ClassCompleteContextProcessorSettings
Settings for full-context processing over document text (such as PDF), configuring token limits, encoding, and model selection.
Definition
Namespace:Telerik.Windows.Documents.AIConnector
Assembly:Telerik.Windows.Documents.AIConnector.dll
Syntax:
public class CompleteContextProcessorSettingsInheritance: objectCompleteContextProcessorSettings
Derived Classes:
Constructors
CompleteContextProcessorSettings(int, string, string, bool)
Initializes a new instance of the CompleteContextProcessorSettings class with the specified maximum input token limit.
Declaration
public CompleteContextProcessorSettings(int modelMaxInputTokenLimit, string modelId = null, string tokenizationEncoding = null, bool produceJsonFormattedContext = false)Parameters
modelMaxInputTokenLimit
The maximum input token limit for the model.
modelId
The model identifier.
tokenizationEncoding
The tokenization encoding the model uses.
produceJsonFormattedContext
Determines whether the context sent to the model will be formatted as json when applicable.
Properties
ModelId
Gets the model identifier used for AI requests.
ModelMaxInputTokenLimit
Gets the maximum input token limit for prompts sent to the model, bounding full-context requests.
ProduceJsonFormattedContext
Determines whether the context sent to the model is in JSON or plain text format, if json format is applicable.
Declaration
public bool ProduceJsonFormattedContext { get; }Property Value
Remarks
Plain text might consume more tokens but should lead to better results when asking the LLM.
TokenizationEncoding
Gets the tokenization encoding used to measure and split text when preparing prompts.