> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hebbianrobotics.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Get the environments, objects, and actions found in a dataset.

> Returns published terms, their tiers and categories, and diversity metrics.
Use `section` to request one vocabulary section.



## OpenAPI

````yaml https://api.hebbianrobotics.com/public-openapi.json get /api/quality/vocabulary
openapi: 3.1.0
info:
  description: >-
    Use content diversity, frame-quality, and hand-activity metrics to evaluate
    robot and egocentric video datasets. Start with `GET /api/access`, then list
    available datasets with `GET /api/quality/datasets`.
  license:
    identifier: Apache-2.0
    name: Apache-2.0
  title: Robotics Data Quality API
  version: 0.0.0
servers:
  - description: Production API
    url: https://api.hebbianrobotics.com
security:
  - {}
  - bearer_token: []
tags:
  - description: >-
      Content diversity, frame-quality, and hand-activity metrics for robotics
      video data.
    name: quality
  - description: Scope and capabilities granted by a bearer token.
    name: access
paths:
  /api/quality/vocabulary:
    get:
      tags:
        - quality
      summary: Get the environments, objects, and actions found in a dataset.
      description: >-
        Returns published terms, their tiers and categories, and diversity
        metrics.

        Use `section` to request one vocabulary section.
      operationId: quality_vocabulary_route
      parameters:
        - description: Dataset ID from `GET /api/quality/datasets`.
          in: query
          name: dataset
          required: true
          schema:
            type: string
        - description: |-
            Opaque `vocabulary` token from an earlier response. Omit to use the
            latest vocabulary.
          in: query
          name: vocabulary
          required: false
          schema:
            type:
              - string
              - 'null'
        - description: Return only `environments`, `objects`, or `actions`.
          in: query
          name: section
          required: false
          schema:
            type:
              - string
              - 'null'
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QualityVocabularyResponse'
          description: Published vocabulary by section
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
          description: The dataset ID or section is invalid
        '401':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
          description: A valid bearer token is required
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
          description: The dataset, vocabulary, or a source measurement is unavailable
        '409':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
          description: >-
            The requested vocabulary is stale; omit the vocabulary token and
            retry
      security:
        - bearer_token: []
components:
  schemas:
    QualityVocabularyResponse:
      description: Published dataset vocabulary and coverage.
      properties:
        clips_analyzed:
          description: Clips included in the vocabulary analysis.
          minimum: 0
          type: integer
        dataset:
          description: Dataset ID used in the request.
          type: string
        sections:
          items:
            $ref: '#/components/schemas/QualityVocabularySectionDto'
          type: array
        segments_unassessed:
          description: Segments of footage that could not be assessed.
          minimum: 0
          type: integer
        segments_unusable:
          description: Segments whose assessment was unusable.
          minimum: 0
          type: integer
        vocabulary:
          description: >-
            Opaque vocabulary token. Matching tokens identify results from the
            same

            vocabulary measurement.
          type: string
      required:
        - dataset
        - vocabulary
        - clips_analyzed
        - segments_unassessed
        - segments_unusable
        - sections
      type: object
    ApiErrorBody:
      description: Error payload returned for handled API failures.
      properties:
        code:
          description: Machine-readable error code, e.g. `dataset_not_found`.
          type: string
        message:
          description: Human-readable message.
          type: string
      required:
        - code
        - message
      type: object
    QualityVocabularySectionDto:
      description: Vocabulary measurements for environments, objects, or actions.
      properties:
        comparable_depth_clips:
          description: Sampling depth used for `rarefied_distinct_terms`.
          minimum: 0
          type: integer
        distinct_kinds:
          description: Broader categories represented by the published terms.
          minimum: 0
          type: integer
        distinct_terms:
          description: Published terms with an assigned tier.
          minimum: 0
          type: integer
        effective_distinct_terms:
          description: >-
            Term count adjusted for repetition. Higher values indicate more
            terms

            are represented consistently.
          format: double
          type: number
        rarefied_distinct_terms:
          description: >-
            Term breadth normalized to `comparable_depth_clips`. Use this value
            for

            cross-dataset comparisons. `null` when the dataset has too few
            clips.
          format: double
          type:
            - number
            - 'null'
        section:
          description: '`environments`, `objects` or `actions`.'
          type: string
        terms:
          description: Every published term, most frequent first.
          items:
            $ref: '#/components/schemas/QualityTermDto'
          type: array
        tiers:
          description: All available tiers, including tiers with no matching terms.
          items:
            $ref: '#/components/schemas/QualityVocabularyTierDto'
          type: array
        untiered_terms:
          description: Published terms without an assigned tier.
          items:
            type: string
          type: array
      required:
        - section
        - distinct_terms
        - effective_distinct_terms
        - comparable_depth_clips
        - distinct_kinds
        - tiers
        - untiered_terms
        - terms
      type: object
    QualityTermDto:
      description: One published vocabulary term and its dataset coverage.
      properties:
        clip_count:
          description: Distinct clips containing the term.
          minimum: 0
          type: integer
        kind:
          description: Broader category. `null` when the term is its own category.
          type:
            - string
            - 'null'
        spellings:
          description: Observed wordings normalized into this term.
          items:
            type: string
          type: array
        term:
          description: Normalized term published by the API.
          type: string
        tier:
          description: Assigned tier. `null` when the term has no tier.
          type:
            - string
            - 'null'
      required:
        - term
        - clip_count
        - spellings
      type: object
    QualityVocabularyTierDto:
      description: Summary of one vocabulary tier.
      properties:
        distinct_terms:
          description: Number of published terms in this tier.
          minimum: 0
          type: integer
        example_terms:
          description: Frequent terms in this tier.
          items:
            type: string
          type: array
        label:
          description: Display name.
          type: string
        share:
          description: Share of the section's term-to-clip matches, in `[0, 1]`.
          format: double
          type: number
        tier:
          description: Stable tier or environment-category name.
          type: string
      required:
        - tier
        - label
        - distinct_terms
        - share
        - example_terms
      type: object
  securitySchemes:
    bearer_token:
      description: Bearer access token issued through OAuth 2.0 client credentials.
      scheme: bearer
      type: http

````