Class ConvertDocumentOptions.Builder

java.lang.Object
ai.docling.serve.api.convert.request.options.ConvertDocumentOptions.Builder
Enclosing class:
ConvertDocumentOptions

public static class ConvertDocumentOptions.Builder extends Object
  • Method Details

    • fromFormat

      public @NonNull ConvertDocumentOptions.Builder fromFormat(InputFormat fromFormat)
    • fromFormats

      public @NonNull ConvertDocumentOptions.Builder fromFormats(@NonNull Collection<? extends InputFormat> fromFormats)
    • clearFromFormats

      public @NonNull ConvertDocumentOptions.Builder clearFromFormats()
    • toFormat

      public @NonNull ConvertDocumentOptions.Builder toFormat(OutputFormat toFormat)
    • toFormats

      public @NonNull ConvertDocumentOptions.Builder toFormats(@NonNull Collection<? extends OutputFormat> toFormats)
    • clearToFormats

      public @NonNull ConvertDocumentOptions.Builder clearToFormats()
    • imageExportMode

      public @NonNull ConvertDocumentOptions.Builder imageExportMode(@Nullable ImageRefMode imageExportMode)
      Image export mode for the document (in case of JSON, Markdown or HTML). Allowed values: placeholder, embedded, referenced. Optional, defaults to Embedded.
      Returns:
      this.
    • doOcr

      public @NonNull ConvertDocumentOptions.Builder doOcr(@Nullable Boolean doOcr)
      If enabled, the bitmap content will be processed using OCR. Boolean. Optional, defaults to true.
      Returns:
      this.
    • forceOcr

      public @NonNull ConvertDocumentOptions.Builder forceOcr(@Nullable Boolean forceOcr)
      If enabled, replace existing text with OCR-generated text over content. Boolean. Optional, defaults to false.
      Returns:
      this.
    • ocrEngine

      public @NonNull ConvertDocumentOptions.Builder ocrEngine(@Nullable OcrEngine ocrEngine)
      The OCR engine to use. String. Allowed values: auto, easyocr, ocrmac, rapidocr, tesserocr, tesseract. Optional, defaults to easyocr.
      Returns:
      this.
    • ocrLang

      public @NonNull ConvertDocumentOptions.Builder ocrLang(String ocrLang)
    • ocrLang

      public @NonNull ConvertDocumentOptions.Builder ocrLang(@NonNull Collection<? extends String> ocrLang)
    • clearOcrLang

      public @NonNull ConvertDocumentOptions.Builder clearOcrLang()
    • pdfBackend

      public @NonNull ConvertDocumentOptions.Builder pdfBackend(@Nullable PdfBackend pdfBackend)
      The PDF backend to use. String. Allowed values: pypdfium2, dlparse_v1, dlparse_v2, dlparse_v4. Optional, defaults to dlparse_v4.
      Returns:
      this.
    • tableMode

      public @NonNull ConvertDocumentOptions.Builder tableMode(@Nullable TableFormerMode tableMode)
      Mode to use for table structure, String. Allowed values: fast, accurate. Optional, defaults to accurate.
      Returns:
      this.
    • tableCellMatching

      public @NonNull ConvertDocumentOptions.Builder tableCellMatching(@Nullable Boolean tableCellMatching)
      If true, matches table cells predictions back to PDF cells. Can break table output if PDF cells are merged across table columns. If false, let table structure model define the text cells, ignore PDF cells.
      Returns:
      this.
    • pipeline

      public @NonNull ConvertDocumentOptions.Builder pipeline(@Nullable ProcessingPipeline pipeline)
      Choose the pipeline to process PDF or image files.
      Returns:
      this.
    • pageRange

      public @NonNull ConvertDocumentOptions.Builder pageRange(Integer pageRange)
    • pageRange

      public @NonNull ConvertDocumentOptions.Builder pageRange(@NonNull Collection<? extends Integer> pageRange)
    • clearPageRange

      public @NonNull ConvertDocumentOptions.Builder clearPageRange()
    • documentTimeout

      public @NonNull ConvertDocumentOptions.Builder documentTimeout(@Nullable Duration documentTimeout)
      The timeout for processing each document, in seconds.
      Returns:
      this.
    • abortOnError

      public @NonNull ConvertDocumentOptions.Builder abortOnError(@Nullable Boolean abortOnError)
      Abort on error if enabled. Boolean. Optional, defaults to false.
      Returns:
      this.
    • doTableStructure

      public @NonNull ConvertDocumentOptions.Builder doTableStructure(@Nullable Boolean doTableStructure)
      If enabled, the table structure will be extracted. Boolean. Optional, defaults to true.
      Returns:
      this.
    • includeImages

      public @NonNull ConvertDocumentOptions.Builder includeImages(@Nullable Boolean includeImages)
      If enabled, images will be extracted from the document. Boolean. Optional, defaults to true.
      Returns:
      this.
    • imagesScale

      public @NonNull ConvertDocumentOptions.Builder imagesScale(@Nullable Double imagesScale)
      Scale factor for images. Float. Optional, defaults to 2.0.
      Returns:
      this.
    • mdPageBreakPlaceholder

      public @NonNull ConvertDocumentOptions.Builder mdPageBreakPlaceholder(@Nullable String mdPageBreakPlaceholder)
      Add this placeholder between pages in the markdown output.
      Returns:
      this.
    • doCodeEnrichment

      public @NonNull ConvertDocumentOptions.Builder doCodeEnrichment(@Nullable Boolean doCodeEnrichment)
      If enabled, perform OCR code enrichment. Boolean. Optional, defaults to false.
      Returns:
      this.
    • doFormulaEnrichment

      public @NonNull ConvertDocumentOptions.Builder doFormulaEnrichment(@Nullable Boolean doFormulaEnrichment)
      If enabled, perform formula OCR, return LaTeX code. Boolean. Optional, defaults to false.
      Returns:
      this.
    • doPictureClassification

      public @NonNull ConvertDocumentOptions.Builder doPictureClassification(@Nullable Boolean doPictureClassification)
      If enabled, classify pictures in documents. Boolean. Optional, defaults to false.
      Returns:
      this.
    • doPictureDescription

      public @NonNull ConvertDocumentOptions.Builder doPictureDescription(@Nullable Boolean doPictureDescription)
      If enabled, describe pictures in documents. Boolean. Optional, defaults to false.
      Returns:
      this.
    • pictureDescriptionAreaThreshold

      public @NonNull ConvertDocumentOptions.Builder pictureDescriptionAreaThreshold(@Nullable Double pictureDescriptionAreaThreshold)
      Minimum percentage of the area for a picture to be processed with the models.
      Returns:
      this.
    • pictureDescriptionLocal

      public @NonNull ConvertDocumentOptions.Builder pictureDescriptionLocal(@Nullable PictureDescriptionLocal pictureDescriptionLocal)
      Options for running a local vision-language model in the picture description. The parameters refer to a model hosted on Hugging Face. This parameter is mutually exclusive with picture_description_api.
      Returns:
      this.
    • pictureDescriptionApi

      public @NonNull ConvertDocumentOptions.Builder pictureDescriptionApi(@Nullable PictureDescriptionApi pictureDescriptionApi)
      API details for using a vision-language model in the picture description. This parameter is mutually exclusive with picture_description_local.
      Returns:
      this.
    • vlmPipelineModel

      public @NonNull ConvertDocumentOptions.Builder vlmPipelineModel(@Nullable VlmModelType vlmPipelineModel)
      Preset of local and API models for the vlm pipeline. This parameter is mutually exclusive with vlm_pipeline_model_local and vlm_pipeline_model_api. Use the other options for more parameters.
      Returns:
      this.
    • vlmPipelineModelLocal

      public @NonNull ConvertDocumentOptions.Builder vlmPipelineModelLocal(@Nullable String vlmPipelineModelLocal)
      Options for running a local vision-language model for the vlm pipeline. The parameters refer to a model hosted on Hugging Face. This parameter is mutually exclusive with vlm_pipeline_model_api and vlm_pipeline_model.
      Returns:
      this.
    • vlmPipelineModelApi

      public @NonNull ConvertDocumentOptions.Builder vlmPipelineModelApi(@Nullable String vlmPipelineModelApi)
      API details for using a vision-language model for the vlm pipeline. This parameter is mutually exclusive with vlm_pipeline_model_local and vlm_pipeline_model.
      Returns:
      this.
    • build

      public @NonNull ConvertDocumentOptions build()
    • toString

      public @NonNull String toString()
      Overrides:
      toString in class Object