com.oracle.bmc.generativeaiinference.model

Class GeneratedText.Builder

java.lang.Object

com.oracle.bmc.generativeaiinference.model.GeneratedText.Builder

Enclosing class:

GeneratedText

public static class GeneratedText.Builder
extends Object

Constructor Summary

Constructors

Constructor and Description
Builder()

Method Summary

Modifier and Type	Method and Description
GeneratedText	build()
GeneratedText.Builder	copy(GeneratedText model)
GeneratedText.Builder	finishReason(String finishReason) The reason why the model stopped generating tokens.
GeneratedText.Builder	id(String id) A unique identifier for this text generation.
GeneratedText.Builder	likelihood(Double likelihood) The overall likelihood of the generated text.
GeneratedText.Builder	text(String text) The generated text.
GeneratedText.Builder	tokenLikelihoods(List<TokenLikelihood> tokenLikelihoods) A collection of generated tokens and their corresponding likelihoods.

Methods inherited from class java.lang.Object

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

Constructor Detail

Builder

public Builder()

Method Detail

id

public GeneratedText.Builder id(String id)

A unique identifier for this text generation.

Parameters:

id - the value to set

Returns:

this builder

text

public GeneratedText.Builder text(String text)

The generated text.

Parameters:

text - the value to set

Returns:

this builder

likelihood

public GeneratedText.Builder likelihood(Double likelihood)

The overall likelihood of the generated text.

When a large language model generates a new token for the output text, a likelihood is assigned to all tokens, where tokens with higher likelihoods are more likely to follow the current token. For example, it's more likely that the word favorite is followed by the word food or book rather than the word zebra. A lower likelihood means that it's less likely that token follows the current token.

Parameters:

likelihood - the value to set

Returns:

this builder

finishReason

public GeneratedText.Builder finishReason(String finishReason)

The reason why the model stopped generating tokens.

A model stops generating tokens if the model hits a natural stop point or reaches a provided stop sequence.

Parameters:

finishReason - the value to set

Returns:

this builder

tokenLikelihoods

public GeneratedText.Builder tokenLikelihoods(List<TokenLikelihood> tokenLikelihoods)

A collection of generated tokens and their corresponding likelihoods.

Parameters:

tokenLikelihoods - the value to set

Returns:

this builder

build

public GeneratedText build()

copy

public GeneratedText.Builder copy(GeneratedText model)