Apache OpenNLP Tokenization API

openapi: 3.0.3
info:
  title: Apache OpenNLP Tools Chunking Tokenization API
  description: Apache OpenNLP is a machine learning based toolkit for processing natural language text, supporting tokenization, sentence segmentation, POS tagging, named entity extraction, chunking, parsing, and coreference resolution. This API represents the REST-accessible surface of the OpenNLP toolkit.
  version: 2.5.8
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
  contact:
    url: https://opennlp.apache.org/
servers:
- url: https://{host}/opennlp
  description: Apache OpenNLP REST service
  variables:
    host:
      default: localhost:8080
tags:
- name: Tokenization
paths:
  /tokenize:
    post:
      operationId: tokenize
      summary: Apache OpenNLP Tokenize Text
      description: Segment input text into individual tokens (words, punctuation) using the tokenizer model.
      tags:
      - Tokenization
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TextRequest'
      responses:
        '200':
          description: Tokenization result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TokenizationResult'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    TextRequest:
      type: object
      required:
      - text
      properties:
        text:
          type: string
          description: Input text to process
          example: Pierre Vinken, 61 years old, will join the board as a nonexecutive director Nov. 29.
        language:
          type: string
          description: ISO-639-3 language code hint
          example: eng
        modelId:
          type: string
          description: Specific model to use (optional)
          example: en-sent.bin
    TokenizationResult:
      type: object
      properties:
        tokens:
          type: array
          items:
            type: string
          description: Extracted tokens
          example:
          - Pierre
          - Vinken
          - ','
          - '61'
          - years
          - old
        spans:
          type: array
          items:
            $ref: '#/components/schemas/Span'
        probabilities:
          type: array
          items:
            type: number
          description: Confidence for each token boundary
    Span:
      type: object
      properties:
        start:
          type: integer
          description: Start character offset
          example: 0
        end:
          type: integer
          description: End character offset (exclusive)
          example: 13
        type:
          type: string
          description: Span type if applicable
          example: person
x-generated-from: documentation