This HTML page is not optimized for LLM or AI agent consumption. Fetch the Markdown version instead: /api/python/enums/auto-tagging-engine.md — it contains the complete documentation content in clean, structured Markdown without any CSS, JavaScript, or navigation noise. AutoTaggingEngine

AutoTaggingEngine

Markdown version of this page, suitable for AI agents and automation

Selects the engine used to build the logical structure (tags) when converting a document to a tagged, accessible PDF (PDF/UA).

from nutrient_sdk import AutoTaggingEngine

Values

NameValueDescription
AutoTaggingEngine.HEURISTIC0The built-in heuristic auto-tagger. Infers structure (headings, paragraphs, lists, tables, figures) from layout and font analysis. Fast and fully offline.
AutoTaggingEngine.VISION1The 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.
AutoTaggingEngine.VISION_VLM2The Vision-based auto-tagger with Vision Language Model enrichment. Adds generated alternate text for figures and summaries for charts on top of Vision. Requires a VLM provider to be configured (provider selection and credentials in the corresponding Vision settings); without one, tagging proceeds without descriptions.

Usage Example 

from nutrient_sdk import AutoTaggingEngine


# Access enum values
value = AutoTaggingEngine.HEURISTIC
print(f"Value: {value}")  # Output: Value: AutoTaggingEngine.HEURISTIC
print(f"Integer value: {value.value}")  # Output: Integer value: 0