software.amazon.awssdk.services.bedrockruntime.model.InferenceConfiguration Maven / Gradle / Ivy
Show all versions of bedrockruntime Show documentation
/*
* Copyright 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 software.amazon.awssdk.services.bedrockruntime.model;
import java.io.Serializable;
import java.util.Arrays;
import java.util.Collection;
import java.util.Collections;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.function.BiConsumer;
import java.util.function.Function;
import software.amazon.awssdk.annotations.Generated;
import software.amazon.awssdk.core.SdkField;
import software.amazon.awssdk.core.SdkPojo;
import software.amazon.awssdk.core.protocol.MarshallLocation;
import software.amazon.awssdk.core.protocol.MarshallingType;
import software.amazon.awssdk.core.traits.ListTrait;
import software.amazon.awssdk.core.traits.LocationTrait;
import software.amazon.awssdk.core.util.DefaultSdkAutoConstructList;
import software.amazon.awssdk.core.util.SdkAutoConstructList;
import software.amazon.awssdk.utils.ToString;
import software.amazon.awssdk.utils.builder.CopyableBuilder;
import software.amazon.awssdk.utils.builder.ToCopyableBuilder;
/**
*
* Base inference parameters to pass to a model in a call to Converse or ConverseStream.
* For more information, see Inference parameters for foundation
* models.
*
*
* If you need to pass additional parameters that the model supports, use the additionalModelRequestFields
* request field in the call to Converse or ConverseStream. For more information, see Model parameters.
*
*/
@Generated("software.amazon.awssdk:codegen")
public final class InferenceConfiguration implements SdkPojo, Serializable,
ToCopyableBuilder {
private static final SdkField MAX_TOKENS_FIELD = SdkField. builder(MarshallingType.INTEGER)
.memberName("maxTokens").getter(getter(InferenceConfiguration::maxTokens)).setter(setter(Builder::maxTokens))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("maxTokens").build()).build();
private static final SdkField TEMPERATURE_FIELD = SdkField. builder(MarshallingType.FLOAT)
.memberName("temperature").getter(getter(InferenceConfiguration::temperature)).setter(setter(Builder::temperature))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("temperature").build()).build();
private static final SdkField TOPP_FIELD = SdkField. builder(MarshallingType.FLOAT).memberName("topP")
.getter(getter(InferenceConfiguration::topP)).setter(setter(Builder::topP))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("topP").build()).build();
private static final SdkField> STOP_SEQUENCES_FIELD = SdkField
.> builder(MarshallingType.LIST)
.memberName("stopSequences")
.getter(getter(InferenceConfiguration::stopSequences))
.setter(setter(Builder::stopSequences))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("stopSequences").build(),
ListTrait
.builder()
.memberLocationName(null)
.memberFieldInfo(
SdkField. builder(MarshallingType.STRING)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD)
.locationName("member").build()).build()).build()).build();
private static final List> SDK_FIELDS = Collections.unmodifiableList(Arrays.asList(MAX_TOKENS_FIELD,
TEMPERATURE_FIELD, TOPP_FIELD, STOP_SEQUENCES_FIELD));
private static final long serialVersionUID = 1L;
private final Integer maxTokens;
private final Float temperature;
private final Float topP;
private final List stopSequences;
private InferenceConfiguration(BuilderImpl builder) {
this.maxTokens = builder.maxTokens;
this.temperature = builder.temperature;
this.topP = builder.topP;
this.stopSequences = builder.stopSequences;
}
/**
*
* The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value
* for the model that you are using. For more information, see Inference parameters for
* foundation models.
*
*
* @return The maximum number of tokens to allow in the generated response. The default value is the maximum allowed
* value for the model that you are using. For more information, see Inference parameters
* for foundation models.
*/
public final Integer maxTokens() {
return maxTokens;
}
/**
*
* The likelihood of the model selecting higher-probability options while generating a response. A lower value makes
* the model more likely to choose higher-probability options, while a higher value makes the model more likely to
* choose lower-probability options.
*
*
* The default value is the default value for the model that you are using. For more information, see Inference parameters for
* foundation models.
*
*
* @return The likelihood of the model selecting higher-probability options while generating a response. A lower
* value makes the model more likely to choose higher-probability options, while a higher value makes the
* model more likely to choose lower-probability options.
*
* The default value is the default value for the model that you are using. For more information, see Inference parameters
* for foundation models.
*/
public final Float temperature() {
return temperature;
}
/**
*
* The percentage of most-likely candidates that the model considers for the next token. For example, if you choose
* a value of 0.8 for topP, the model selects from the top 80% of the probability distribution of
* tokens that could be next in the sequence.
*
*
* The default value is the default value for the model that you are using. For more information, see Inference parameters for
* foundation models.
*
*
* @return The percentage of most-likely candidates that the model considers for the next token. For example, if you
* choose a value of 0.8 for topP, the model selects from the top 80% of the probability
* distribution of tokens that could be next in the sequence.
*
* The default value is the default value for the model that you are using. For more information, see Inference parameters
* for foundation models.
*/
public final Float topP() {
return topP;
}
/**
* For responses, this returns true if the service returned a value for the StopSequences property. This DOES NOT
* check that the value is non-empty (for which, you should check the {@code isEmpty()} method on the property).
* This is useful because the SDK will never return a null collection or map, but you may need to differentiate
* between the service returning nothing (or null) and the service returning an empty collection or map. For
* requests, this returns true if a value for the property was specified in the request builder, and false if a
* value was not specified.
*/
public final boolean hasStopSequences() {
return stopSequences != null && !(stopSequences instanceof SdkAutoConstructList);
}
/**
*
* A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating
* the response.
*
*
* Attempts to modify the collection returned by this method will result in an UnsupportedOperationException.
*
*
* This method will never return null. If you would like to know whether the service returned this field (so that
* you can differentiate between null and empty), you can use the {@link #hasStopSequences} method.
*
*
* @return A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop
* generating the response.
*/
public final List stopSequences() {
return stopSequences;
}
@Override
public Builder toBuilder() {
return new BuilderImpl(this);
}
public static Builder builder() {
return new BuilderImpl();
}
public static Class serializableBuilderClass() {
return BuilderImpl.class;
}
@Override
public final int hashCode() {
int hashCode = 1;
hashCode = 31 * hashCode + Objects.hashCode(maxTokens());
hashCode = 31 * hashCode + Objects.hashCode(temperature());
hashCode = 31 * hashCode + Objects.hashCode(topP());
hashCode = 31 * hashCode + Objects.hashCode(hasStopSequences() ? stopSequences() : null);
return hashCode;
}
@Override
public final boolean equals(Object obj) {
return equalsBySdkFields(obj);
}
@Override
public final boolean equalsBySdkFields(Object obj) {
if (this == obj) {
return true;
}
if (obj == null) {
return false;
}
if (!(obj instanceof InferenceConfiguration)) {
return false;
}
InferenceConfiguration other = (InferenceConfiguration) obj;
return Objects.equals(maxTokens(), other.maxTokens()) && Objects.equals(temperature(), other.temperature())
&& Objects.equals(topP(), other.topP()) && hasStopSequences() == other.hasStopSequences()
&& Objects.equals(stopSequences(), other.stopSequences());
}
/**
* 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.
*/
@Override
public final String toString() {
return ToString.builder("InferenceConfiguration").add("MaxTokens", maxTokens()).add("Temperature", temperature())
.add("TopP", topP()).add("StopSequences", hasStopSequences() ? stopSequences() : null).build();
}
public final Optional getValueForField(String fieldName, Class clazz) {
switch (fieldName) {
case "maxTokens":
return Optional.ofNullable(clazz.cast(maxTokens()));
case "temperature":
return Optional.ofNullable(clazz.cast(temperature()));
case "topP":
return Optional.ofNullable(clazz.cast(topP()));
case "stopSequences":
return Optional.ofNullable(clazz.cast(stopSequences()));
default:
return Optional.empty();
}
}
@Override
public final List> sdkFields() {
return SDK_FIELDS;
}
private static Function getter(Function g) {
return obj -> g.apply((InferenceConfiguration) obj);
}
private static BiConsumer setter(BiConsumer s) {
return (obj, val) -> s.accept((Builder) obj, val);
}
public interface Builder extends SdkPojo, CopyableBuilder {
/**
*
* The maximum number of tokens to allow in the generated response. The default value is the maximum allowed
* value for the model that you are using. For more information, see Inference parameters for
* foundation models.
*
*
* @param maxTokens
* The maximum number of tokens to allow in the generated response. The default value is the maximum
* allowed value for the model that you are using. For more information, see Inference parameters
* for foundation models.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder maxTokens(Integer maxTokens);
/**
*
* The likelihood of the model selecting higher-probability options while generating a response. A lower value
* makes the model more likely to choose higher-probability options, while a higher value makes the model more
* likely to choose lower-probability options.
*
*
* The default value is the default value for the model that you are using. For more information, see Inference parameters for
* foundation models.
*
*
* @param temperature
* The likelihood of the model selecting higher-probability options while generating a response. A lower
* value makes the model more likely to choose higher-probability options, while a higher value makes the
* model more likely to choose lower-probability options.
*
* The default value is the default value for the model that you are using. For more information, see Inference parameters
* for foundation models.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder temperature(Float temperature);
/**
*
* The percentage of most-likely candidates that the model considers for the next token. For example, if you
* choose a value of 0.8 for topP, the model selects from the top 80% of the probability
* distribution of tokens that could be next in the sequence.
*
*
* The default value is the default value for the model that you are using. For more information, see Inference parameters for
* foundation models.
*
*
* @param topP
* The percentage of most-likely candidates that the model considers for the next token. For example, if
* you choose a value of 0.8 for topP, the model selects from the top 80% of the probability
* distribution of tokens that could be next in the sequence.
*
* The default value is the default value for the model that you are using. For more information, see Inference parameters
* for foundation models.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder topP(Float topP);
/**
*
* A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop
* generating the response.
*
*
* @param stopSequences
* A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop
* generating the response.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder stopSequences(Collection stopSequences);
/**
*
* A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop
* generating the response.
*
*
* @param stopSequences
* A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop
* generating the response.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder stopSequences(String... stopSequences);
}
static final class BuilderImpl implements Builder {
private Integer maxTokens;
private Float temperature;
private Float topP;
private List stopSequences = DefaultSdkAutoConstructList.getInstance();
private BuilderImpl() {
}
private BuilderImpl(InferenceConfiguration model) {
maxTokens(model.maxTokens);
temperature(model.temperature);
topP(model.topP);
stopSequences(model.stopSequences);
}
public final Integer getMaxTokens() {
return maxTokens;
}
public final void setMaxTokens(Integer maxTokens) {
this.maxTokens = maxTokens;
}
@Override
public final Builder maxTokens(Integer maxTokens) {
this.maxTokens = maxTokens;
return this;
}
public final Float getTemperature() {
return temperature;
}
public final void setTemperature(Float temperature) {
this.temperature = temperature;
}
@Override
public final Builder temperature(Float temperature) {
this.temperature = temperature;
return this;
}
public final Float getTopP() {
return topP;
}
public final void setTopP(Float topP) {
this.topP = topP;
}
@Override
public final Builder topP(Float topP) {
this.topP = topP;
return this;
}
public final Collection getStopSequences() {
if (stopSequences instanceof SdkAutoConstructList) {
return null;
}
return stopSequences;
}
public final void setStopSequences(Collection stopSequences) {
this.stopSequences = InferenceConfigurationStopSequencesListCopier.copy(stopSequences);
}
@Override
public final Builder stopSequences(Collection stopSequences) {
this.stopSequences = InferenceConfigurationStopSequencesListCopier.copy(stopSequences);
return this;
}
@Override
@SafeVarargs
public final Builder stopSequences(String... stopSequences) {
stopSequences(Arrays.asList(stopSequences));
return this;
}
@Override
public InferenceConfiguration build() {
return new InferenceConfiguration(this);
}
@Override
public List> sdkFields() {
return SDK_FIELDS;
}
}
}