Seldon health API

openapi: 3.0.0
info:
  description: 'API to interact and manage the lifecycle of your machine learning models

    deployed through Seldon Deploy.'
  title: Seldon Deploy AlertingService health API
  version: v1alpha1
servers:
- url: http://X.X.X.X/seldon-deploy/api/v1alpha1
- url: https://X.X.X.X/seldon-deploy/api/v1alpha1
security:
- OAuth2:
  - '[]'
tags:
- name: health
paths:
  /v2/health/live:
    get:
      summary: Server Live
      responses:
        '200':
          description: OK
      operationId: server-live
      description: The “server live” API indicates if the inference server is able to receive and respond to metadata and inference requests. The “server live” API can be used directly to implement the Kubernetes `livenessProbe`.
      tags:
      - health
  /v2/health/ready:
    get:
      summary: Server Ready
      tags:
      - health
      responses:
        '200':
          description: OK
      operationId: server-ready
      description: The “server ready” health API indicates if all the models are ready for inferencing. The “server ready” health API can be used directly to implement the Kubernetes readinessProbe.
  /v2/models/{model_name}/versions/{model_version}/ready:
    parameters:
    - schema:
        type: string
      name: model_name
      in: path
      required: true
    - schema:
        type: string
      name: model_version
      in: path
      required: true
    get:
      summary: Model Ready
      tags:
      - health
      responses:
        '200':
          description: OK
      operationId: model-version-ready
      description: The “model ready” health API indicates if a specific model is ready for inferencing. The model name and (optionally) version must be available in the URL. If a version is not provided the server may choose a version based on its own policies.
  /v2/models/{model_name}/ready:
    parameters:
    - schema:
        type: string
      name: model_name
      in: path
      required: true
    get:
      summary: Model Ready
      tags:
      - health
      responses:
        '200':
          description: OK
      operationId: model-ready
      description: The “model ready” health API indicates if a specific model is ready for inferencing. The model name and (optionally) version must be available in the URL. If a version is not provided the server may choose a version based on its own policies.
components:
  securitySchemes:
    OAuth2:
      type: oauth2
      flows:
        password:
          tokenUrl: https://Y.Y.Y.Y
          scopes:
            email: ''
            groups: ''
            openid: ''
            profile: ''