Specifies which vision processing pipeline to use for content extraction.
ICR (Intelligent Content Recognition) refers to intelligent document understanding that goes beyond traditional OCR. While OCR simply converts images of text into machine-readable characters, ICR analyzes the full document structure.
using Nutrient;Values
| Name | Value | Description |
|---|---|---|
VisionEngine.VlmEnhancedIcr | 0 | VLM-enhanced ICR extraction pipeline combining ICR with Vision Language Models. |
VisionEngine.AdaptiveOcr | 1 | Adaptive OCR pipeline: heuristic-first with OCR fallback per page. |
VisionEngine.Icr | 2 | Local ICR extraction pipeline using only small models (no VLM required). |
VisionEngine.Auto | 3 | Automatically selects the extraction pipeline independently for each page. |