Nutrient Java SDK/io.nutrient.sdk.settings/VisionSettings

VisionSettings

Settings for Vision. Values fall back through three levels: document → SDK → built-in default. Writes target the document only when set on a document's settings, otherwise the SDK globally when set on SdkSettings.

Functions

getAccessibleImageDescriptions

public final boolean getAccessibleImageDescriptions()

Indicates whether VLM image descriptions should be written as screen-reader alt text.

getEnableOcr

public final OcrActivationMode getEnableOcr()

Controls OCR resource loading and OCR-based word detection inside the ICR image pipeline.

getEnableVlm

public final boolean getEnableVlm()

Indicates whether the ICR image pipeline should run late VLM augmentation.

getEngine

public final VisionEngine getEngine()

Specifies which vision processing engine/pipeline to use for content extraction.

getFallbackProvider

public final VlmProvider getFallbackProvider()

Optional secondary provider used to transparently retry a request when the primary fails in a way a retry on the same model can't fix — a content-filtered or refused response, or a transient outage (unreachable endpoint, server error, rate limit).

getFeatures

public final VisionFeatures getFeatures()

Vision features to enable during document processing.

getOutputFormat

public final VisionOutputFormat getOutputFormat()

Format of content returned by .

getProvider

public final VlmProvider getProvider()

The primary Vision Language Model provider to use for AI-powered features.

setAccessibleImageDescriptions

public final void setAccessibleImageDescriptions(boolean value)

Indicates whether VLM image descriptions should be written as screen-reader alt text.