GeminiPromptExecutionSettings Class

Reference

Definition

Namespace:: Microsoft.SemanticKernel.Connectors.Google

Assembly:: Microsoft.SemanticKernel.Connectors.Google.dll

Package:: Microsoft.SemanticKernel.Connectors.Google v1.20.0-alpha

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.

Represents the settings for executing a prompt with the Gemini model.

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

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

Public NotInheritable Class GeminiPromptExecutionSettings
Inherits PromptExecutionSettings

Inheritance: Object

PromptExecutionSettings
GeminiPromptExecutionSettings

Attributes: JsonNumberHandlingAttribute

Constructors

GeminiPromptExecutionSettings()

Properties

CandidateCount	The count of candidates. Possible values range from 1 to 8.
DefaultTextMaxTokens	Default max tokens for a text generation.
ExtensionData	Extra properties that may be included in the serialized execution settings. (Inherited from PromptExecutionSettings)
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 in the completion.
ModelId	Model identifier. This identifies the AI model these settings are configured for e.g., gpt-4, gpt-3.5-turbo (Inherited from PromptExecutionSettings)
SafetySettings	Represents a list of safety settings.
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	Sequences where the completion will stop generating further tokens. Maximum number of stop sequences is 5.
Temperature	Temperature controls the randomness of the completion. The higher the temperature, the more random the completion. Range is 0.0 to 1.0.
ToolCallBehavior	Gets or sets the behavior for how tool calls are handled.
TopK	Gets or sets the value of the TopK property. The TopK property represents the maximum value of a collection or dataset.
TopP	TopP controls the diversity of the completion. The higher the TopP, the more diverse the completion.

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)	Converts a PromptExecutionSettings object to a GeminiPromptExecutionSettings object.
ThrowIfFrozen()	Throws an InvalidOperationException if the PromptExecutionSettings are frozen. (Inherited from PromptExecutionSettings)

Applies to

Share via