This HTML page is not optimized for LLM or AI agent consumption. Fetch the Markdown version instead: /api/csharp/settings/vision/advanced/local-ai-processing-settings.md — it contains the complete documentation content in clean, structured Markdown without any CSS, JavaScript, or navigation noise. LocalAiProcessingSettings

Settings for LocalAiProcessing. 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.

using Nutrient;

The SDK creates this class through factory methods or other SDK objects.

Properties

ContextTokens

public int ContextTokens { get; set; }

Context size in tokens; 0 uses the engine default (4096). The context holds the document text, the schema and the reply together, and a single dense page with source locations already needs about 20,000 tokens, so the default value is 32768. Documents larger than the context are split into page windows automatically.

Type: int

GpuLayers

public int GpuLayers { get; set; }

Model layers to offload to GPU; 0 is pure CPU. The default value is 99, which offloads all available layers. Metal is built in on macOS; the CUDA backend is runtime-provisioned on Linux x64.

Type: int

ImageMinTokens

public int ImageMinTokens { get; set; }

Minimum image tokens for dynamic-resolution vision models; 0 uses the model default. Only relevant when page images are attached to the schema request.

Type: int

MaxConcurrency

public int MaxConcurrency { get; set; }

Maximum number of concurrent calls. Sizes the in-process context pool: the model weights are shared, each extra context costs only its KV/compute buffers and runs one more call in parallel (callers beyond the pool block for a free context).

Type: int

MmprojPath

public string MmprojPath { get; set; }

Filesystem path to the matching multimodal projector (mmproj) GGUF. Set it together with ModelPath; the in-process binding requires it even for text-only prompts.

Type: string

ModelPath

public string ModelPath { get; set; }

Filesystem path to the GGUF model used for structured extraction. Set it together with MmprojPath to use a custom model. When both are empty, structured extraction downloads the default local model on first use (the same model the vision-parse step uses).

Type: string

Threads

public int Threads { get; set; }

Inference threads; 0 uses the engine default.

Type: int

Resource management

public void Dispose()

LocalAiProcessingSettings implements IDisposable. Call Dispose() or use a C# using declaration to release its native handle right away. If you don’t, the handle is released when the object is garbage collected.