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

VlmClassificationStrategy

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

Strategy for how zones are sent to the VLM for classification.

using Nutrient;

Values

NameValueDescription
VlmClassificationStrategy.OneShot0Send a single full-page image with bounding box coordinates in the prompt. The VLM performs spatial reasoning to classify each zone by its bbox.
VlmClassificationStrategy.MultiZone1Crop each zone from the source image and send multiple zone images per VLM call. The VLM classifies each cropped image by its visual content. Supports batching (BatchSize) and parallel execution (MaxConcurrency).