AutoTaggingEngine

The built-in heuristic auto-tagger. Infers structure (headings, paragraphs, lists, tables, figures) from layout and font analysis. Fast and fully offline.

The Vision-based auto-tagger. Uses document layout segmentation, reading-order detection and table-structure recognition to build a higher-fidelity structure tree. Does not generate figure descriptions.

The Vision-based auto-tagger with Vision Language Model enrichment. Adds generated alternate text for figures and summaries for charts on top of . Requires a VLM provider to be configured (provider selection and credentials in the corresponding Vision settings); without one, tagging proceeds without descriptions.

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)

Returns an array containing the constants of this enum type, in the order they're declared. This method may be used to iterate over the constants.