ArthurAI Datasets V1 API

openapi: 3.2.0
info:
  title: Arthur Scope Datasets V1 API
  version: 0.1.0
tags:
- name: Datasets V1
paths:
  /api/v1/connectors/{connector_id}/datasets:
    get:
      tags:
      - Datasets V1
      summary: Get Datasets By Connector Id
      description: Returns a list of configured datasets for the connector. Requires connector_list_datasets permission.
      operationId: get_connector_datasets
      security:
      - OAuth2AuthorizationCode:
        - connector_list_datasets
      parameters:
      - name: connector_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Connector Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResourceList_Dataset_'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    post:
      tags:
      - Datasets V1
      summary: Create Connector Dataset
      description: Create connector dataset. Requires connector_create_dataset permission.
      operationId: post_connector_dataset
      security:
      - OAuth2AuthorizationCode:
        - connector_create_dataset
      parameters:
      - name: connector_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Connector Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostDataset'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/connectors/{connector_id}/available_datasets:
    get:
      tags:
      - Datasets V1
      summary: Get Available Datasets By Connector Id
      description: Returns a list of available datasets for the connector. Requires connector_list_available_datasets permission.
      operationId: get_connector_available_datasets
      security:
      - OAuth2AuthorizationCode:
        - connector_list_available_datasets
      parameters:
      - name: connector_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Connector Id
      - name: sort
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/AvailableDatasetsSort'
          description: The field to sort by.
          default: created_at
        description: The field to sort by.
      - name: order
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/SortOrder'
          description: The order to sort by.
          default: desc
        description: The order to sort by.
      - name: search
        in: query
        required: false
        schema:
          type: string
          description: Search term to filter by.
          title: Search
        description: Search term to filter by.
      - name: page
        in: query
        required: false
        schema:
          type: integer
          minimum: 1
          description: The page to return starting from 1 up to total_pages.
          default: 1
          title: Page
        description: The page to return starting from 1 up to total_pages.
      - name: page_size
        in: query
        required: false
        schema:
          type: integer
          maximum: 1000
          minimum: 1
          description: The number of records per page. The max is 1000.
          default: 20
          title: Page Size
        description: The number of records per page. The max is 1000.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResourceList_AvailableDataset_'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    put:
      tags:
      - Datasets V1
      summary: Overwrite Connector Available Datasets
      description: Overwrite all available datasets for this connector. Requires connector_put_available_datasets permission.
      operationId: put_connector_available_datasets
      security:
      - OAuth2AuthorizationCode:
        - connector_put_available_datasets
      parameters:
      - name: connector_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Connector Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PutAvailableDatasets'
      responses:
        '204':
          description: Successful Response
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    post:
      tags:
      - Datasets V1
      summary: Create Single Available Dataset
      description: Create a single available dataset for this connector. Requires connector_create_available_datasetpermission.
      operationId: post_available_dataset
      security:
      - OAuth2AuthorizationCode:
        - connector_create_available_dataset
      parameters:
      - name: connector_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Connector Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PutAvailableDataset'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AvailableDataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/datasets/{dataset_id}:
    get:
      tags:
      - Datasets V1
      summary: Get Dataset By Id
      description: Returns a single dataset by ID. Requires dataset_read permission.
      operationId: get_dataset
      security:
      - OAuth2AuthorizationCode:
        - dataset_read
      parameters:
      - name: dataset_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Dataset Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    patch:
      tags:
      - Datasets V1
      summary: Update Dataset
      description: Update a dataset. Requires dataset_update permission.
      operationId: patch_dataset
      security:
      - OAuth2AuthorizationCode:
        - dataset_update
      parameters:
      - name: dataset_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Dataset Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PatchDataset'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - Datasets V1
      summary: Delete Dataset
      description: Delete a dataset. Requires dataset_delete permission.
      operationId: delete_dataset
      security:
      - OAuth2AuthorizationCode:
        - dataset_delete
      parameters:
      - name: dataset_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Dataset Id
      responses:
        '204':
          description: No Content
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/datasets/{dataset_id}/schema:
    put:
      tags:
      - Datasets V1
      summary: Update Dataset Schema
      description: Update a dataset schema. Requires dataset_put_schema permission.
      operationId: put_dataset_schema
      security:
      - OAuth2AuthorizationCode:
        - dataset_put_schema
      parameters:
      - name: dataset_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Dataset Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PutDatasetSchema'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/workspaces/{workspace_id}/datasets:
    get:
      tags:
      - Datasets V1
      summary: Get Workspace Datasets
      description: Endpoint requires workspace_list_datasets permission. It will only include datasets the user has additional dataset_read permissions on in the response.
      operationId: get_datasets_in_workspace
      security:
      - OAuth2AuthorizationCode:
        - workspace_list_datasets
      parameters:
      - name: workspace_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Workspace Id
      - name: sort
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/DatasetsSort'
          description: Override the field used for sorting the returned list. Optional.
          default: created_at
        description: Override the field used for sorting the returned list. Optional.
      - name: order
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/SortOrder'
          description: Override the sort order used. Optional.
          default: desc
        description: Override the sort order used. Optional.
      - name: model_ids
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              type: string
              format: uuid
          - type: 'null'
          description: Filter the results for datasets that are used by these models. Optional.
          title: Model Ids
        description: Filter the results for datasets that are used by these models. Optional.
      - name: search
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Search for datasets by connector name or dataset name.
          title: Search
        description: Search for datasets by connector name or dataset name.
      - name: connector_type
        in: query
        required: false
        schema:
          anyOf:
          - $ref: '#/components/schemas/ConnectorType'
          - type: 'null'
          description: Filter datasets by connector type.
          title: Connector Type
        description: Filter datasets by connector type.
      - name: connector_name
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter datasets by connector name.
          title: Connector Name
        description: Filter datasets by connector name.
      - name: dataset_name
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter datasets by dataset name.
          title: Dataset Name
        description: Filter datasets by dataset name.
      - name: joined_datasets
        in: query
        required: false
        schema:
          anyOf:
          - type: boolean
          - type: 'null'
          description: Filter for joined datasets. Only returns joined datasets if True. Only returns non-joined datasets if False. Not applied if None.
          title: Joined Datasets
        description: Filter for joined datasets. Only returns joined datasets if True. Only returns non-joined datasets if False. Not applied if None.
      - name: data_plane_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          description: Filter datasets by the data plane (engine) that backs them.
          title: Data Plane Id
        description: Filter datasets by the data plane (engine) that backs them.
      - name: page
        in: query
        required: false
        schema:
          type: integer
          minimum: 1
          description: The page to return starting from 1 up to total_pages.
          default: 1
          title: Page
        description: The page to return starting from 1 up to total_pages.
      - name: page_size
        in: query
        required: false
        schema:
          type: integer
          maximum: 1000
          minimum: 1
          description: The number of records per page. The max is 1000.
          default: 20
          title: Page Size
        description: The number of records per page. The max is 1000.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResourceList_Dataset_'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/projects/{project_id}/datasets:
    get:
      tags:
      - Datasets V1
      summary: Get Datasets
      description: Returns a list of configured datasets. Requires project_list_datasets permission.
      operationId: get_datasets
      security:
      - OAuth2AuthorizationCode:
        - project_list_datasets
      parameters:
      - name: project_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Project Id
      - name: sort
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/DatasetsSort'
          description: Override the field used for sorting the returned list. Optional.
          default: created_at
        description: Override the field used for sorting the returned list. Optional.
      - name: order
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/SortOrder'
          description: Override the sort order used. Optional.
          default: desc
        description: Override the sort order used. Optional.
      - name: model_ids
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              type: string
              format: uuid
          - type: 'null'
          description: Filter the results for datasets that are used by these models. Optional.
          title: Model Ids
        description: Filter the results for datasets that are used by these models. Optional.
      - name: search
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Search for datasets by connector name or dataset name.
          title: Search
        description: Search for datasets by connector name or dataset name.
      - name: connector_type
        in: query
        required: false
        schema:
          anyOf:
          - $ref: '#/components/schemas/ConnectorType'
          - type: 'null'
          description: Filter datasets by connector type.
          title: Connector Type
        description: Filter datasets by connector type.
      - name: connector_name
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter datasets by connector name.
          title: Connector Name
        description: Filter datasets by connector name.
      - name: dataset_name
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter datasets by dataset name.
          title: Dataset Name
        description: Filter datasets by dataset name.
      - name: joined_datasets
        in: query
        required: false
        schema:
          anyOf:
          - type: boolean
          - type: 'null'
          description: Filter for joined datasets. Only returns joined datasets if True. Only returns non-joined datasets if False. Not applied if None.
          title: Joined Datasets
        description: Filter for joined datasets. Only returns joined datasets if True. Only returns non-joined datasets if False. Not applied if None.
      - name: data_plane_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          description: Filter datasets by the data plane (engine) that backs them.
          title: Data Plane Id
        description: Filter datasets by the data plane (engine) that backs them.
      - name: page
        in: query
        required: false
        schema:
          type: integer
          minimum: 1
          description: The page to return starting from 1 up to total_pages.
          default: 1
          title: Page
        description: The page to return starting from 1 up to total_pages.
      - name: page_size
        in: query
        required: false
        schema:
          type: integer
          maximum: 1000
          minimum: 1
          description: The number of records per page. The max is 1000.
          default: 20
          title: Page Size
        description: The number of records per page. The max is 1000.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResourceList_Dataset_'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    post:
      tags:
      - Datasets V1
      summary: Create Project Dataset
      description: Create project dataset. Requires project_create_dataset permission.
      operationId: post_project_dataset
      security:
      - OAuth2AuthorizationCode:
        - project_create_dataset
      parameters:
      - name: project_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Project Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostDataset'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/projects/{project_id}/available_datasets:
    post:
      tags:
      - Datasets V1
      summary: Create Project Available Dataset
      description: Create project dataset. Requires project_create_available_dataset permission.
      operationId: post_project_available_dataset
      security:
      - OAuth2AuthorizationCode:
        - project_create_available_dataset
      parameters:
      - name: project_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Project Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PutAvailableDataset'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AvailableDataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestError'
          description: Bad Request
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/available_datasets/{available_dataset_id}:
    get:
      tags:
      - Datasets V1
      summary: Get Available Dataset By Id
      description: Returns a single available dataset by ID. Requires available_dataset_read permission.
      operationId: get_available_dataset
      security:
      - OAuth2AuthorizationCode:
        - available_dataset_read
      parameters:
      - name: available_dataset_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Available Dataset Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AvailableDataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/available_datasets/{available_dataset_id}/schema:
    put:
      tags:
      - Datasets V1
      summary: Update Available Dataset Schema
      description: Update a single available dataset schema. Requires available_dataset_put_schema permission.
      operationId: put_available_dataset_schema
      security:
      - OAuth2AuthorizationCode:
        - available_dataset_put_schema
      parameters:
      - name: available_dataset_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Available Dataset Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PutDatasetSchema'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AvailableDataset'
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerError'
          description: Internal Server Error
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundError'
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    Dataset:
      properties:
        created_at:
          type: string
          format: date-time
          title: Created At
          description: Time of record creation.
        updated_at:
          type: string
          format: date-time
          title: Updated At
          description: Time of last record update.
        id:
          type: string
          format: uuid
          title: Id
          description: Unique ID of the dataset.
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: Name of the dataset.
        dataset_locator:
          anyOf:
          - $ref: '#/components/schemas/DatasetLocator'
          - type: 'null'
          description: Metadata specifying the location of the dataset within the connector. Schema defined on connector schema.
        dataset_schema:
          $ref: '#/components/schemas/DatasetSchema'
          description: Schema definition of the dataset.
        data_plane_id:
          type: string
          format: uuid
          title: Data Plane Id
          description: ID of the data plane backing this dataset.
        connector:
          anyOf:
          - $ref: '#/components/schemas/DatasetConnector'
          - type: 'null'
          description: Connector associated with the dataset.
        project_id:
          type: string
          format: uuid
          title: Project Id
          description: ID of parent project.
        join_spec:
          anyOf:
          - $ref: '#/components/schemas/DatasetJoinSpec'
          - type: 'null'
          description: Field for defining a dataset as a join between two other datasets.
        model_problem_type:
          $ref: '#/components/schemas/ModelProblemType'
          description: Model problem type associated with the dataset.
        is_static:
          type: boolean
          title: Is Static
          description: Whether this dataset has no time dimension. Static datasets are fully loaded on each metrics run.
          default: false
      type: object
      required:
      - created_at
      -

# --- truncated at 32 KB (50 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/arthurai/refs/heads/main/openapi/arthurai-datasets-v1-api-openapi.yml