Hugging Face Datasets API

openapi: 3.1.0
info:
  title: Hugging Face Dataset Viewer Audio Datasets 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: Datasets
  description: Operations for managing and querying datasets on the Hub
paths:
  /datasets:
    get:
      summary: List Datasets on the Hub
      description: List and search datasets hosted on the Hugging Face Hub. Supports filtering by author, tags, and full-text search.
      operationId: listDatasets
      tags:
      - Datasets
      security: []
      parameters:
      - name: search
        in: query
        description: Full-text search query to filter datasets
        schema:
          type: string
        example: example_value
      - name: author
        in: query
        description: Filter by dataset author or organization
        schema:
          type: string
        example: example_value
      - name: filter
        in: query
        description: Filter by tags (comma-separated)
        schema:
          type: string
        example: example_value
      - name: sort
        in: query
        description: Property to sort results by
        schema:
          type: string
          enum:
          - lastModified
          - downloads
          - likes
          - createdAt
        example: lastModified
      - name: direction
        in: query
        description: Sort direction
        schema:
          type: string
          enum:
          - '-1'
          - '1'
        example: '-1'
      - name: limit
        in: query
        description: Number of results to return
        schema:
          type: integer
          default: 30
          maximum: 1000
        example: 10
      - name: full
        in: query
        description: Whether to return full dataset information
        schema:
          type: boolean
          default: false
        example: true
      responses:
        '200':
          description: List of datasets matching the query
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/DatasetSummary'
              examples:
                Listdatasets200Example:
                  summary: Default listDatasets 200 response
                  x-microcks-default: true
                  value:
                  - _id: '500123'
                    id: abc123
                    author: example_value
                    sha: example_value
                    lastModified: '2026-01-15T10:30:00Z'
                    private: true
                    gated: true
                    disabled: true
                    tags:
                    - example_value
                    downloads: 10
                    likes: 10
                    createdAt: '2026-01-15T10:30:00Z'
                    description: A sample description.
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /datasets/{repo_id}:
    get:
      summary: Get Dataset Information
      description: Get detailed information about a specific dataset.
      operationId: getDataset
      tags:
      - Datasets
      security: []
      parameters:
      - name: repo_id
        in: path
        required: true
        description: The dataset repository ID
        schema:
          type: string
        example: squad
      responses:
        '200':
          description: Detailed dataset information
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DatasetInfo'
              examples:
                Getdataset200Example:
                  summary: Default getDataset 200 response
                  x-microcks-default: true
                  value: {}
        '404':
          description: Dataset not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Getdataset404Example:
                  summary: Default getDataset 404 response
                  x-microcks-default: true
                  value:
                    error: example_value
                    statusCode: 10
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /datasets/{repo_id}/parquet:
    get:
      summary: Get Dataset Parquet Files
      description: Get the list of auto-converted Parquet files for a dataset.
      operationId: getDatasetParquet
      tags:
      - Datasets
      security: []
      parameters:
      - name: repo_id
        in: path
        required: true
        schema:
          type: string
        example: '500123'
      responses:
        '200':
          description: List of Parquet file URLs
          content:
            application/json:
              schema:
                type: object
                properties:
                  parquet_files:
                    type: array
                    items:
                      type: object
                      properties:
                        dataset:
                          type: string
                        config:
                          type: string
                        split:
                          type: string
                        url:
                          type: string
                          format: uri
                        filename:
                          type: string
                        size:
                          type: integer
              examples:
                Getdatasetparquet200Example:
                  summary: Default getDatasetParquet 200 response
                  x-microcks-default: true
                  value:
                    parquet_files:
                    - dataset: example_value
                      config: example_value
                      split: example_value
                      url: https://www.example.com
                      filename: example_value
                      size: 10
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /datasets-tags-by-type:
    get:
      summary: List Dataset Tags Grouped by Type
      description: Get all available dataset tags organized by type (task_categories, language, size_categories, etc.).
      operationId: listDatasetTags
      tags:
      - Datasets
      security: []
      responses:
        '200':
          description: Tags grouped by type
          content:
            application/json:
              schema:
                type: object
                additionalProperties:
                  type: array
                  items:
                    type: object
                    properties:
                      id:
                        type: string
                      label:
                        type: string
              examples:
                Listdatasettags200Example:
                  summary: Default listDatasetTags 200 response
                  x-microcks-default: true
                  value: {}
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    Error:
      type: object
      properties:
        error:
          type: string
          description: Error message
          example: example_value
        statusCode:
          type: integer
          description: HTTP status code
          example: 10
    DatasetSummary:
      type: object
      properties:
        _id:
          type: string
          example: '500123'
        id:
          type: string
          description: Dataset repository ID
          example: abc123
        author:
          type: string
          example: example_value
        sha:
          type: string
          example: example_value
        lastModified:
          type: string
          format: date-time
          example: '2026-01-15T10:30:00Z'
        private:
          type: boolean
          example: true
        gated:
          type: boolean
          example: true
        disabled:
          type: boolean
          example: true
        tags:
          type: array
          items:
            type: string
          example: []
        downloads:
          type: integer
          example: 10
        likes:
          type: integer
          example: 10
        createdAt:
          type: string
          format: date-time
          example: '2026-01-15T10:30:00Z'
        description:
          type: string
          example: A sample description.
    DatasetInfo:
      allOf:
      - $ref: '#/components/schemas/DatasetSummary'
      - type: object
        properties:
          siblings:
            type: array
            items:
              type: object
              properties:
                rfilename:
                  type: string
                size:
                  type: integer
          cardData:
            type: object
            description: Parsed dataset card metadata
            properties:
              language:
                type: array
                items:
                  type: string
              license:
                type: string
              task_categories:
                type: array
                items:
                  type: string
              size_categories:
                type: array
                items:
                  type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: HF Token
      description: Optional Hugging Face API token. Required for private and gated datasets.