DocumentVLMOptions
Options & Configuration · AiDotNet.VisionLanguage.Document
Base configuration options for document understanding vision-language models.
Inheritance: ModelOptions → GenerativeVLMOptions → DocumentVLMOptions
Known derived types: DocPediaOptions, GOTOCR2Options, MPLUGDocOwl15Options, MPLUGDocOwl2Options, MPLUGDocOwlOptions, SuryaOptions, TextMonkeyOptions, UReaderOptions
For Beginners
These options configure the Document model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
DocumentVLMOptions() |
Initializes a new instance with default values. |
DocumentVLMOptions(DocumentVLMOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
bool IsOcrFree { get; set; } |
Gets or sets whether this model operates OCR-free (no external OCR required). |
int MaxOutputTokens { get; set; } |
Gets or sets the maximum output text length in tokens. |
int MaxPages { get; set; } |
Gets or sets the maximum document page count supported. |