com.box.sdk

Class BoxAIAgentLLMEndpointParamsGoogle

Object

BoxJSONObject

BoxAIAgentLLMEndpointParams

BoxAIAgentLLMEndpointParamsGoogle

public class BoxAIAgentLLMEndpointParamsGoogle
extends BoxAIAgentLLMEndpointParams

Represents the AI LLM endpoint params Google object.

Field Summary

Fields

Modifier and Type	Field and Description
static String	TYPE The type of the LLM endpoint parameters.

Constructor Summary

Constructors

Constructor and Description
BoxAIAgentLLMEndpointParamsGoogle(Double temperature, Integer topK, Double topP) Constructs an AI agent with default settings.
BoxAIAgentLLMEndpointParamsGoogle(JsonObject jsonObject) Constructs an AI agent with default settings.

Method Summary

Modifier and Type	Method and Description
JsonObject	getJSONObject()
Double	getTemperature() Gets the temperature used for sampling during response generation, which occurs when top-P and top-K are applied.
Integer	getTopK() Gets the top-K value.
Double	getTopP() Gets the top-P value.
void	setTemperature(Double temperature) Sets the temperature used for sampling during response generation, which occurs when top-P and top-K are applied.
void	setTopK(Integer topK) Sets the top-K value.
void	setTopP(Double topP) Sets the top-P value.

Methods inherited from class BoxAIAgentLLMEndpointParams

getType, parse, setType

Methods inherited from class BoxJSONObject

clearPendingChanges, getJson, getPendingChanges, getPendingChangesAsJsonObject, getPendingJSONObject

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

TYPE

public static final String TYPE

The type of the LLM endpoint parameters.

See Also:

Constant Field Values

Constructor Detail

BoxAIAgentLLMEndpointParamsGoogle

public BoxAIAgentLLMEndpointParamsGoogle(Double temperature,
                                         Integer topK,
                                         Double topP)

Constructs an AI agent with default settings.

Parameters:

temperature - The temperature is used for sampling during response generation, which occurs when top-P and top-K are applied. Temperature controls the degree of randomness in token selection.

topK - Top-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-K of 3 means that the next token is selected from among the three most probable tokens by using temperature.

topP - Top-P changes how the model selects tokens for output. Tokens are selected from the most (see top-K) to least probable until the sum of their probabilities equals the top-P value.

BoxAIAgentLLMEndpointParamsGoogle

public BoxAIAgentLLMEndpointParamsGoogle(JsonObject jsonObject)

Constructs an AI agent with default settings.

Parameters:

jsonObject - JSON object representing the AI agent.

Method Detail

getTemperature

public Double getTemperature()

Gets the temperature used for sampling during response generation, which occurs when top-P and top-K are applied.

Returns:

The temperature used for sampling during response generation, which occurs when top-P and top-K are applied.

setTemperature

public void setTemperature(Double temperature)

Sets the temperature used for sampling during response generation, which occurs when top-P and top-K are applied.

Parameters:

temperature - The temperature used for sampling during response generation, which occurs when top-P and top-K are applied.

getTopK

public Integer getTopK()

Gets the top-K value.

Returns:

The top-K value.

setTopK

public void setTopK(Integer topK)

Sets the top-K value.

Parameters:

topK - The top-K value.

getTopP

public Double getTopP()

Gets the top-P value.

Returns:

The top-P value.

setTopP

public void setTopP(Double topP)

Sets the top-P value.

Parameters:

topP - The top-P value.

getJSONObject

public JsonObject getJSONObject()

Overrides:

getJSONObject in class BoxAIAgentLLMEndpointParams