---
title: "AutoTaggingEngine"
canonical_url: "https://www.nutrient.io/api/python/enums/auto-tagging-engine/"
md_url: "https://www.nutrient.io/api/python/enums/auto-tagging-engine.md"
last_updated: "2026-09-02T09:34:35.870Z"
description: "Selects the engine used to build the logical structure (tags) when converting a document to a tagged, accessible PDF (PDF/UA)."
---

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

```python

from nutrient_sdk import AutoTaggingEngine

```

## Values

| Name                           | Value | Description                                                                                                                                                                                                                                                                                                                        |
| ------------------------------ | ----- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `AutoTaggingEngine.HEURISTIC`  | `0`   | The built-in heuristic auto-tagger. Infers structure (headings, paragraphs, lists, tables, figures) from layout and font analysis. Fast and fully offline.                                                                                                                                                                         |
| `AutoTaggingEngine.VISION`     | `1`   | 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.                                                                                                                         |
| `AutoTaggingEngine.VISION_VLM` | `2`   | The 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

```python

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

```

---

## Related pages

- [All public classes import directly from the top-level package:](/api/python/enums.md)
- [Access enum values](/api/python/enums/description-level.md)
- [Access enum values](/api/python/enums/document-bookmark-source.md)
- [Access enum values](/api/python/enums/document-format.md)
- [Access enum values](/api/python/enums/document-markup-mode.md)
- [Access enum values](/api/python/enums/document-type.md)
- [Access enum values](/api/python/enums/execution-provider.md)
- [Access enum values](/api/python/enums/html-layout-type.md)
- [Access enum values](/api/python/enums/image-export-format.md)
- [Access enum values](/api/python/enums/image-export-mode.md)
- [Access enum values](/api/python/enums/image-setting-mode.md)
- [Access enum values](/api/python/enums/implicit-conversion.md)
- [Access enum values](/api/python/enums/instant-json-render-theme.md)
- [Access enum values](/api/python/enums/json-export-content.md)
- [Access enum values](/api/python/enums/json-export-format.md)
- [Access enum values](/api/python/enums/ocr-activation-mode.md)
- [Access enum values](/api/python/enums/open-settings-mode.md)
- [Access enum values](/api/python/enums/page-cache-mode.md)
- [Access enum values](/api/python/enums/pdf-border-style.md)
- [Access enum values](/api/python/enums/pdf-compression.md)
- [Access enum values](/api/python/enums/pdf-conformance.md)
- [Access enum values](/api/python/enums/pdf-form-field-type.md)
- [Access enum values](/api/python/enums/pdf-line-ending-style.md)
- [Access enum values](/api/python/enums/pdf-page-sizes.md)
- [Access enum values](/api/python/enums/pdf-rubber-stamp-icon.md)
- [Access enum values](/api/python/enums/pdf-save-preferences.md)
- [Access enum values](/api/python/enums/pdf-settings-mode.md)
- [Access enum values](/api/python/enums/pdf-validation-conformance.md)
- [Access enum values](/api/python/enums/rendering-layout-mode.md)
- [Access enum values](/api/python/enums/restoration-mode.md)
- [Access enum values](/api/python/enums/schema-compatibility.md)
- [Access enum values](/api/python/enums/search-display.md)
- [Access enum values](/api/python/enums/search-mode.md)
- [Access enum values](/api/python/enums/signature-certification-level.md)
- [Access enum values](/api/python/enums/signature-format.md)
- [Access enum values](/api/python/enums/signature-hash-algorithm.md)
- [Access enum values](/api/python/enums/signature-key-source.md)
- [Access enum values](/api/python/enums/signature-level.md)
- [Access enum values](/api/python/enums/text-direction.md)
- [Access enum values](/api/python/enums/tiff-compression.md)
- [Access enum values](/api/python/enums/unit-mode.md)
- [Access enum values](/api/python/enums/unparseable-output-handling.md)
- [Access enum values](/api/python/enums/vision-engine.md)
- [Access enum values](/api/python/enums/vision-features.md)
- [Access enum values](/api/python/enums/vision-output-format.md)
- [Access enum values](/api/python/enums/vlm-classification-strategy.md)
- [Access enum values](/api/python/enums/vlm-provider.md)
- [Access enum values](/api/python/enums/word-refining-method.md)