Xceptor Extraction API

openapi: 3.1.0
info:
  title: Xceptor Document Upload Authentication Extraction API
  description: API for uploading and processing documents through Xceptor's data extraction engine. Supports intelligent document processing using NLP, OCR, and generative AI to transform unstructured documents including PDFs, emails, spreadsheets, and handwritten forms into structured, trusted data. The API handles document ingestion, classification, field and table extraction, and confidence-scored output for financial services use cases such as trade confirmations, tax documents, loan notices, and client onboarding materials.
  version: '1.0'
  contact:
    name: Xceptor API Support
    url: https://www.xceptor.com/support
    email: api-support@xceptor.com
  termsOfService: https://www.xceptor.com/legal-tcs
servers:
- url: https://api.xceptor.com/v1
  description: Production Server
security:
- bearerAuth: []
tags:
- name: Extraction
  description: Operations for triggering and monitoring document data extraction using Xceptor's AI-powered processing engine.
paths:
  /documents/{documentId}/extraction:
    get:
      operationId: getDocumentExtraction
      summary: Xceptor Get extraction results
      description: Retrieves the data extraction results for a processed document. The results include all extracted fields and tables with their values, locations in the source document, and AI confidence scores. Fields with confidence scores below the configured threshold are flagged for manual review.
      tags:
      - Extraction
      parameters:
      - $ref: '#/components/parameters/DocumentIdParam'
      responses:
        '200':
          description: Extraction results
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionResult'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '404':
          description: Document not found or extraction not yet available
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
    post:
      operationId: triggerExtraction
      summary: Xceptor Trigger document extraction
      description: Manually triggers the data extraction process for a document that has been uploaded but not yet processed, or re-triggers extraction with a different template. The extraction runs asynchronously and results can be retrieved once the document status transitions to extracted.
      tags:
      - Extraction
      parameters:
      - $ref: '#/components/parameters/DocumentIdParam'
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                template_id:
                  type: string
                  format: uuid
                  description: The extraction template to use. Overrides the previously assigned template if one exists.
      responses:
        '202':
          description: Extraction triggered
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Document'
        '400':
          description: Document is not in a valid state for extraction
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '404':
          description: Document not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    ExtractedTable:
      type: object
      description: A table extracted from a document with its rows and column headers
      properties:
        name:
          type: string
          description: The name or label of the extracted table
        headers:
          type: array
          items:
            type: string
          description: The column headers of the extracted table
        rows:
          type: array
          items:
            type: array
            items:
              description: A cell value in the table row
          description: The data rows of the extracted table
        confidence:
          type: number
          description: The confidence score for the table extraction (0.0 to 1.0)
          minimum: 0.0
          maximum: 1.0
        page_number:
          type: integer
          description: The page number where the table was found
          minimum: 1
    Error:
      type: object
      description: An error response from the Xceptor API
      properties:
        code:
          type: string
          description: A machine-readable error code
        message:
          type: string
          description: A human-readable description of the error
        details:
          type: object
          description: Additional error details when available
          additionalProperties: true
    BoundingBox:
      type: object
      description: The bounding box coordinates of an extracted element on the document page, in normalized coordinates (0.0 to 1.0).
      properties:
        x:
          type: number
          description: The x-coordinate of the top-left corner
          minimum: 0.0
          maximum: 1.0
        y:
          type: number
          description: The y-coordinate of the top-left corner
          minimum: 0.0
          maximum: 1.0
        width:
          type: number
          description: The width of the bounding box
          minimum: 0.0
          maximum: 1.0
        height:
          type: number
          description: The height of the bounding box
          minimum: 0.0
          maximum: 1.0
    ExtractedField:
      type: object
      description: A single field extracted from a document with its value and metadata
      properties:
        name:
          type: string
          description: The name of the extracted field
        value:
          description: The extracted value of the field
        data_type:
          type: string
          description: The data type of the extracted value
          enum:
          - string
          - number
          - date
          - currency
          - boolean
        confidence:
          type: number
          description: The confidence score for this extraction (0.0 to 1.0)
          minimum: 0.0
          maximum: 1.0
        page_number:
          type: integer
          description: The page number where the field was found
          minimum: 1
        bounding_box:
          $ref: '#/components/schemas/BoundingBox'
        requires_review:
          type: boolean
          description: Whether this field requires manual review due to low confidence
    Document:
      type: object
      description: A document that has been uploaded to the Xceptor platform for intelligent data extraction and processing.
      properties:
        id:
          type: string
          format: uuid
          description: The unique identifier of the document
        filename:
          type: string
          description: The original filename of the uploaded document
        content_type:
          type: string
          description: The MIME type of the uploaded document
        file_size:
          type: integer
          description: The file size in bytes
          minimum: 0
        status:
          type: string
          description: The current processing status of the document
          enum:
          - uploaded
          - classifying
          - classified
          - extracting
          - extracted
          - validated
          - failed
        classification:
          type: string
          description: The document type classification determined by AI or assigned by template
        template_id:
          type: string
          format: uuid
          description: The extraction template used for this document
        confidence_score:
          type: number
          description: The overall confidence score for the classification (0.0 to 1.0)
          minimum: 0.0
          maximum: 1.0
        page_count:
          type: integer
          description: The number of pages in the document
          minimum: 1
        uploaded_at:
          type: string
          format: date-time
          description: The date and time the document was uploaded
        processed_at:
          type: string
          format: date-time
          description: The date and time extraction was completed
        metadata:
          type: object
          description: Custom metadata associated with the document
          additionalProperties: true
    ExtractionResult:
      type: object
      description: The data extraction results for a processed document, including all extracted fields, tables, and their confidence scores.
      properties:
        document_id:
          type: string
          format: uuid
          description: The identifier of the source document
        template_id:
          type: string
          format: uuid
          description: The extraction template that was applied
        classification:
          type: string
          description: The classified document type
        extraction_method:
          type: string
          description: The AI method used for extraction
          enum:
          - ocr
          - nlp
          - generative_ai
          - template_based
          - hybrid
        overall_confidence:
          type: number
          description: The overall confidence score for the extraction (0.0 to 1.0)
          minimum: 0.0
          maximum: 1.0
        fields:
          type: array
          items:
            $ref: '#/components/schemas/ExtractedField'
          description: The list of extracted fields with values and confidence scores
        tables:
          type: array
          items:
            $ref: '#/components/schemas/ExtractedTable'
          description: The list of extracted tables
        requires_review:
          type: boolean
          description: Whether any extracted values fall below the confidence threshold and require manual review
        extracted_at:
          type: string
          format: date-time
          description: The date and time the extraction was performed
  parameters:
    DocumentIdParam:
      name: documentId
      in: path
      required: true
      description: The unique identifier of the document
      schema:
        type: string
        format: uuid
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: OAuth2 access token obtained via the client credentials flow. Include as a Bearer token in the Authorization header.
externalDocs:
  description: Xceptor Document Upload API Documentation
  url: https://docs.xceptor.com/api/documents