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

VisionFeatures

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

Vision processing features that can be enabled or disabled.

from nutrient_sdk import VisionFeatures

Values

NameValueDescription
VisionFeatures.UNKNOWN0No features enabled.
VisionFeatures.EQUATION1Mathematical equation detection and recognition.
VisionFeatures.TABLE2Table structure detection and extraction.
VisionFeatures.KEY_VALUE_REGION4Key-value region detection for form-like content.
VisionFeatures.IMAGE_CLASSIFICATION8Image classification for figures and diagrams.
VisionFeatures.HANDWRITING16Handwriting recognition in document regions.
VisionFeatures.FORM32Form field detection (TextBox, ChoiceButton, Signature).
VisionFeatures.BARCODE_DETECTION64Barcode/QR decode-test on image regions: regions whose content decodes as a barcode are emitted as BarcodeNode instead of PictureNode.
VisionFeatures.INLINE_STYLES128Inline text-style classification (bold, italic, underline, strikeout, highlight, superscript, subscript) on OCR words. Advanced options are configured via InlineStyleSettings.
VisionFeatures.LEXICON256Language-aware dehyphenation from lexicon packs; off means the built-in English lists only.
VisionFeatures.ALL511All vision features enabled.

Usage Example 

from nutrient_sdk import VisionFeatures


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