AzureAIInferencePromptExecutionSettings Class

Reference

Definition

Namespace:: Microsoft.SemanticKernel.Connectors.AzureAIInference

Assembly:: Microsoft.SemanticKernel.Connectors.AzureAIInference.dll

Package:: Microsoft.SemanticKernel.Connectors.AzureAIInference v1.20.0-beta

Important

Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.

Chat completion prompt execution settings.

[System.Text.Json.Serialization.JsonNumberHandling(System.Text.Json.Serialization.JsonNumberHandling.AllowReadingFromString)]
public sealed class AzureAIInferencePromptExecutionSettings : Microsoft.SemanticKernel.PromptExecutionSettings

[<System.Text.Json.Serialization.JsonNumberHandling(System.Text.Json.Serialization.JsonNumberHandling.AllowReadingFromString)>]
type AzureAIInferencePromptExecutionSettings = class
    inherit PromptExecutionSettings

Public NotInheritable Class AzureAIInferencePromptExecutionSettings
Inherits PromptExecutionSettings

Inheritance: Object

PromptExecutionSettings
AzureAIInferencePromptExecutionSettings

Attributes: JsonNumberHandlingAttribute

Constructors

AzureAIInferencePromptExecutionSettings()

Initializes a new instance of the AzureAIInferencePromptExecutionSettings class.

Properties

ExtensionData	Extra properties that may be included in the serialized execution settings. (Inherited from PromptExecutionSettings)
ExtraParameters	Allowed values: "error" \| "drop" \| "pass-through"
FrequencyPenalty	A value that influences the probability of generated tokens appearing based on their cumulative frequency in generated text. Positive values will make tokens less likely to appear as their frequency increases and decrease the likelihood of the model repeating the same statements verbatim. Supported range is [-2, 2].
FunctionChoiceBehavior	Gets or sets the behavior defining the way functions are chosen by LLM and how they are invoked by AI connectors. (Inherited from PromptExecutionSettings)
IsFrozen	Gets a value that indicates whether the PromptExecutionSettings are currently modifiable. (Inherited from PromptExecutionSettings)
MaxTokens	The maximum number of tokens to generate.
ModelId	Model identifier. This identifies the AI model these settings are configured for e.g., gpt-4, gpt-3.5-turbo (Inherited from PromptExecutionSettings)
NucleusSamplingFactor	An alternative to sampling with temperature called nucleus sampling. This value causes the model to consider the results of tokens with the provided probability mass. As an example, a value of 0.15 will cause only the tokens comprising the top 15% of probability mass to be considered. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. Supported range is [0, 1].
PresencePenalty	A value that influences the probability of generated tokens appearing based on their existing presence in generated text. Positive values will make tokens less likely to appear when they already exist and increase the model's likelihood to output new topics. Supported range is [-2, 2].
ResponseFormat	The format that the model must output. Use this to enable JSON mode instead of the default text mode. Note that to enable JSON mode, some AI models may also require you to instruct the model to produce JSON via a system or user message. Please note ChatCompletionsResponseFormat is the base class. According to the scenario, a derived class of the base class might need to be assigned here, or this property needs to be casted to one of the possible derived classes. The available derived classes include ChatCompletionsResponseFormatJSON and ChatCompletionsResponseFormatText.
Seed	If specified, the system will make a best effort to sample deterministically such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed.
ServiceId	Service identifier. This identifies the service these settings are configured for e.g., azure_openai_eastus, openai, ollama, huggingface, etc. (Inherited from PromptExecutionSettings)
StopSequences	A collection of textual sequences that will end completions generation.
Temperature	The sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict. Supported range is [0, 1].
Tools	The available tool definitions that the chat completions request can use, including caller-defined functions. Please note ChatCompletionsToolDefinition is the base class. According to the scenario, a derived class of the base class might need to be assigned here, or this property needs to be casted to one of the possible derived classes. The available derived classes include Azure.AI.Inference.ChatCompletionsFunctionToolDefinition.

Methods

Clone()	Creates a new PromptExecutionSettings object that is a copy of the current instance.
Freeze()	Makes the current PromptExecutionSettings unmodifiable and sets its IsFrozen property to true.
FromExecutionSettings(PromptExecutionSettings)	Create a new settings object with the values from another settings object.
ThrowIfFrozen()	Throws an InvalidOperationException if the PromptExecutionSettings are frozen. (Inherited from PromptExecutionSettings)

Applies to

Share via