Hugging Face Files & Metadata API

openapi: 3.2.0
info:
  title: Hugging Face Dataset Viewer Files & Metadata 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: Files & Metadata
  description: Parquet files, size, statistics, and metadata
paths:
  /parquet:
    get:
      summary: List Parquet Files
      description: Get the list of a dataset's files converted to Parquet format. Datasets are auto-converted to Parquet on the Hub for efficient data access.
      operationId: getParquetFiles
      tags:
      - Files & Metadata
      parameters:
      - name: dataset
        in: query
        required: true
        description: The dataset ID
        schema:
          type: string
        example: squad
      responses:
        '200':
          description: List of Parquet files
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ParquetResponse'
              examples:
                Getparquetfiles200Example:
                  summary: Default getParquetFiles 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
                    partial: true
        '404':
          description: Dataset not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Getparquetfiles404Example:
                  summary: Default getParquetFiles 404 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
  /size:
    get:
      summary: Get Dataset Size
      description: Get size information for a dataset including the number of rows and size in bytes for the full dataset and for each subset and split.
      operationId: getDatasetSize
      tags:
      - Files & Metadata
      parameters:
      - name: dataset
        in: query
        required: true
        description: The dataset ID
        schema:
          type: string
        example: squad
      responses:
        '200':
          description: Dataset size information
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SizeResponse'
              examples:
                Getdatasetsize200Example:
                  summary: Default getDatasetSize 200 response
                  x-microcks-default: true
                  value:
                    size:
                      dataset:
                        dataset: example_value
                        num_bytes_original_files: 10
                        num_bytes_parquet_files: 10
                        num_bytes_memory: 10
                        num_rows: 10
                      configs:
                      - dataset: example_value
                        config: example_value
                        num_bytes_original_files: 10
                        num_bytes_parquet_files: 10
                        num_bytes_memory: 10
                        num_rows: 10
                        num_columns: 10
                      splits:
                      - dataset: example_value
                        config: example_value
                        split: example_value
                        num_bytes_parquet_files: 10
                        num_bytes_memory: 10
                        num_rows: 10
                        num_columns: 10
                    partial: true
        '404':
          description: Dataset not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Getdatasetsize404Example:
                  summary: Default getDatasetSize 404 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
  /statistics:
    get:
      summary: Get Dataset Statistics
      description: Get descriptive statistics for columns in a dataset split including distributions, counts, means, and other summary metrics.
      operationId: getStatistics
      tags:
      - Files & Metadata
      parameters:
      - name: dataset
        in: query
        required: true
        description: The dataset ID
        schema:
          type: string
        example: example_value
      - name: config
        in: query
        required: true
        description: The subset (configuration) name
        schema:
          type: string
        example: example_value
      - name: split
        in: query
        required: true
        description: The split name
        schema:
          type: string
        example: example_value
      responses:
        '200':
          description: Column statistics
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StatisticsResponse'
              examples:
                Getstatistics200Example:
                  summary: Default getStatistics 200 response
                  x-microcks-default: true
                  value:
                    num_examples: 10
                    statistics:
                    - column_name: example_value
                      column_type: example_value
                      column_statistics:
                        nan_count: 10
                        nan_proportion: 42.5
                        min: example_value
                        max: example_value
                        mean: 42.5
                        median: 42.5
                        std: 42.5
                        histogram: {}
                        frequencies: {}
                    partial: true
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Getstatistics400Example:
                  summary: Default getStatistics 400 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
  /croissant:
    get:
      summary: Get Croissant Metadata
      description: Get Croissant (schema.org/Dataset compatible) metadata for a dataset. Croissant is a metadata format for ML datasets based on schema.org.
      operationId: getCroissantMetadata
      tags:
      - Files & Metadata
      parameters:
      - name: dataset
        in: query
        required: true
        description: The dataset ID
        schema:
          type: string
        example: squad
      responses:
        '200':
          description: Croissant metadata in JSON-LD format
          content:
            application/json:
              schema:
                type: object
                description: Croissant metadata following schema.org/Dataset vocabulary
                properties:
                  '@context':
                    type: object
                  '@type':
                    type: string
                    const: sc:Dataset
                  name:
                    type: string
                  description:
                    type: string
                  url:
                    type: string
                    format: uri
                  distribution:
                    type: array
                    items:
                      type: object
                  recordSet:
                    type: array
                    items:
                      type: object
              examples:
                Getcroissantmetadata200Example:
                  summary: Default getCroissantMetadata 200 response
                  x-microcks-default: true
                  value:
                    '@context': example_value
                    '@type': example_value
                    name: Example Title
                    description: A sample description.
                    url: https://www.example.com
                    distribution:
                    - {}
                    recordSet:
                    - {}
        '404':
          description: Dataset not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
              examples:
                Getcroissantmetadata404Example:
                  summary: Default getCroissantMetadata 404 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: []
    StatisticsResponse:
      type: object
      properties:
        num_examples:
          type: integer
          description: Total number of examples analyzed
          example: 10
        statistics:
          type: array
          items:
            type: object
            properties:
              column_name:
                type: string
                description: Name of the column
              column_type:
                type: string
                description: Data type of the column
              column_statistics:
                type: object
                description: Statistics for the column
                properties:
                  nan_count:
                    type: integer
                  nan_proportion:
                    type: number
                    format: float
                  min:
                    oneOf:
                    - type: number
                    - type: string
                  max:
                    oneOf:
                    - type: number
                    - type: string
                  mean:
                    type: number
                    format: float
                  median:
                    type: number
                    format: float
                  std:
                    type: number
                    format: float
                  histogram:
                    type: object
                    properties:
                      hist:
                        type: array
                        items:
                          type: integer
                      bin_edges:
                        type: array
                        items:
                          type: number
                  frequencies:
                    type: array
                    items:
                      type: object
                      properties:
                        value:
                          type: string
                        count:
                          type: integer
                        proportion:
                          type: number
                          format: float
          example: []
        partial:
          type: boolean
          example: true
    SizeResponse:
      type: object
      properties:
        size:
          type: object
          properties:
            dataset:
              type: object
              properties:
                dataset:
                  type: string
                num_bytes_original_files:
                  type: integer
                  description: Original files size in bytes
                num_bytes_parquet_files:
                  type: integer
                  description: Parquet files size in bytes
                num_bytes_memory:
                  type: integer
                  description: Estimated in-memory size in bytes
                num_rows:
                  type: integer
                  description: Total number of rows
            configs:
              type: array
              items:
                type: object
                properties:
                  dataset:
                    type: string
                  config:
                    type: string
                  num_bytes_original_files:
                    type: integer
                  num_bytes_parquet_files:
                    type: integer
                  num_bytes_memory:
                    type: integer
                  num_rows:
                    type: integer
                  num_columns:
                    type: integer
            splits:
              type: array
              items:
                type: object
                properties:
                  dataset:
                    type: string
                  config:
                    type: string
                  split:
                    type: string
                  num_bytes_parquet_files:
                    type: integer
                  num_bytes_memory:
                    type: integer
                  num_rows:
                    type: integer
                  num_columns:
                    type: integer
          example: example_value
        partial:
          type: boolean
          example: true
    ParquetResponse:
      type: object
      properties:
        parquet_files:
          type: array
          items:
            type: object
            properties:
              dataset:
                type: string
                description: Dataset ID
              config:
                type: string
                description: Subset name
              split:
                type: string
                description: Split name
              url:
                type: string
                format: uri
                description: Direct download URL for the Parquet file
              filename:
                type: string
                description: Parquet file name
              size:
                type: integer
                description: File size in bytes
          example: []
        partial:
          type: boolean
          description: Whether only partial data was converted
          example: true
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: HF Token
      description: Optional Hugging Face API token. Required for private and gated datasets.