Scale AI Training Datasets V3 (Beta) API

openapi: 3.2.0
info:
  title: EGP API V4 Training Datasets V3 (Beta) 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: Training Datasets V3 (Beta)
paths:
  /v4/training-datasets:
    post:
      tags:
      - Training Datasets V3 (Beta)
      summary: Create Training Dataset
      operationId: POST-V4-/training-datasets
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_POST-V4-_training-datasets'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TrainingDatasetResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/training-datasets-v3-beta/create-training-dataset
    get:
      tags:
      - Training Datasets V3 (Beta)
      summary: List Training Datasets
      description: '### Description

        Lists all training datasets accessible to the user.


        ### Details

        This API can be used to list training datasets. If a user has access to multiple accounts, all training datasets from all accounts the user is associated with will be returned.'
      operationId: GET-V4-/training-datasets
      parameters:
      - name: page
        in: query
        required: false
        schema:
          type: integer
          minimum: 1
          description: Page number for pagination to be returned by the given endpoint. Starts at page 1
          default: 1
          title: Page
        description: Page number for pagination to be returned by the given endpoint. Starts at page 1
      - name: limit
        in: query
        required: false
        schema:
          type: integer
          maximum: 10000
          minimum: 1
          description: Maximum number of artifacts to be returned by the given endpoint. Defaults to 100 and cannot be greater than 10k.
          default: 100
          title: Limit
        description: Maximum number of artifacts to be returned by the given endpoint. Defaults to 100 and cannot be greater than 10k.
      - name: account_id
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Account Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PaginatedTrainingDatasetResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/training-datasets-v3-beta/list-training-datasets
  /v4/training-datasets/{training_dataset_id}:
    delete:
      tags:
      - Training Datasets V3 (Beta)
      summary: Delete Training Dataset
      description: '### Description

        Deletes a training dataset


        ### Details

        This API can be used to delete a training dataset by ID. To use this API, pass in the `id` that was returned from your Create Training Dataset API call as a path parameter.'
      operationId: DELETE-V4-/training-datasets/{training_dataset_id}
      parameters:
      - name: training_dataset_id
        in: path
        required: true
        schema:
          type: string
          title: Training Dataset Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeleteResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/training-datasets-v3-beta/delete-training-dataset
    get:
      tags:
      - Training Datasets V3 (Beta)
      summary: Get Training Dataset
      description: '### Description

        Gets the details of a training dataset


        ### Details

        This API can be used to get information about a single training dataset by ID. To use this API, pass in the `id` that was returned from your Create Training Dataset API call as a path parameter.


        Review the response schema to see the fields that will be returned.'
      operationId: GET-V4-/training-datasets/{training_dataset_id}
      parameters:
      - name: training_dataset_id
        in: path
        required: true
        schema:
          type: string
          title: Training Dataset Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TrainingDatasetResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/training-datasets-v3-beta/get-training-dataset
  /v4/training-datasets/{training_dataset_id}/contents:
    get:
      tags:
      - Training Datasets V3 (Beta)
      summary: Get Training Dataset Contents
      operationId: GET-V4-/training-datasets/{training_dataset_id}/contents
      parameters:
      - name: training_dataset_id
        in: path
        required: true
        schema:
          type: string
          title: Training Dataset Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/TrainingDatasetGenerationItem'
                title: Response Get-V4-/Training-Datasets/{Training Dataset Id}/Contents
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-source: https://docs.gp.scale.com/reference/v4/training-datasets-v3-beta/get-training-dataset-contents
components:
  schemas:
    TrainingDatasetORMSchemaTypeEnum:
      type: string
      enum:
      - GENERATION
      - RERANKING_QUESTIONS
      title: TrainingDatasetORMSchemaTypeEnum
    TrainingDatasetGenerationItem:
      properties:
        schema_type:
          type: string
          const: GENERATION
          title: Schema Type
          default: GENERATION
        input:
          type: string
          title: Input
        output:
          title: Output
          type: string
      type: object
      required:
      - input
      - output
      title: TrainingDatasetGenerationItem
    PaginatedTrainingDatasetResponse:
      properties:
        items:
          items:
            $ref: '#/components/schemas/TrainingDatasetResponse'
          type: array
          title: Items
          description: The data returned for the current page.
        total_item_count:
          type: integer
          title: Total Item Count
          description: The total number of items of the query
        current_page:
          type: integer
          title: Current Page
          description: The current page number.
        items_per_page:
          type: integer
          title: Items Per Page
          description: The number of items per page.
      type: object
      required:
      - items
      - total_item_count
      - current_page
      - items_per_page
      title: PaginatedTrainingDatasetResponse
    DataSource:
      type: string
      enum:
      - S3
      - SharePoint
      - SharePointPage
      - LocalFile
      - LocalChunks
      - GoogleDrive
      - AzureBlobStorage
      - GoogleCloudStorage
      - Confluence
      - Slack
      - Snowflake
      - Databricks
      - SQLDatabase
      - MongoDB
      - BigQuery
      title: DataSource
    TrainingDatasetResponse:
      properties:
        name:
          type: string
          title: Name
          description: The name of the dataset
        schema_type:
          $ref: '#/components/schemas/TrainingDatasetORMSchemaTypeEnum'
          description: The schema type of the dataset, currently only GENERATION is supported
        data_source:
          $ref: '#/components/schemas/DataSource'
          description: The data source of the dataset, used to determine how to parse the location
        id:
          type: string
          title: Id
          description: The unique identifier of the entity.
        created_at:
          type: string
          format: date-time
          title: Created At
          description: The date and time when the entity was created in ISO format.
        account_id:
          type: string
          title: Account Id
          description: The ID of the account that owns the given entity.
          can_patch: false
        created_by_user_id:
          type: string
          title: Created By User Id
          description: The user who originally created the entity.
        created_by_identity_type:
          $ref: '#/components/schemas/IdentifierTypeEnum'
          description: The type of identity that created the entity.
      type: object
      required:
      - name
      - schema_type
      - data_source
      - id
      - created_at
      - account_id
      - created_by_user_id
      - created_by_identity_type
      title: TrainingDatasetResponse
    Body_POST-V4-_training-datasets:
      properties:
        account_id:
          type: string
          title: Account Id
          description: The ID of the account that owns the given entity.
        name:
          type: string
          title: Name
          description: The name of the dataset
        schema_type:
          $ref: '#/components/schemas/TrainingDatasetORMSchemaTypeEnum'
          description: The schema type of the dataset, currently only GENERATION is supported
        file:
          type: string
          contentMediaType: application/octet-stream
          title: File
          description: The file to upload as the training dataset
      type: object
      required:
      - account_id
      - name
      - schema_type
      - file
      title: Body_POST-V4-/training-datasets
    IdentifierTypeEnum:
      type: string
      enum:
      - user
      - service_account
      title: IdentifierTypeEnum
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    DeleteResponse:
      properties:
        success:
          type: boolean
          title: Success
        count:
          type: integer
          title: Count
      type: object
      required:
      - success
      - count
      title: DeleteResponse
    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
  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)