kdeps-components-ocr_image

version: 1.0.2
requires:
    schemas/v1: ""
    tools/ocr_image: ""
files:
    component.yaml: |
        apiVersion: kdeps.io/v1
        kind: Component
        metadata:
          name: ocr_image
          description: Extract text from an image with tesseract through the kdeps API
          version: "1.0.2"
        interface:
          inputs:
            - name: file
              type: string
              required: true
              description: Absolute path to the image (png, jpg/jpeg, tiff, bmp, gif). PDFs with a text layer go through load_document instead.
            - name: language
              type: string
              default: eng
              description: 'tesseract -l value, e.g. eng or eng+fra'
            - name: psm
              type: integer
              default: 3
              description: 'tesseract --psm page segmentation mode (3 = fully automatic)'
            - name: oem
              type: integer
              default: 3
              description: 'tesseract --oem engine mode (3 = whatever is available)'
          # body is the extracted text. A missing tesseract is an error. The HTTP envelope stays inside the call.
          output: "{{ output('call').body }}"
        resources:
          - actionId: call
            name: OCR
            httpClient:
              method: POST
              # In-process host. The HTTP executor calls the handler without dialing.
              url: http://kdeps.api/apis/tools.kdeps.io/v1/tools/ocr_image/call
              headers:
                Content-Type: application/json
              failOnError: true
              timeout: 120s
              data:
                file: "{{ get('ocr_image.file') }}"
                language: "{{ get('ocr_image.language') }}"
                psm: "{{ get('ocr_image.psm') }}"
                oem: "{{ get('ocr_image.oem') }}"