com.box.sdkgen.schemas.aillmendpointparamsopenai

Class AiLlmEndpointParamsOpenAi

Object

NullableFieldTracker

SerializableObject

AiLlmEndpointParamsOpenAi

All Implemented Interfaces:

Serializable

public class AiLlmEndpointParamsOpenAi
extends SerializableObject

AI LLM endpoint params OpenAI object.

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AiLlmEndpointParamsOpenAi.Builder

Field Summary

Fields

Modifier and Type	Field and Description
protected Double	frequencyPenalty A number between -2.0 and 2.0.
protected Double	presencePenalty A number between -2.0 and 2.0.
protected String	stop Up to 4 sequences where the API will stop generating further tokens.
protected Double	temperature What sampling temperature to use, between 0 and 2.
protected Double	topP An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass.
protected EnumWrapper<AiLlmEndpointParamsOpenAiTypeField>	type The type of the AI LLM endpoint params object for OpenAI.

Fields inherited from class NullableFieldTracker

explicitlySetNullableFields

Constructor Summary

Constructors

Modifier	Constructor and Description
	AiLlmEndpointParamsOpenAi()
protected	AiLlmEndpointParamsOpenAi(AiLlmEndpointParamsOpenAi.Builder builder)

Method Summary

Modifier and Type	Method and Description
boolean	equals(Object o)
Double	getFrequencyPenalty()
Double	getPresencePenalty()
String	getStop()
Double	getTemperature()
Double	getTopP()
EnumWrapper<AiLlmEndpointParamsOpenAiTypeField>	getType()
int	hashCode()
String	toString()

Methods inherited from class SerializableObject

getRawData, setRawData

Methods inherited from class NullableFieldTracker

getExplicitlySetNullableFields, isFieldExplicitlySet, markNullableFieldAsSet, markNullableFieldsAsSet

Methods inherited from class Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Field Detail

type

protected EnumWrapper<AiLlmEndpointParamsOpenAiTypeField> type

The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**.

temperature

protected Double temperature

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.

topP

protected Double topP

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

frequencyPenalty

protected Double frequencyPenalty

A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

presencePenalty

protected Double presencePenalty

A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

stop

protected String stop

Up to 4 sequences where the API will stop generating further tokens.

Constructor Detail

AiLlmEndpointParamsOpenAi

public AiLlmEndpointParamsOpenAi()

AiLlmEndpointParamsOpenAi

protected AiLlmEndpointParamsOpenAi(AiLlmEndpointParamsOpenAi.Builder builder)

Method Detail

getType

public EnumWrapper<AiLlmEndpointParamsOpenAiTypeField> getType()

getTemperature

public Double getTemperature()

getTopP

public Double getTopP()

getFrequencyPenalty

public Double getFrequencyPenalty()

getPresencePenalty

public Double getPresencePenalty()

getStop

public String getStop()

equals

public boolean equals(Object o)

Overrides:

equals in class Object

hashCode

public int hashCode()

Overrides:

hashCode in class Object

toString

public String toString()

Overrides:

toString in class Object