Qubrid AI Datasets API

openapi: 3.1.0
info:
  title: Qubrid AI Compute Chat Completions Datasets API
  description: The Qubrid AI Compute API provides programmatic access to GPU cloud infrastructure including NVIDIA H100, H200, and B200 accelerators. Developers can provision and manage GPU instances for AI and machine learning workloads through API calls. The service supports on-demand compute for training, fine-tuning, and batch inference jobs, with usage-based billing and enterprise features such as team collaboration and usage tracking. Instances can be accessed via SSH, Jupyter notebooks, or Visual Studio Code, and support quick-deploy templates for popular frameworks including PyTorch, TensorFlow, ComfyUI, n8n, and Langflow.
  version: 1.0.0
  contact:
    name: Qubrid AI Support
    url: https://www.qubrid.com/contact
  termsOfService: https://www.qubrid.com/terms-of-service
servers:
- url: https://platform.qubrid.com/api/v1
  description: Qubrid AI Compute Production Server
security:
- bearerAuth: []
tags:
- name: Datasets
  description: Upload and manage CSV training datasets used for fine-tuning models. Datasets must be in CSV format with columns appropriate for the selected task type (QA or non-QA).
paths:
  /fine-tuning/datasets:
    get:
      operationId: listDatasets
      summary: List training datasets
      description: Returns a list of training datasets uploaded by the authenticated user. Datasets are in CSV format and can be used for fine-tuning jobs.
      tags:
      - Datasets
      responses:
        '200':
          description: Successfully retrieved the list of datasets.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DatasetList'
        '401':
          description: Authentication failed due to a missing or invalid bearer token.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
    post:
      operationId: uploadDataset
      summary: Upload a training dataset
      description: Uploads a new CSV training dataset for use in fine-tuning jobs. The dataset must be in CSV format; other file extensions are not supported and will return an error. The CSV should contain columns appropriate for the intended task type.
      tags:
      - Datasets
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/UploadDatasetRequest'
      responses:
        '201':
          description: Successfully uploaded the training dataset.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '400':
          description: The uploaded file was not in CSV format or was malformed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Authentication failed due to a missing or invalid bearer token.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
  /fine-tuning/datasets/{dataset_id}:
    get:
      operationId: getDataset
      summary: Retrieve a dataset
      description: Returns details about a specific training dataset including its name, size, row count, and upload timestamp.
      tags:
      - Datasets
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      responses:
        '200':
          description: Successfully retrieved the dataset details.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '401':
          description: Authentication failed due to a missing or invalid bearer token.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: The specified dataset was not found.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
    delete:
      operationId: deleteDataset
      summary: Delete a dataset
      description: Deletes a training dataset. Datasets that are currently in use by a running fine-tuning job cannot be deleted.
      tags:
      - Datasets
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      responses:
        '204':
          description: Successfully deleted the dataset.
        '401':
          description: Authentication failed due to a missing or invalid bearer token.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: The specified dataset was not found.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '409':
          description: The dataset is currently in use by a running fine-tuning job and cannot be deleted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    UploadDatasetRequest:
      type: object
      required:
      - file
      properties:
        file:
          type: string
          format: binary
          description: The CSV training dataset file. Only CSV format is accepted; other file extensions will return an error.
        name:
          type: string
          description: An optional display name for the dataset.
          maxLength: 256
    ErrorResponse:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              description: A human-readable error message describing what went wrong.
            type:
              type: string
              description: The type of error that occurred.
            code:
              type: string
              description: A machine-readable error code.
    Dataset:
      type: object
      properties:
        id:
          type: string
          description: The unique identifier of the dataset.
        name:
          type: string
          description: The original filename of the uploaded dataset.
        size_bytes:
          type: integer
          description: The size of the dataset file in bytes.
        row_count:
          type: integer
          description: The number of rows in the CSV dataset.
        columns:
          type: array
          items:
            type: string
          description: The column names found in the CSV dataset.
        created_at:
          type: string
          format: date-time
          description: The timestamp when the dataset was uploaded.
    DatasetList:
      type: object
      properties:
        data:
          type: array
          description: A list of dataset objects.
          items:
            $ref: '#/components/schemas/Dataset'
  parameters:
    DatasetId:
      name: dataset_id
      in: path
      required: true
      description: The unique identifier of the training dataset.
      schema:
        type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: QUBRID_API_KEY
      description: Qubrid AI API key passed as a bearer token in the Authorization header. Obtain your API key from the Qubrid AI platform dashboard at https://platform.qubrid.com.
externalDocs:
  description: Qubrid AI Documentation
  url: https://docs.platform.qubrid.com