Scale AI Model server API

openapi: 3.2.0
info:
  title: EGP API V4 Model server API
  description: This is the parent API for all EGP APIs. If you are looking for the EGP API, please go to https://api.egp.scale.com/docs.
  contact:
    name: Scale Generative AI Platform
    url: https://scale.com/genai-platform
  version: 0.1.0
servers:
- url: https://api.egp.scale.com
security: []
tags:
- name: Model server
paths:
  /v4/serving:
    post:
      tags:
      - Model server
      summary: Create a new Model Server
      operationId: POST-V4-/v4/serving
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateModelServerRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelServerInfo'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/create-a-new-model-server
  /v4/serving/{model_server_id}/backend:
    put:
      tags:
      - Model server
      summary: Change backend of the Model Server
      operationId: PUT-V4-/v4/serving/{model_server_id}/backend
      parameters:
      - name: model_server_id
        in: path
        required: true
        schema:
          type: string
          title: Model Server Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChangeBackendRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChangeBackendResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/change-backend-of-the-model-server
  /v4/serving/a/{alias}/executeAsync:
    post:
      tags:
      - Model server
      summary: Fixed Server interface for async Model execution by named alias
      operationId: POST-V4-/v4/serving/a/{alias}/executeAsync
      parameters:
      - name: alias
        in: path
        required: true
        schema:
          title: Alias
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenericModelRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncModelExecuteResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/fixed-server-interface-for-async-model-execution-by-named-alias
  /v4/serving/{model_server_id}/executeAsync:
    post:
      tags:
      - Model server
      summary: Fixed Server interface for async Model execution
      operationId: POST-V4-/v4/serving/{model_server_id}/executeAsync
      parameters:
      - name: model_server_id
        in: path
        required: true
        schema:
          type: string
          title: Model Server Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenericModelRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericModelResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/fixed-server-interface-for-async-model-execution
  /v4/serving/a/{alias}/execute:
    post:
      tags:
      - Model server
      summary: Fixed Server interface for Model execution by named alias
      operationId: POST-V4-/v4/serving/a/{alias}/execute
      parameters:
      - name: alias
        in: path
        required: true
        schema:
          title: Alias
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenericModelRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericModelResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/fixed-server-interface-for-model-execution-by-named-alias
  /v4/serving/{model_server_id}/execute:
    post:
      tags:
      - Model server
      summary: Fixed Server interface for Model execution
      operationId: POST-V4-/v4/serving/{model_server_id}/execute
      parameters:
      - name: model_server_id
        in: path
        required: true
        schema:
          type: string
          title: Model Server Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenericModelRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenericModelResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/fixed-server-interface-for-model-execution
  /v4/serving/{model_server_id}/deployment:
    get:
      tags:
      - Model server
      summary: Get current deployment of the Model Server
      operationId: GET-V4-/v4/serving/{model_server_id}/deployment
      parameters:
      - name: model_server_id
        in: path
        required: true
        schema:
          type: string
          title: Model Server Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetModelServerDeploymentResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/get-current-deployment-of-the-model-server
  /v4/serving/a/{alias}/pollAsync/{async_task_id}:
    get:
      tags:
      - Model server
      summary: Poll Async Inference for result by named alias
      operationId: GET-V4-/v4/serving/a/{alias}/pollAsync/{async_task_id}
      parameters:
      - name: alias
        in: path
        required: true
        schema:
          title: Alias
          type: string
      - name: async_task_id
        in: path
        required: true
        schema:
          type: string
          title: Async Task Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncPollTaskResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/poll-async-inference-for-result-by-named-alias
  /v4/serving/{model_server_id}/pollAsync/{async_task_id}:
    get:
      tags:
      - Model server
      summary: Poll Async Inference for result
      operationId: GET-V4-/v4/serving/{model_server_id}/pollAsync/{async_task_id}
      parameters:
      - name: model_server_id
        in: path
        required: true
        schema:
          type: string
          title: Model Server Id
      - name: async_task_id
        in: path
        required: true
        schema:
          type: string
          title: Async Task Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncPollTaskResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/poll-async-inference-for-result
  /v4/serving/{model_server_id}/rollback:
    post:
      tags:
      - Model server
      summary: Rollback backend of the Model Server
      operationId: POST-V4-/v4/serving/{model_server_id}/rollback
      parameters:
      - name: model_server_id
        in: path
        required: true
        schema:
          type: string
          title: Model Server Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RollbackResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/model-server/rollback-backend-of-the-model-server
components:
  schemas:
    ChangeBackendResponse:
      properties:
        name:
          type: string
          title: Name
        model_server_id:
          type: string
          title: Model Server Id
        model_deployment_id:
          title: Model Deployment Id
          type: string
        account_id:
          type: string
          title: Account Id
        alias:
          title: Alias
          type: string
        new_model_deployment_id:
          type: string
          title: New Model Deployment Id
        old_model_deployment_id:
          title: Old Model Deployment Id
          type: string
      type: object
      required:
      - name
      - model_server_id
      - account_id
      - new_model_deployment_id
      title: ChangeBackendResponse
      description: "Point the model server to a new model deployment.\n\nArgs:\n    old_model_deployment_id(str): The ID of the model deployment to use as the new backend."
    CreateModelServerRequest:
      properties:
        name:
          type: string
          title: Name
        model_deployment_id:
          title: Model Deployment Id
          type: string
        alias:
          title: Alias
          type: string
      type: object
      required:
      - name
      - model_deployment_id
      title: CreateModelServerRequest
      description: "Create a new model server with an initial backend configuration.\n\nArgs:\n    name (str): The name of the model server. Only used for display purposes.\n    model_deployment_id (str): The ID of the model deployment to use as the initial backend.\n    alias (str, optional): An alias for the model server. Defaults to None. If configured the model\n        server can be accessed via the alias instead of the model server ID. i.e /models/server/alias/{alias}/execute"
    GetModelServerDeploymentResponse:
      properties:
        model_deployment_id:
          title: Model Deployment Id
          type: string
      type: object
      required:
      - model_deployment_id
      title: GetModelServerDeploymentResponse
    GenericModelResponse:
      properties:
        status:
          type: string
          title: Status
        status_code:
          title: Status Code
          type: integer
        error_message:
          title: Error Message
          type: string
      additionalProperties: true
      type: object
      title: GenericModelResponse
    ChangeBackendRequest:
      properties:
        new_model_deployment_id:
          type: string
          title: New Model Deployment Id
      type: object
      required:
      - new_model_deployment_id
      title: ChangeBackendRequest
    AsyncModelExecuteResponse:
      properties:
        async_task_id:
          type: string
          title: Async Task Id
      type: object
      required:
      - async_task_id
      title: AsyncModelExecuteResponse
    ModelServerInfo:
      properties:
        name:
          type: string
          title: Name
        model_server_id:
          type: string
          title: Model Server Id
        model_deployment_id:
          title: Model Deployment Id
          type: string
        account_id:
          type: string
          title: Account Id
        alias:
          title: Alias
          type: string
      type: object
      required:
      - name
      - model_server_id
      - account_id
      title: ModelServerInfo
      description: 'Model server information.

        name: The name of the model server. Only used for display purposes.

        model_server_id: The ID of the model server.

        model_deployment_id: The ID of the model deployment being used as the backend.

        account_id: The ID of the account that owns the model server.

        alias: An alias for the model server. If configured the model server can be accessed via the alias instead of the model server ID. i.e /models/server/alias/{alias}/execute'
    RollbackResponse:
      properties:
        rolled_back_to_deployment:
          type: string
          title: Rolled Back To Deployment
        from_deployment:
          type: string
          title: From Deployment
      type: object
      required:
      - rolled_back_to_deployment
      - from_deployment
      title: RollbackResponse
    AsyncPollTaskResponse:
      properties:
        status:
          type: string
          title: Status
        result:
          title: Result
        traceback:
          title: Traceback
          type: string
        reason:
          title: Reason
          type: string
        code:
          title: Code
          type: string
      type: object
      required:
      - status
      title: AsyncPollTaskResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
          additionalProperties: true
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    GenericModelRequest:
      properties:
        stream:
          title: Stream
          description: Flag indicating whether to stream the completion response
          default: false
          type: boolean
      additionalProperties: true
      type: object
      title: GenericModelRequest
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: x-api-key
x-assembled-from: Per-operation OpenAPI fragments embedded verbatim in docs.gp.scale.com reference pages; source spec https://api.sgp.scale.com/openapi-versions/v4/openapi.json (404 when assembled)