NVIDIA Run:ai Events API

openapi: 3.0.3
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 Events 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: Events
  description: Workload events that occurred while the workload was running. Use to diagnose issue around workload scheduling.
paths:
  /api/v1/workloads/{workloadId}/events:
    get:
      summary: Get the workload events.
      description: Retrieve all the workload events using a workload id.
      operationId: get_workload_events
      tags:
      - Events
      parameters:
      - $ref: '#/components/parameters/WorkloadId'
      - $ref: '#/components/parameters/Offset'
      - $ref: '#/components/parameters/Limit'
      - $ref: '#/components/parameters/EventsSort'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                type: object
                required:
                - events
                properties:
                  next:
                    type: integer
                    example: 1
                  events:
                    $ref: '#/components/schemas/Events'
        '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/{workloadId}/history:
    get:
      summary: Get the workload history.
      description: Retrieve workload history details, including events, using a workload id.
      operationId: get_workload_history
      tags:
      - Events
      parameters:
      - $ref: '#/components/parameters/WorkloadId'
      - $ref: '#/components/parameters/Offset'
      - $ref: '#/components/parameters/Limit'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                type: object
                required:
                - records
                properties:
                  next:
                    type: integer
                    example: 1
                  records:
                    $ref: '#/components/schemas/HistoryRecords1'
        '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/revisions/{revisionId}/events:
    get:
      summary: Get revision events by id. [Experimental]
      description: Retrieve all the revision events using a revision id. Supported for clusters v2.21+.
      operationId: get_revision_events
      tags:
      - Events
      parameters:
      - $ref: '#/components/parameters/RevisionId'
      - $ref: '#/components/parameters/Offset'
      - $ref: '#/components/parameters/Limit'
      - $ref: '#/components/parameters/EventsSort'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                type: object
                required:
                - events
                properties:
                  next:
                    type: integer
                    example: 1
                  events:
                    $ref: '#/components/schemas/Events'
        '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/revisions/{revisionId}/history:
    get:
      summary: Get the revision history. [Experimental]
      description: Retrieve revision history details, including events, using a revision id. Supported for clusters v2.21+.
      operationId: get_revision_history
      tags:
      - Events
      parameters:
      - $ref: '#/components/parameters/RevisionId'
      - $ref: '#/components/parameters/Offset'
      - $ref: '#/components/parameters/Limit'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                type: object
                required:
                - records
                properties:
                  next:
                    type: integer
                    example: 1
                  records:
                    $ref: '#/components/schemas/HistoryRecords1'
        '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:
    InvolvedObject:
      type: object
      required:
      - uid
      - kind
      - name
      - namespace
      properties:
        uid:
          type: string
          format: uuid
        kind:
          type: string
          example: Pod
        name:
          type: string
          example: test-0-1
        namespace:
          type: string
          example: runai-test
    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
    HistoryRecord1:
      type: object
      required:
      - meta
      - spec
      properties:
        meta:
          $ref: '#/components/schemas/HistoryRecordMeta'
        spec:
          type: object
          properties:
            event:
              $ref: '#/components/schemas/Event2'
            phaseUpdate:
              $ref: '#/components/schemas/PhaseUpdate'
    HistoryRecordType:
      type: string
      enum:
      - Event
      - PhaseUpdate
    ClusterId:
      description: The id of the cluster.
      type: string
      format: uuid
      example: 71f69d83-ba66-4822-adf5-55ce55efd210
    Phase:
      type: string
      enum:
      - Creating
      - Initializing
      - Resuming
      - Pending
      - Deleting
      - Running
      - Updating
      - Stopped
      - Stopping
      - Degraded
      - Failed
      - Completed
      - Terminating
      - Unknown
    PhaseUpdate:
      type: object
      nullable: true
      example: null
      required:
      - phase
      - phaseMessage
      properties:
        phase:
          $ref: '#/components/schemas/Phase'
        phaseMessage:
          type: string
          example: Not enough resources in the requested nodepool
    Events:
      type: array
      items:
        $ref: '#/components/schemas/Event2'
      x-schema-name: Events
    Event2:
      type: object
      nullable: true
      required:
      - createdAt
      - type
      - clusterId
      - message
      properties:
        createdAt:
          type: string
          format: date-time
          example: '2022-01-01T03:49:52.531Z'
        id:
          type: string
          format: uuid
        type:
          type: string
          example: Normal
        clusterId:
          $ref: '#/components/schemas/ClusterId'
        message:
          type: string
          example: Started container z
        reason:
          type: string
          example: Started
        source:
          type: string
          example: kubelet
        involvedObject:
          $ref: '#/components/schemas/InvolvedObject'
    HistoryRecords1:
      type: array
      items:
        $ref: '#/components/schemas/HistoryRecord1'
      x-schema-name: HistoryRecords
    HistoryRecordMeta:
      type: object
      required:
      - creationTimestamp
      - type
      properties:
        creationTimestamp:
          type: string
          format: date-time
          example: '2022-01-01T03:49:52.531Z'
        type:
          $ref: '#/components/schemas/HistoryRecordType'
  responses:
    404NotFound:
      description: The specified resource was not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 404
            message: Resource id not found.
    500InternalServerError:
      description: unexpected error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 500
            message: Something went wrong.
    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.
  parameters:
    RevisionId:
      name: revisionId
      in: path
      required: true
      description: The  Universally Unique Identifier (UUID) of the revision.
      schema:
        type: string
        format: uuid
    EventsSort:
      name: sortOrder
      in: query
      required: false
      description: Sort results in descending or ascending order.
      schema:
        type: string
        enum:
        - asc
        - desc
        default: desc
    WorkloadId:
      name: workloadId
      in: path
      required: true
      description: The  Universally Unique Identifier (UUID) of the workload.
      schema:
        type: string
        format: uuid
    Limit:
      name: limit
      in: query
      required: false
      description: The maximum number of entries to return.
      schema:
        type: integer
        format: int32
        default: 50
        minimum: 1
        maximum: 500
    Offset:
      name: offset
      in: query
      required: false
      description: The offset of the first item returned in the collection.
      schema:
        type: integer
        format: int32
        example: 100
  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