OPAQUE Datasets API

openapi: 3.2.0
info:
  title: Opaque UI Datasets API
  version: '2.5'
  description: This documentation details the REST API endpoints that the client exposes.
  contact:
    name: Opaque Systems
    email: hello@opaque.co
servers:
- url: http://localhost:5001/
  description: Local Server
security:
- sessionToken: []
  refreshTokenCookie: []
tags:
- name: datasets
  description: Data & Datum
paths:
  /{version}/workspace/{workspace-uuid}/data:
    parameters:
    - $ref: '#/components/parameters/version'
    - schema:
        type: string
      name: workspace-uuid
      in: path
      required: true
    get:
      summary: Get data for workspace
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: ../models/Datum.yaml
      operationId: get_data_by_workspace
      description: 'Get a list of all datum matching the workspace UUID.

        `conditions` and `conditionDropdowns` will be **null** in objects where the user is not the creator.'
      tags:
      - datasets
    delete:
      summary: Remove data from workspace
      tags:
      - datasets
      parameters:
      - schema:
          type: string
        name: dataset-path
        in: query
        required: true
      - schema:
          type: string
        name: data-store-config-uuid
        in: query
        required: true
      responses:
        '204':
          description: No Content
      operationId: remove_workspace_data
  /{version}/datum/{datum-uuid}:
    parameters:
    - schema:
        type: string
      name: datum-uuid
      in: path
      required: true
    - $ref: '#/components/parameters/version'
    get:
      summary: Get datum
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: ../models/Datum.yaml
      operationId: get_datum
      description: 'Get a datum.

        `conditions` and `conditionDropdowns` will be **null** if the user is not the creator.'
      tags:
      - datasets
    delete:
      summary: Delete datum
      operationId: delete_datum
      responses:
        '204':
          description: No Content
        '500':
          description: 'Internal Server Error

            - Provider deletion failed'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
      tags:
      - datasets
      description: Delete the datum with the provided id
    patch:
      summary: Update data in workspace
      tags:
      - datasets
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: ../models/Datum.yaml
      operationId: update_workspace_data
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                description:
                  type: string
                  x-stoplight:
                    id: lj7wjfrbrvoe4
  /{version}/organization/datasets:
    parameters:
    - $ref: '#/components/parameters/version'
    get:
      summary: List Data
      tags:
      - datasets
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: ../models/OrganizationData.yaml
      operationId: list_data
  /{version}/organization/data:
    parameters:
    - $ref: '#/components/parameters/version'
    - schema:
        type: string
      name: dataset-path
      in: query
      required: true
    - schema:
        type: string
      name: data-store-config-uuid
      in: query
      required: true
    get:
      summary: Get dataset metadata
      tags:
      - datasets
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: ../models/OrganizationData.yaml
        '400':
          description: Bad Request
      operationId: get_data_metadata
    patch:
      summary: Update dataset
      tags:
      - datasets
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: ../models/OrganizationData.yaml
      operationId: update_data
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                name:
                  type: string
                  x-stoplight:
                    id: 1236qktwgl5h8
                description:
                  type: string
                  x-stoplight:
                    id: 7xpiox3s2axqp
                testDataType:
                  type: string
                  enum:
                  - synthetic
                  - mock
                  description: Type of test data to generate. Synthetic test data simulates the original data file. Mock test data is faked data that only uses the data schema.
    delete:
      summary: Delete dataset
      tags:
      - datasets
      responses:
        '204':
          description: No Content
      operationId: delete_data
  /{version}/organization/data/schema:
    parameters:
    - $ref: '#/components/parameters/version'
    post:
      summary: Upload dataset schema
      operationId: upload_dataset_schema
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                properties:
                  schemaId:
                    type: string
                    description: The upload id corresponding to this schema upload.
                required:
                - schemaId
        '500':
          description: 'Internal Server Error

            - Could not write schema to disk'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
      description: Upload a datum's schema.
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  type: string
                  format: Binary
                  description: Schema file getting uploaded.
              required:
              - file
          application/json:
            schema:
              type: object
      tags:
      - datasets
  /{version}/organization/data/share:
    parameters:
    - $ref: '#/components/parameters/version'
    post:
      summary: Batch share organization data with workspace
      tags:
      - datasets
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: ../models/Datum.yaml
      operationId: share_org_data_with_workspace
      requestBody:
        content:
          application/json:
            schema:
              type: array
              items:
                type: object
                properties:
                  workspace-uuid:
                    type: string
                  dataset-path:
                    type: string
                  data-store-config-uuid:
                    type: string
                  description:
                    type: string
                required:
                - workspace-uuid
                - dataset-path
                - data-store-config-uuid
  /{version}/organization/data/upload:
    parameters:
    - $ref: '#/components/parameters/version'
    post:
      summary: Upload data
      operationId: upload_data
      responses:
        '200':
          description: 'OK

            - Data upload successful'
          content:
            application/json:
              schema:
                $ref: ../models/OrganizationData.yaml
        '204':
          description: 'No Content

            - Chunk upload successful'
        '400':
          description: 'Bad Request

            - File already exists'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
        '500':
          description: 'Internal Server Error

            - Could not write file to disk

            - Size mismatch

            - Encryption failed

            - Upload to provider failed'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  type: string
                  format: Binary
                schemaId:
                  type: string
                name:
                  type: string
                policy:
                  $ref: ../models/DatumPolicy.yaml
                testDataType:
                  type: string
                  enum:
                  - synthetic
                  - mock
                  description: Type of test data to generate. Synthetic test data simulates the original data file. Mock test data is faked data that only uses the data schema.
                description:
                  type: string
                dzchunkindex:
                  type: string
                  description: The current chunk index. Required if chunked = true.
                dzchunkbyteoffset:
                  type: string
                  description: The byte offset to place chunk at in file. Required if chunked = true.
                dztotalchunkcount:
                  type: string
                  description: Total number of chunks. Required if chunked = true.
                dztotalfilesize:
                  type: string
                  description: Total file size. Required if chunked = true.
              required:
              - file
              - schemaId
              - name
              - policy
              - testDataType
            encoding:
              policy:
                contentType: application/json
      description: 'Upload dataset to the Opaque platform for encryption and upload to cloud storage. If the `chunked=true` query parameter is specified, then this endpoint expects additional form parameters for chunking as specified by Dropzone.js.

        The data file should be a CSV file with an optional header row detailing the names of the columns. If the header row is absent, it will be deduced from the associated schema file instead prior to uploading the encrypted data to the cloud.

        If the policy parameter is included in the request body, it may need to be converted to a string before being provided. For example if you are using python

        to send the requests you could use `json.loads(policy)` to convert the policy dictionary to a string.'
      parameters:
      - schema:
          type: boolean
        in: query
        name: chunked
        description: Boolean indicating if a chunked upload is occurring
      security:
      - userIdentitySecret: []
        sessionToken: []
      tags:
      - datasets
  /{version}/organization/data/upload_aws_s3:
    parameters:
    - $ref: '#/components/parameters/version'
    post:
      summary: Upload data from AWS S3
      operationId: upload_data_aws_s3
      responses:
        '200':
          description: 'OK

            - Data upload from AWS S3 successful'
          content:
            application/json:
              schema:
                $ref: ../models/OrganizationData.yaml
        '400':
          description: 'Bad Request

            - File already exists'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
        '500':
          description: 'Internal Server Error

            - Streaming from AWS S3 failed

            - Upload to provider failed'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: Name of the dataset after uploading
                policy:
                  $ref: ../models/DatumPolicy.yaml
                testDataType:
                  type: string
                  enum:
                  - synthetic
                  - mock
                  description: Type of test data to generate. Synthetic test data simulates the original data file. Mock test data is faked data that only uses the data schema.
                schemaId:
                  type: string
                bucketName:
                  type: string
                  description: Name of the data source AWS S3 bucket
                fileName:
                  type: string
                  description: Name of the data file in the AWS S3 bucket (that is, the key)
                accessKey:
                  type: string
                  description: AWS access key ID
                secretKey:
                  type: string
                  description: AWS secret access key
                description:
                  type: string
                  description: A description of the dataset
              required:
              - name
              - policy
              - testDataType
              - schemaId
              - bucketName
              - fileName
              - accessKey
              - secretKey
      tags:
      - datasets
      description: Upload dataset to the Opaque platform by streaming existing data from AWS S3.
      security:
      - userIdentitySecret: []
        sessionToken: []
  /{version}/organization/data/upload_azure_blob_storage:
    parameters:
    - $ref: '#/components/parameters/version'
    post:
      summary: Upload data from Azure Blob Storage
      operationId: upload_data_azure_blob_storage
      responses:
        '200':
          description: 'OK

            - Data upload from Azure Blob Storage successful'
          content:
            application/json:
              schema:
                $ref: ../models/OrganizationData.yaml
        '400':
          description: 'Bad Request

            - File already exists'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
        '500':
          description: 'Internal Server Error

            - Streaming from Azure Blob Storage failed

            - Upload to provider failed'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: Name of the dataset after uploading
                policy:
                  $ref: ../models/DatumPolicy.yaml
                testDataType:
                  type: string
                  enum:
                  - synthetic
                  - mock
                  description: Type of test data to generate. Synthetic test data simulates the original data file. Mock test data is faked data that only uses the data schema.
                schemaId:
                  type: string
                containerName:
                  type: string
                  description: Name of the data source Azure Blob Storage container
                blobName:
                  type: string
                  description: Name of the data file (that is, the blob) in the Azure Blob Storage container
                connectionString:
                  type: string
                  description: 'Azure Storage connection string

                    https://learn.microsoft.com/en-us/azure/storage/common/storage-configure-connection-string'
                description:
                  type: string
                  description: A description of the dataset
              required:
              - name
              - policy
              - testDataType
              - schemaId
              - containerName
              - blobName
              - connectionString
      tags:
      - datasets
      description: Upload dataset to the Opaque platform by streaming existing data from Azure Blob Storage.
      security:
      - userIdentitySecret: []
        sessionToken: []
  /{version}/organization/data/upload_azure_files:
    parameters:
    - $ref: '#/components/parameters/version'
    post:
      summary: Upload data from Azure Files
      operationId: upload_data_azure_files
      responses:
        '200':
          description: 'OK

            - Data upload from Azure Files successful'
          content:
            application/json:
              schema:
                $ref: ../models/OrganizationData.yaml
        '400':
          description: 'Bad Request

            - File already exists'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
        '500':
          description: 'Internal Server Error

            - Streaming from Azure Files failed

            - Upload to provider failed'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: Name of the dataset after uploading
                policy:
                  $ref: ../models/DatumPolicy.yaml
                testDataType:
                  type: string
                  enum:
                  - synthetic
                  - mock
                  description: Type of test data to generate. Synthetic test data simulates the original data file. Mock test data is faked data that only uses the data schema.
                schemaId:
                  type: string
                shareName:
                  type: string
                  description: Name of the Azure Files file share
                filePath:
                  type: string
                  description: Path of the file on Azure Files
                connectionString:
                  type: string
                  description: 'Azure Storage connection string

                    https://learn.microsoft.com/en-us/azure/storage/common/storage-configure-connection-string'
                description:
                  type: string
                  description: A description of the dataset
              required:
              - name
              - policy
              - testDataType
              - schemaId
              - shareName
              - filePath
              - connectionString
      tags:
      - datasets
      description: Upload dataset to the Opaque platform by streaming existing data from Azure Files.
      security:
      - userIdentitySecret: []
        sessionToken: []
  /{version}/organization/data/upload_google_cloud_storage:
    parameters:
    - $ref: '#/components/parameters/version'
    post:
      summary: Upload data from Google Cloud Storage
      operationId: upload_data_google_cloud_storage
      responses:
        '200':
          description: 'OK

            - Data upload from Google Cloud Storage successful'
          content:
            application/json:
              schema:
                $ref: ../models/OrganizationData.yaml
        '400':
          description: 'Bad Request

            - File already exists'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
        '500':
          description: 'Internal Server Error

            - Streaming from Google Cloud Storage failed

            - Upload to provider failed'
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: Name of the dataset after uploading
                policy:
                  $ref: ../models/DatumPolicy.yaml
                testDataType:
                  type: string
                  enum:
                  - synthetic
                  - mock
                  description: Type of test data to generate. Synthetic test data simulates the original data file. Mock test data is faked data that only uses the data schema.
                schemaId:
                  type: string
                bucketName:
                  type: string
                  description: Name of the bucket containing data file
                objectName:
                  type: string
                  description: Name of the data object
                credentialsJson:
                  type: string
                  description: 'Google application credential JSON

                    https://cloud.google.com/docs/authentication/application-default-credentials'
                description:
                  type: string
                  description: A description of the dataset
              required:
              - name
              - policy
              - testDataType
              - schemaId
              - bucketName
              - objectName
              - credentialsJson
      tags:
      - datasets
      description: Upload dataset to the Opaque platform by streaming existing data from Google Cloud Storage.
      security:
      - userIdentitySecret: []
        sessionToken: []
  /{version}/organization/data/download:
    parameters:
    - $ref: '#/components/parameters/version'
    - schema:
        type: string
      name: dataset-path
      in: query
      required: true
    - schema:
        type: string
      name: data-store-config-uuid
      in: query
      required: true
    get:
      summary: Download data
      tags:
      - datasets
      responses:
        '200':
          description: OK
          content:
            text/plain:
              schema:
                format: binary
                type: string
                description: Data as a CSV file
          headers:
            Set-Cookie:
              schema:
                type: string
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: ../models/Error.yaml
      operationId: download_data
      security:
      - sessionTokenCookie: []
        userIdentitySecret: []
        refreshTokenCookie: []
components:
  parameters:
    version:
      in: path
      name: version
      schema:
        type: string
        default: v1.2
        example: v1.2
      description: Version of the API to call
      required: true
  securitySchemes:
    sessionToken:
      type: http
      scheme: bearer
      description: The bearer token is obtained from the `/login` and `/register` endpoints.
    userIdentitySecret:
      name: userIdentitySecret
      type: apiKey
      in: cookie
      description: A binary blob derived from a user's passkey. It can be obtained from the `/login` and `/register` endpoints.
    sessionTokenCookie:
      name: sessionTokenCookie
      type: apiKey
      in: cookie
    refreshTokenCookie:
      name: refreshTokenCookie
      type: apiKey
      in: cookie
x-origin: origin
x-extension-with: x-extension-with