format: date-time
          type:
          - string
          - 'null'
        start:
          description: 'Start of the period to retrieve monitoring data, defaults to 7 days ago from the end of the period. Note: this field only accepts top of the hour RFC3339 datetime strings, for example: ``2019-08-01T00:00:00Z``.'
          format: date-time
          type:
          - string
          - 'null'
      type: object
    ServiceStatsOverTimeBucket:
      description: Service health stats of the deployment over a time range.
      properties:
        modelId:
          description: The id of the model for which metrics are being retrieved.
          type: string
          x-versionadded: v2.37
        period:
          $ref: '#/components/schemas/TimeRange'
        value:
          description: Value of the metric in the bucket. Null if no value
          type:
          - number
          - 'null'
      required:
      - period
      - value
      type: object
    Batch:
      description: Batch info.
      properties:
        earliestPredictionTimestamp:
          description: Earliest prediction timestamp of a batch.
          format: date-time
          type: string
          x-versionadded: v2.33
        id:
          description: Batch ID.
          type: string
          x-versionadded: v2.33
        latestPredictionTimestamp:
          description: Latest prediction timestamp of a batch.
          format: date-time
          type:
          - string
          - 'null'
          x-versionadded: v2.33
        name:
          description: Batch name.
          type: string
          x-versionadded: v2.33
      required:
      - earliestPredictionTimestamp
      - id
      - latestPredictionTimestamp
      - name
      type: object
  securitySchemes:
    BearerAuth:
      description: JWT Bearer Auth
      scheme: bearer
      type: http