Class ConvertDocumentOptions.Builder
java.lang.Object
ai.docling.serve.api.convert.request.options.ConvertDocumentOptions.Builder
- Enclosing class:
- ConvertDocumentOptions
-
Method Summary
Modifier and TypeMethodDescription@NonNull ConvertDocumentOptions.BuilderabortOnError(@Nullable Boolean abortOnError) Abort on error if enabled.@NonNull ConvertDocumentOptionsbuild()@NonNull ConvertDocumentOptions.Builder@NonNull ConvertDocumentOptions.Builder@NonNull ConvertDocumentOptions.Builder@NonNull ConvertDocumentOptions.Builder@NonNull ConvertDocumentOptions.BuilderdoCodeEnrichment(@Nullable Boolean doCodeEnrichment) If enabled, perform OCR code enrichment.@NonNull ConvertDocumentOptions.BuilderdocumentTimeout(@Nullable Duration documentTimeout) The timeout for processing each document, in seconds.@NonNull ConvertDocumentOptions.BuilderdoFormulaEnrichment(@Nullable Boolean doFormulaEnrichment) If enabled, perform formula OCR, return LaTeX code.@NonNull ConvertDocumentOptions.BuilderIf enabled, the bitmap content will be processed using OCR.@NonNull ConvertDocumentOptions.BuilderdoPictureClassification(@Nullable Boolean doPictureClassification) If enabled, classify pictures in documents.@NonNull ConvertDocumentOptions.BuilderdoPictureDescription(@Nullable Boolean doPictureDescription) If enabled, describe pictures in documents.@NonNull ConvertDocumentOptions.BuilderdoTableStructure(@Nullable Boolean doTableStructure) If enabled, the table structure will be extracted.@NonNull ConvertDocumentOptions.BuilderIf enabled, replace existing text with OCR-generated text over content.@NonNull ConvertDocumentOptions.BuilderfromFormat(InputFormat fromFormat) @NonNull ConvertDocumentOptions.BuilderfromFormats(@NonNull Collection<? extends InputFormat> fromFormats) @NonNull ConvertDocumentOptions.BuilderimageExportMode(@Nullable ImageRefMode imageExportMode) Image export mode for the document (in case of JSON, Markdown or HTML).@NonNull ConvertDocumentOptions.BuilderimagesScale(@Nullable Double imagesScale) Scale factor for images.@NonNull ConvertDocumentOptions.BuilderincludeImages(@Nullable Boolean includeImages) If enabled, images will be extracted from the document.@NonNull ConvertDocumentOptions.BuildermdPageBreakPlaceholder(@Nullable String mdPageBreakPlaceholder) Add this placeholder between pages in the markdown output.@NonNull ConvertDocumentOptions.BuilderThe OCR engine to use.@NonNull ConvertDocumentOptions.BuilderocrLang(@NonNull Collection<? extends String> ocrLang) @NonNull ConvertDocumentOptions.Builder@NonNull ConvertDocumentOptions.BuilderpageRange(@NonNull Collection<? extends Integer> pageRange) @NonNull ConvertDocumentOptions.Builder@NonNull ConvertDocumentOptions.BuilderpdfBackend(@Nullable PdfBackend pdfBackend) The PDF backend to use.@NonNull ConvertDocumentOptions.BuilderpictureDescriptionApi(@Nullable PictureDescriptionApi pictureDescriptionApi) API details for using a vision-language model in the picture description.@NonNull ConvertDocumentOptions.BuilderpictureDescriptionAreaThreshold(@Nullable Double pictureDescriptionAreaThreshold) Minimum percentage of the area for a picture to be processed with the models.@NonNull ConvertDocumentOptions.BuilderpictureDescriptionLocal(@Nullable PictureDescriptionLocal pictureDescriptionLocal) Options for running a local vision-language model in the picture description.@NonNull ConvertDocumentOptions.Builderpipeline(@Nullable ProcessingPipeline pipeline) Choose the pipeline to process PDF or image files.@NonNull ConvertDocumentOptions.BuildertableCellMatching(@Nullable Boolean tableCellMatching) If true, matches table cells predictions back to PDF cells.@NonNull ConvertDocumentOptions.BuildertableMode(@Nullable TableFormerMode tableMode) Mode to use for table structure, String.@NonNull ConvertDocumentOptions.BuildertoFormat(OutputFormat toFormat) @NonNull ConvertDocumentOptions.BuildertoFormats(@NonNull Collection<? extends OutputFormat> toFormats) @NonNull StringtoString()@NonNull ConvertDocumentOptions.BuildervlmPipelineModel(@Nullable VlmModelType vlmPipelineModel) Preset of local and API models for the vlm pipeline.@NonNull ConvertDocumentOptions.BuildervlmPipelineModelApi(@Nullable String vlmPipelineModelApi) API details for using a vision-language model for the vlm pipeline.@NonNull ConvertDocumentOptions.BuildervlmPipelineModelLocal(@Nullable String vlmPipelineModelLocal) Options for running a local vision-language model for the vlm pipeline.
-
Method Details
-
fromFormat
-
fromFormats
public @NonNull ConvertDocumentOptions.Builder fromFormats(@NonNull Collection<? extends InputFormat> fromFormats) -
clearFromFormats
-
toFormat
-
toFormats
public @NonNull ConvertDocumentOptions.Builder toFormats(@NonNull Collection<? extends OutputFormat> toFormats) -
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
If enabled, the bitmap content will be processed using OCR. Boolean. Optional, defaults to true.- Returns:
this.
-
forceOcr
If enabled, replace existing text with OCR-generated text over content. Boolean. Optional, defaults to false.- Returns:
this.
-
ocrEngine
The OCR engine to use. String. Allowed values: auto, easyocr, ocrmac, rapidocr, tesserocr, tesseract. Optional, defaults to easyocr.- Returns:
this.
-
ocrLang
-
ocrLang
public @NonNull ConvertDocumentOptions.Builder ocrLang(@NonNull Collection<? extends String> ocrLang) -
clearOcrLang
-
pdfBackend
The PDF backend to use. String. Allowed values: pypdfium2, dlparse_v1, dlparse_v2, dlparse_v4. Optional, defaults to dlparse_v4.- Returns:
this.
-
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
Choose the pipeline to process PDF or image files.- Returns:
this.
-
pageRange
-
pageRange
public @NonNull ConvertDocumentOptions.Builder pageRange(@NonNull Collection<? extends Integer> pageRange) -
clearPageRange
-
documentTimeout
The timeout for processing each document, in seconds.- Returns:
this.
-
abortOnError
Abort on error if enabled. Boolean. Optional, defaults to false.- Returns:
this.
-
doTableStructure
If enabled, the table structure will be extracted. Boolean. Optional, defaults to true.- Returns:
this.
-
includeImages
If enabled, images will be extracted from the document. Boolean. Optional, defaults to true.- Returns:
this.
-
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
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
-
toString
-