Hugging Face Dataset Info API

openapi: 3.2.0
info:
  title: Hugging Face Dataset Viewer Dataset Info API
  description: Query and visualize datasets stored on the Hugging Face Hub through a lightweight REST API. Get dataset splits, preview rows, search and filter data, access Parquet files, retrieve size statistics, and obtain Croissant metadata - all without downloading the entire dataset.
  version: 1.0.0
  termsOfService: https://huggingface.co/terms-of-service
  contact:
    name: Hugging Face Support
    url: https://huggingface.co/support
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://datasets-server.huggingface.co
  description: Hugging Face Dataset Viewer production server
security:
- {}
- bearerAuth: []
tags:
- name: Dataset Info
  description: Dataset validity and structure endpoints
paths:
  /is-valid:
    get:
      summary: Check Dataset Validity
      description: Check whether a specific dataset is valid and processed by the Dataset Viewer. Returns availability status for preview, viewer, search, filter, and statistics features.
      operationId: isValid
      tags:
      - Dataset Info
      parameters:
      - name: dataset
        in: query
        required: true
        description: The dataset ID on the Hugging Face Hub
        schema:
          type: string
        example: cornell-movie-review-data/rotten_tomatoes
      responses:
        '200':
          description: Dataset validity status
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidityResponse'
              examples:
                Isvalid200Example:
                  summary: Default isValid 200 response
                  x-microcks-default: true
                  value:
                    preview: true
                    viewer: true
                    search: true
                    filter: true
                    statistics: true
        '404':
          description: Dataset not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Isvalid404Example:
                  summary: Default isValid 404 response
                  x-microcks-default: true
                  value:
                    error: example_value
                    cause_exception: example_value
                    cause_message: example_value
                    cause_traceback:
                    - example_value
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Isvalid500Example:
                  summary: Default isValid 500 response
                  x-microcks-default: true
                  value:
                    error: example_value
                    cause_exception: example_value
                    cause_message: example_value
                    cause_traceback:
                    - example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /splits:
    get:
      summary: Get Dataset Splits
      description: Get the list of subsets (configurations) and splits for a dataset. A dataset can have multiple subsets, each with different splits (e.g., train, test, validation).
      operationId: getSplits
      tags:
      - Dataset Info
      parameters:
      - name: dataset
        in: query
        required: true
        description: The dataset ID on the Hugging Face Hub
        schema:
          type: string
        example: squad
      responses:
        '200':
          description: List of subsets and splits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SplitsResponse'
              examples:
                Getsplits200Example:
                  summary: Default getSplits 200 response
                  x-microcks-default: true
                  value:
                    splits:
                    - dataset: example_value
                      config: example_value
                      split: example_value
                    pending:
                    - {}
                    failed:
                    - {}
        '404':
          description: Dataset not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Getsplits404Example:
                  summary: Default getSplits 404 response
                  x-microcks-default: true
                  value:
                    error: example_value
                    cause_exception: example_value
                    cause_message: example_value
                    cause_traceback:
                    - example_value
        '500':
          description: Processing error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Getsplits500Example:
                  summary: Default getSplits 500 response
                  x-microcks-default: true
                  value:
                    error: example_value
                    cause_exception: example_value
                    cause_message: example_value
                    cause_traceback:
                    - example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    Error:
      type: object
      properties:
        error:
          type: string
          description: Error message
          example: example_value
        cause_exception:
          type: string
          description: Underlying exception type
          example: example_value
        cause_message:
          type: string
          description: Underlying exception message
          example: example_value
        cause_traceback:
          type: array
          items:
            type: string
          description: Stack trace (only in development)
          example: []
    SplitsResponse:
      type: object
      properties:
        splits:
          type: array
          items:
            type: object
            properties:
              dataset:
                type: string
                description: Dataset ID
              config:
                type: string
                description: Subset (configuration) name
              split:
                type: string
                description: Split name
                example: train
          example: []
        pending:
          type: array
          items:
            type: object
          example: []
        failed:
          type: array
          items:
            type: object
          example: []
    ValidityResponse:
      type: object
      properties:
        preview:
          type: boolean
          description: Whether preview (first rows) is available
          example: true
        viewer:
          type: boolean
          description: Whether the full viewer is available
          example: true
        search:
          type: boolean
          description: Whether full-text search is available
          example: true
        filter:
          type: boolean
          description: Whether filtering is available
          example: true
        statistics:
          type: boolean
          description: Whether statistics are available
          example: true
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: HF Token
      description: Optional Hugging Face API token. Required for private and gated datasets.