LLMWhisperer Highlights API

openapi: 3.0.1
info:
  title: LLMWhisperer Extraction Highlights API
  description: 'LLMWhisperer (by Unstract / Zipstack) is a document-to-text extraction API that converts PDFs, scanned documents, and images into clean, layout-preserving text ready for large language models. The v2 API is asynchronous: submit a document to POST /whisper, poll GET /whisper-status, then fetch the result with GET /whisper-retrieve. GET /highlights returns per-line bounding-box coordinates and /whisper-manage-callback manages webhook callbacks. All requests authenticate with the unstract-key header.'
  termsOfService: https://unstract.com/terms-of-service/
  contact:
    name: Unstract Support
    url: https://unstract.com/llmwhisperer/
  version: '2.0'
servers:
- url: https://llmwhisperer-api.us-central.unstract.com/api/v2
  description: US Central region
- url: https://llmwhisperer-api.eu-west.unstract.com/api/v2
  description: EU West region
security:
- unstractKey: []
tags:
- name: Highlights
paths:
  /highlights:
    get:
      operationId: highlights
      tags:
      - Highlights
      summary: Retrieve per-line bounding-box coordinates
      description: Returns bounding-box metadata for the requested lines so callers can highlight extracted text in the source document. Requires the whisper job to have been submitted with add_line_nos enabled.
      parameters:
      - name: whisper_hash
        in: query
        required: true
        description: The whisper hash returned when the whisper job was started.
        schema:
          type: string
      - name: lines
        in: query
        required: true
        description: Lines to retrieve, e.g. "1-5,7,21-".
        schema:
          type: string
      responses:
        '200':
          description: Map of line number to bounding-box metadata.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HighlightsResponse'
        '400':
          description: Bad request.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    Error:
      type: object
      properties:
        message:
          type: string
    HighlightLine:
      type: object
      properties:
        base_y:
          type: integer
        base_y_percent:
          type: number
        height:
          type: integer
        height_percent:
          type: number
        page:
          type: integer
        page_height:
          type: integer
        raw:
          type: array
          description: '[page_no, y, height, page_height]'
          items:
            type: integer
    HighlightsResponse:
      type: object
      additionalProperties:
        $ref: '#/components/schemas/HighlightLine'
  securitySchemes:
    unstractKey:
      type: apiKey
      in: header
      name: unstract-key
      description: LLMWhisperer API key passed in the unstract-key request header.