Constructor DocumentToMarkdown

Namespace

LMKit.Document.Conversion

Assembly

LM-Kit.NET.dll

DocumentToMarkdown()

Initializes a new instance of the DocumentToMarkdown class without a user-supplied vision model. All strategies remain available: if a vision-language strategy is selected, the default model lightonocr-2:1b (see DefaultVisionModelId) is loaded lazily on first use.

public DocumentToMarkdown()

DocumentToMarkdown(LM)

Initializes a new instance of the DocumentToMarkdown class with the specified vision-language model. The model is used for all vision-based strategies and must support text generation and vision.

public DocumentToMarkdown(LM visionModel)

Parameters

visionModel LM

A vision-capable LM used by the VLM OCR strategy. Pass null to defer to the default model (DefaultVisionModelId), which is loaded lazily the first time a vision-based strategy actually needs it.

Exceptions

InvalidModelException

Thrown when visionModel is not vision-capable or has been loaded without tensor weights.