com.amazonaws.services.bedrockagentruntime.model.TextInferenceConfig Maven / Gradle / Ivy
/*
* Copyright 2019-2024 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance with
* the License. A copy of the License is located at
*
* http://aws.amazon.com/apache2.0
*
* or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
* CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
* and limitations under the License.
*/
package com.amazonaws.services.bedrockagentruntime.model;
import java.io.Serializable;
import javax.annotation.Generated;
import com.amazonaws.protocol.StructuredPojo;
import com.amazonaws.protocol.ProtocolMarshaller;
/**
*
* Configuration settings for text generation using a language model via the RetrieveAndGenerate operation. Includes
* parameters like temperature, top-p, maximum token count, and stop sequences.
*
*
*
* The valid range of maxTokens depends on the accepted values for your chosen model's inference
* parameters. To see the inference parameters for your model, see Inference parameters for foundation
* models.
*
*
*
* @see AWS API Documentation
*/
@Generated("com.amazonaws:aws-java-sdk-code-generator")
public class TextInferenceConfig implements Serializable, Cloneable, StructuredPojo {
/**
*
* The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536.
* The limit values described here are arbitary values, for actual values consult the limits defined by your
* specific model.
*
*/
private Integer maxTokens;
/**
*
* A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do
* not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values,
* for actual values consult the limits defined by your specific model.
*
*/
private java.util.List stopSequences;
/**
*
* Controls the random-ness of text generated by the language model, influencing how much the model sticks to the
* most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3)
* makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the
* outputs more creative or unpredictable.
*
*/
private Float temperature;
/**
*
* A probability distribution threshold which controls what the model considers for the set of possible next tokens.
* The model will only consider the top p% of the probability distribution when generating the next token.
*
*/
private Float topP;
/**
*
* The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536.
* The limit values described here are arbitary values, for actual values consult the limits defined by your
* specific model.
*
*
* @param maxTokens
* The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of
* 65536. The limit values described here are arbitary values, for actual values consult the limits defined
* by your specific model.
*/
public void setMaxTokens(Integer maxTokens) {
this.maxTokens = maxTokens;
}
/**
*
* The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536.
* The limit values described here are arbitary values, for actual values consult the limits defined by your
* specific model.
*
*
* @return The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum
* of 65536. The limit values described here are arbitary values, for actual values consult the limits
* defined by your specific model.
*/
public Integer getMaxTokens() {
return this.maxTokens;
}
/**
*
* The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536.
* The limit values described here are arbitary values, for actual values consult the limits defined by your
* specific model.
*
*
* @param maxTokens
* The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of
* 65536. The limit values described here are arbitary values, for actual values consult the limits defined
* by your specific model.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public TextInferenceConfig withMaxTokens(Integer maxTokens) {
setMaxTokens(maxTokens);
return this;
}
/**
*
* A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do
* not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values,
* for actual values consult the limits defined by your specific model.
*
*
* @return A list of sequences of characters that, if generated, will cause the model to stop generating further
* tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are
* arbitary values, for actual values consult the limits defined by your specific model.
*/
public java.util.List getStopSequences() {
return stopSequences;
}
/**
*
* A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do
* not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values,
* for actual values consult the limits defined by your specific model.
*
*
* @param stopSequences
* A list of sequences of characters that, if generated, will cause the model to stop generating further
* tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are
* arbitary values, for actual values consult the limits defined by your specific model.
*/
public void setStopSequences(java.util.Collection stopSequences) {
if (stopSequences == null) {
this.stopSequences = null;
return;
}
this.stopSequences = new java.util.ArrayList(stopSequences);
}
/**
*
* A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do
* not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values,
* for actual values consult the limits defined by your specific model.
*
*
* NOTE: This method appends the values to the existing list (if any). Use
* {@link #setStopSequences(java.util.Collection)} or {@link #withStopSequences(java.util.Collection)} if you want
* to override the existing values.
*
*
* @param stopSequences
* A list of sequences of characters that, if generated, will cause the model to stop generating further
* tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are
* arbitary values, for actual values consult the limits defined by your specific model.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public TextInferenceConfig withStopSequences(String... stopSequences) {
if (this.stopSequences == null) {
setStopSequences(new java.util.ArrayList(stopSequences.length));
}
for (String ele : stopSequences) {
this.stopSequences.add(ele);
}
return this;
}
/**
*
* A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do
* not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values,
* for actual values consult the limits defined by your specific model.
*
*
* @param stopSequences
* A list of sequences of characters that, if generated, will cause the model to stop generating further
* tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are
* arbitary values, for actual values consult the limits defined by your specific model.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public TextInferenceConfig withStopSequences(java.util.Collection stopSequences) {
setStopSequences(stopSequences);
return this;
}
/**
*
* Controls the random-ness of text generated by the language model, influencing how much the model sticks to the
* most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3)
* makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the
* outputs more creative or unpredictable.
*
*
* @param temperature
* Controls the random-ness of text generated by the language model, influencing how much the model sticks to
* the most predictable next words versus exploring more surprising options. A lower temperature value (e.g.
* 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or
* 0.9) makes the outputs more creative or unpredictable.
*/
public void setTemperature(Float temperature) {
this.temperature = temperature;
}
/**
*
* Controls the random-ness of text generated by the language model, influencing how much the model sticks to the
* most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3)
* makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the
* outputs more creative or unpredictable.
*
*
* @return Controls the random-ness of text generated by the language model, influencing how much the model sticks
* to the most predictable next words versus exploring more surprising options. A lower temperature value
* (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g.
* 0.8 or 0.9) makes the outputs more creative or unpredictable.
*/
public Float getTemperature() {
return this.temperature;
}
/**
*
* Controls the random-ness of text generated by the language model, influencing how much the model sticks to the
* most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3)
* makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the
* outputs more creative or unpredictable.
*
*
* @param temperature
* Controls the random-ness of text generated by the language model, influencing how much the model sticks to
* the most predictable next words versus exploring more surprising options. A lower temperature value (e.g.
* 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or
* 0.9) makes the outputs more creative or unpredictable.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public TextInferenceConfig withTemperature(Float temperature) {
setTemperature(temperature);
return this;
}
/**
*
* A probability distribution threshold which controls what the model considers for the set of possible next tokens.
* The model will only consider the top p% of the probability distribution when generating the next token.
*
*
* @param topP
* A probability distribution threshold which controls what the model considers for the set of possible next
* tokens. The model will only consider the top p% of the probability distribution when generating the next
* token.
*/
public void setTopP(Float topP) {
this.topP = topP;
}
/**
*
* A probability distribution threshold which controls what the model considers for the set of possible next tokens.
* The model will only consider the top p% of the probability distribution when generating the next token.
*
*
* @return A probability distribution threshold which controls what the model considers for the set of possible next
* tokens. The model will only consider the top p% of the probability distribution when generating the next
* token.
*/
public Float getTopP() {
return this.topP;
}
/**
*
* A probability distribution threshold which controls what the model considers for the set of possible next tokens.
* The model will only consider the top p% of the probability distribution when generating the next token.
*
*
* @param topP
* A probability distribution threshold which controls what the model considers for the set of possible next
* tokens. The model will only consider the top p% of the probability distribution when generating the next
* token.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public TextInferenceConfig withTopP(Float topP) {
setTopP(topP);
return this;
}
/**
* Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be
* redacted from this string using a placeholder value.
*
* @return A string representation of this object.
*
* @see java.lang.Object#toString()
*/
@Override
public String toString() {
StringBuilder sb = new StringBuilder();
sb.append("{");
if (getMaxTokens() != null)
sb.append("MaxTokens: ").append(getMaxTokens()).append(",");
if (getStopSequences() != null)
sb.append("StopSequences: ").append(getStopSequences()).append(",");
if (getTemperature() != null)
sb.append("Temperature: ").append(getTemperature()).append(",");
if (getTopP() != null)
sb.append("TopP: ").append(getTopP());
sb.append("}");
return sb.toString();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (obj instanceof TextInferenceConfig == false)
return false;
TextInferenceConfig other = (TextInferenceConfig) obj;
if (other.getMaxTokens() == null ^ this.getMaxTokens() == null)
return false;
if (other.getMaxTokens() != null && other.getMaxTokens().equals(this.getMaxTokens()) == false)
return false;
if (other.getStopSequences() == null ^ this.getStopSequences() == null)
return false;
if (other.getStopSequences() != null && other.getStopSequences().equals(this.getStopSequences()) == false)
return false;
if (other.getTemperature() == null ^ this.getTemperature() == null)
return false;
if (other.getTemperature() != null && other.getTemperature().equals(this.getTemperature()) == false)
return false;
if (other.getTopP() == null ^ this.getTopP() == null)
return false;
if (other.getTopP() != null && other.getTopP().equals(this.getTopP()) == false)
return false;
return true;
}
@Override
public int hashCode() {
final int prime = 31;
int hashCode = 1;
hashCode = prime * hashCode + ((getMaxTokens() == null) ? 0 : getMaxTokens().hashCode());
hashCode = prime * hashCode + ((getStopSequences() == null) ? 0 : getStopSequences().hashCode());
hashCode = prime * hashCode + ((getTemperature() == null) ? 0 : getTemperature().hashCode());
hashCode = prime * hashCode + ((getTopP() == null) ? 0 : getTopP().hashCode());
return hashCode;
}
@Override
public TextInferenceConfig clone() {
try {
return (TextInferenceConfig) super.clone();
} catch (CloneNotSupportedException e) {
throw new IllegalStateException("Got a CloneNotSupportedException from Object.clone() " + "even though we're Cloneable!", e);
}
}
@com.amazonaws.annotation.SdkInternalApi
@Override
public void marshall(ProtocolMarshaller protocolMarshaller) {
com.amazonaws.services.bedrockagentruntime.model.transform.TextInferenceConfigMarshaller.getInstance().marshall(this, protocolMarshaller);
}
}