NVIDIA Run:ai Revisions API

openapi: 3.2.0
info:
  version: latest
  description: '# Introduction


    The NVIDIA Run:ai Control-Plane API reference is a guide that provides an easy-to-use programming interface for adding various tasks to your application, including workload submission, resource management, and administrative operations.


    NVIDIA Run:ai APIs are accessed using *bearer tokens*. To obtain a token, you need to create a **Service account** through the NVIDIA Run:ai user interface.

    To create a service account, in your UI, go to Access → Service Accounts (for organization-level service accounts) or User settings → Access Keys (for user access keys), and create a new one.


    After you have created a new service account, you will need to assign it access rules.

    To assign access rules to the service account, see [Create access rules](https://run-ai-docs.nvidia.com/saas/infrastructure-setup/authentication/accessrules#create-or-delete-rules).

    Make sure you assign the correct rules to your service account. Use the [Roles](https://run-ai-docs.nvidia.com/saas/infrastructure-setup/authentication/roles) to assign the correct access rules.


    To get your access token, follow the instructions in [Request a token](https://run-ai-docs.nvidia.com/saas/reference/api/rest-auth/#request-an-api-token).

    '
  title: NVIDIA Run:ai Access Keys Revisions API
  x-logo:
    url: https://api.redocly.com/registry/raw/runai-xq8/saas/latest/public/runai-logo-api.png
    altText: NVIDIA Run:ai
    href: https://run.ai
  license:
    name: NVIDIA Run:ai
    url: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/
servers:
- url: https://app.run.ai
security:
- bearerAuth: []
tags:
- name: Revisions
  description: Revisions are associated with an inference workload and represent a snapshot of its configuration. A revision is created on each change to the inference workload.
paths:
  /api/v1/workloads/inferences/{workloadId}/revisions:
    get:
      summary: Get inference workload revisions by id. [Experimental]
      description: Retrieve the details of inference workload revisions by workload id. Supported for clusters v2.21+.
      operationId: get_inference_workload_revisions
      tags:
      - Revisions
      parameters:
      - $ref: '#/components/parameters/WorkloadId'
      - $ref: '#/components/parameters/Deleted'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                type: object
                required:
                - revisions
                properties:
                  revisions:
                    type: array
                    items:
                      $ref: '#/components/schemas/Revision'
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '404':
          $ref: '#/components/responses/404NotFound'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
  /api/v1/workloads/inferences/{workloadId}/revisions/count:
    get:
      summary: Get inference workload revisions count. [Experimental]
      description: Retrieve the number of an inference workload revisions from a cluster. Supported for clusters v2.21+.
      operationId: count_inference_workload_revisions
      tags:
      - Revisions
      parameters:
      - $ref: '#/components/parameters/WorkloadId'
      - $ref: '#/components/parameters/Deleted'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                type: object
                required:
                - count
                properties:
                  count:
                    type: integer
                    format: int64
                    example: 1
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
  /api/v1/workloads/inferences/revisions/{revisionId}:
    get:
      summary: Get revision data. [Experimental]
      operationId: get_revision
      description: Retrieve revision details using a revision id. Supported for clusters v2.21+.
      tags:
      - Revisions
      parameters:
      - $ref: '#/components/parameters/RevisionId'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Revision'
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '404':
          $ref: '#/components/responses/404NotFound'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
components:
  schemas:
    ClusterId:
      description: The id of the cluster.
      type: string
      format: uuid
      example: 71f69d83-ba66-4822-adf5-55ce55efd210
    WorkloadAllocatedResources:
      type:
      - object
      - 'null'
      properties:
        gpu:
          type:
          - number
          - 'null'
          format: double
          example: 1.5
          description: Required if and only if gpuRequestType is portion. States the number of GPUs allocated for the created workload. The default is no allocated GPUs.
        gpuMemory:
          type:
          - string
          - 'null'
          pattern: ^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
          example: 200Mi
        cpu:
          type:
          - number
          - 'null'
          format: double
          description: States the amount of CPU cores used by the workload running.
          example: 0.5
        cpuMemory:
          type:
          - string
          - 'null'
          pattern: ^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
          example: 0B
        extendedResources:
          $ref: '#/components/schemas/WorkloadsExtendedResources'
    WorkloadsExtendedResource:
      description: Quantity of an extended resource.
      type:
      - object
      - 'null'
      properties:
        resource:
          description: The name of the extended resource (mandatory)
          type:
          - string
          - 'null'
          example: hardware-vendor.example/foo
          minLength: 1
        quantity:
          description: The requested quantity for the given resource.
          type:
          - string
          - 'null'
          example: 2
          minLength: 1
        exclude:
          description: Whether to exclude this extended resource from the workload. This is necessary in case the extended resource is inherited from the policy defaults and it is desired not to include it in this workload.
          type:
          - boolean
          - 'null'
          example: false
    RequestResourceQuantity:
      type:
      - object
      - 'null'
      properties:
        limit:
          type:
          - string
          - 'null'
          pattern: ^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
          example: 2G
        request:
          type:
          - string
          - 'null'
          pattern: ^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
          example: 200M
    RequestedPods:
      type: object
      properties:
        number:
          type:
          - integer
          - 'null'
          format: int32
          example: 1
        min:
          type:
          - integer
          - 'null'
          format: int32
          example: 2
        max:
          type:
          - integer
          - 'null'
          format: int32
          example: 5
        parallelism:
          type:
          - integer
          - 'null'
          format: int32
          description: specifies how many Pods can run in parallel
          example: 3
        completions:
          type:
          - integer
          - 'null'
          description: specifies how many Pods should terminate successfully before the Workload is completed
          format: int32
          example: 5
    Conditions:
      type: array
      items:
        $ref: '#/components/schemas/Condition1'
      x-schema-name: Conditions
    TenantId:
      description: The id of the tenant.
      type: integer
      format: int32
      example: 1001
    WorkloadsExtendedResources:
      description: Set of extended resources with their quantity
      type:
      - array
      - 'null'
      items:
        $ref: '#/components/schemas/WorkloadsExtendedResource'
    ProjectId:
      description: The id of the project.
      type: string
      example: 1
      pattern: .*
    DepartmentId2:
      description: The id of the department.
      type: string
      minLength: 1
      example: 2
      pattern: .*
    GpuRequestType:
      description: Sets the unit type for GPU resources requests. Stated in terms of portion or memory. Sets the unit type for other GPU request fields. If `gpuDevicesRequest > 1`, only `portion` is supported. If `gpuDeviceRequest = 1`, the request type can be stated as `portion` or `memory`.
      type:
      - string
      - 'null'
      minLength: 1
      enum:
      - portion
      - memory
    Revision:
      type: object
      required:
      - type
      - name
      - id
      - workloadId
      - tenantId
      - clusterId
      - departmentId
      - projectId
      - createdAt
      - phase
      properties:
        type:
          type: string
          example: runai-revision
        name:
          type: string
          example: very-important-job
        id:
          type: string
          format: uuid
        workloadId:
          type: string
          format: uuid
        tenantId:
          $ref: '#/components/schemas/TenantId'
        clusterId:
          $ref: '#/components/schemas/ClusterId'
        projectId:
          $ref: '#/components/schemas/ProjectId'
        departmentId:
          $ref: '#/components/schemas/DepartmentId2'
        createdAt:
          type: string
          format: date-time
          example: '2022-01-01T03:49:52.531Z'
        deletedAt:
          type:
          - string
          - 'null'
          format: date-time
          example: '2022-08-12T19:28:24.131Z'
        revisionRequestedResources:
          $ref: '#/components/schemas/WorkloadRequestResources'
        podsRequestedResources:
          $ref: '#/components/schemas/WorkloadRequestResources'
        requestedPods:
          $ref: '#/components/schemas/RequestedPods'
        requestedNodePools:
          type: array
          items:
            type: string
            example: default
        allocatedResources:
          $ref: '#/components/schemas/WorkloadAllocatedResources'
        currentNodePools:
          type: array
          items:
            type: string
            example: default
        runningPods:
          type: integer
          format: int32
          example: 1
        images:
          type: array
          items:
            type: string
            example: alpine:latest
        environmentVariables:
          type: object
          additionalProperties:
            type: string
        command:
          type: string
          example: sleep
        arguments:
          type: string
          example: '1000'
        childrenIds:
          type: array
          writeOnly: true
          items:
            type: object
            required:
            - id
            properties:
              id:
                type: string
                format: uuid
              type:
                type: string
        conditions:
          $ref: '#/components/schemas/Conditions'
        phase:
          $ref: '#/components/schemas/Phase'
        phaseMessage:
          type: string
          example: Not enough resources in the requested nodepool
        phaseUpdatedAt:
          type: string
          format: date-time
          example: '2022-06-08T11:28:24.131Z'
        additionalFields:
          type: object
          additionalProperties: true
    Phase:
      type: string
      enum:
      - Creating
      - Initializing
      - Resuming
      - Pending
      - Deleting
      - Running
      - Updating
      - Stopped
      - Stopping
      - Degraded
      - Failed
      - Completed
      - Terminating
      - Unknown
    WorkloadRequestResources:
      type:
      - object
      - 'null'
      properties:
        gpuRequestType:
          $ref: '#/components/schemas/GpuRequestType'
        gpu:
          $ref: '#/components/schemas/RequestResourceCores'
        gpuMemory:
          $ref: '#/components/schemas/RequestResourceQuantity'
        cpu:
          $ref: '#/components/schemas/RequestResourceCores'
        cpuMemory:
          $ref: '#/components/schemas/RequestResourceQuantity'
        extendedResources:
          $ref: '#/components/schemas/WorkloadsExtendedResources'
    RequestResourceCores:
      type:
      - object
      - 'null'
      properties:
        limit:
          type:
          - number
          - 'null'
          format: double
          example: 1.5
        request:
          type:
          - number
          - 'null'
          format: double
          example: 1
    Condition1:
      type: object
      required:
      - type
      - status
      properties:
        type:
          description: The type of the condition, such as Failed or Available. See Types of domain status conditions.
          type: string
          example: Ready
        status:
          type: string
          description: The status of the condition, such as True, False or Unknown.
          example: 'False'
        message:
          type: string
          description: An optional, human-readable message providing more details about the condition.
          example: 'Resource validation failed: ...'
        reason:
          type: string
          description: The reason for the Failed condition. Not applicable to other types of condition.
          example: ErrorConfig
        lastTransitionTime:
          description: A timestamp of when the condition was created or the last time the condition transitioned from one status to another.
          type:
          - string
          - 'null'
          format: date-time
          example: '2022-01-01T03:49:52.531Z'
    Error:
      required:
      - code
      - message
      properties:
        code:
          type: integer
          minimum: 100
          maximum: 599
        message:
          type: string
        details:
          type: string
      example:
        code: 400
        message: Bad request - Resource should have a name
  parameters:
    Deleted:
      name: deleted
      in: query
      description: Return only deleted resources when `true`.
      schema:
        type: boolean
    WorkloadId:
      name: workloadId
      in: path
      required: true
      description: The  Universally Unique Identifier (UUID) of the workload.
      schema:
        type: string
        format: uuid
    RevisionId:
      name: revisionId
      in: path
      required: true
      description: The  Universally Unique Identifier (UUID) of the revision.
      schema:
        type: string
        format: uuid
  responses:
    403Forbidden:
      description: Forbidden
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 403
            message: You do not have sufficient permissions.
    503ServiceUnavailable:
      description: unexpected error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 503
            message: Please try again in few minutes.
    401Unauthorized:
      description: Unauthorized
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 401
            message: Issuer is not familiar.
    500InternalServerError:
      description: unexpected error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 500
            message: Something went wrong.
    404NotFound:
      description: The specified resource was not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 404
            message: Resource id not found.
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Bearer authentication
x-tagGroups:
- name: Organizations
  tags:
  - Clusters
  - Departments
  - Reports
  - NodePools
  - Nodes
  - Projects
  - Tenant
  - Logo
  - Researcher Command Line Interface
  - Researcher Command Line Interface Deprecated
  - Administrator Command Line Interface
  - Network Topologies
- name: Authentication and Authorization
  tags:
  - Access Keys
  - Access rules
  - Permissions
  - Applications
  - Service Accounts
  - Roles
  - Tokens
  - Users
  - User Applications
  - Idps
  - Me
  - Settings
  - Org unit
- name: Audit
  tags:
  - AuditLogs
- name: Datavolumes
  tags:
  - Datavolumes
- name: Workloads
  tags:
  - Events
  - Pods
  - Workloads
  - Workloads V2
  - NVIDIA NIM
  - Workspaces
  - Trainings
  - Inferences
  - Revisions
  - Distributed
  - Workloads batch
  - Workload properties
  - Workload templates
  - Distributed Inferences
- name: Workload assets
  tags:
  - Compute
  - Credentials
  - Datasources
  - Environment
  - Storage Classes
  - Storage Class Configuration
  - Git
  - HostPath
  - NFS
  - PVC
  - Registry
  - S3
  - ConfigMap
  - Secret
  - Template
- name: Policies
  tags:
  - Policy
- name: Notifications
  tags:
  - Notification State
  - Notification Types
  - NotificationChannels
  - Subscriptions
- name: AI Applications
  tags:
  - AI Applications