com.amazonaws.services.bedrockagent.model.ChunkingConfiguration Maven / Gradle / Ivy
Show all versions of aws-java-sdk-bedrockagent Show documentation
/*
* 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.bedrockagent.model;
import java.io.Serializable;
import javax.annotation.Generated;
import com.amazonaws.protocol.StructuredPojo;
import com.amazonaws.protocol.ProtocolMarshaller;
/**
*
* Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source
* that is returned when the knowledge base that it belongs to is queried.
*
*
* @see AWS API Documentation
*/
@Generated("com.amazonaws:aws-java-sdk-code-generator")
public class ChunkingConfiguration implements Serializable, Cloneable, StructuredPojo {
/**
*
* Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source
* that is returned when the knowledge base that it belongs to is queried. You have the following options for
* chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting
* them up such that each file corresponds to a chunk.
*
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that you set
* in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large chunks,
* and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with natural
* language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want to
* pre-process your documents by splitting them into separate files.
*
*
*
*/
private String chunkingStrategy;
/**
*
* Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as
* NONE, exclude this field.
*
*/
private FixedSizeChunkingConfiguration fixedSizeChunkingConfiguration;
/**
*
* Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers
* of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from
* the first layer.
*
*/
private HierarchicalChunkingConfiguration hierarchicalChunkingConfiguration;
/**
*
* Settings for semantic document chunking for a data source. Semantic chunking splits a document into into smaller
* documents based on groups of similar content derived from the text with natural language processing.
*
*/
private SemanticChunkingConfiguration semanticChunkingConfiguration;
/**
*
* Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source
* that is returned when the knowledge base that it belongs to is queried. You have the following options for
* chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting
* them up such that each file corresponds to a chunk.
*
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that you set
* in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large chunks,
* and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with natural
* language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want to
* pre-process your documents by splitting them into separate files.
*
*
*
*
* @param chunkingStrategy
* Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data
* source that is returned when the knowledge base that it belongs to is queried. You have the following
* options for chunking your data. If you opt for NONE, then you may want to pre-process your
* files by splitting them up such that each file corresponds to a chunk.
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that
* you set in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large
* chunks, and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with
* natural language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want
* to pre-process your documents by splitting them into separate files.
*
*
* @see ChunkingStrategy
*/
public void setChunkingStrategy(String chunkingStrategy) {
this.chunkingStrategy = chunkingStrategy;
}
/**
*
* Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source
* that is returned when the knowledge base that it belongs to is queried. You have the following options for
* chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting
* them up such that each file corresponds to a chunk.
*
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that you set
* in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large chunks,
* and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with natural
* language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want to
* pre-process your documents by splitting them into separate files.
*
*
*
*
* @return Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data
* source that is returned when the knowledge base that it belongs to is queried. You have the following
* options for chunking your data. If you opt for NONE, then you may want to pre-process your
* files by splitting them up such that each file corresponds to a chunk.
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that
* you set in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large
* chunks, and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with
* natural language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want
* to pre-process your documents by splitting them into separate files.
*
*
* @see ChunkingStrategy
*/
public String getChunkingStrategy() {
return this.chunkingStrategy;
}
/**
*
* Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source
* that is returned when the knowledge base that it belongs to is queried. You have the following options for
* chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting
* them up such that each file corresponds to a chunk.
*
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that you set
* in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large chunks,
* and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with natural
* language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want to
* pre-process your documents by splitting them into separate files.
*
*
*
*
* @param chunkingStrategy
* Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data
* source that is returned when the knowledge base that it belongs to is queried. You have the following
* options for chunking your data. If you opt for NONE, then you may want to pre-process your
* files by splitting them up such that each file corresponds to a chunk.
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that
* you set in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large
* chunks, and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with
* natural language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want
* to pre-process your documents by splitting them into separate files.
*
*
* @return Returns a reference to this object so that method calls can be chained together.
* @see ChunkingStrategy
*/
public ChunkingConfiguration withChunkingStrategy(String chunkingStrategy) {
setChunkingStrategy(chunkingStrategy);
return this;
}
/**
*
* Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source
* that is returned when the knowledge base that it belongs to is queried. You have the following options for
* chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting
* them up such that each file corresponds to a chunk.
*
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that you set
* in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large chunks,
* and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with natural
* language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want to
* pre-process your documents by splitting them into separate files.
*
*
*
*
* @param chunkingStrategy
* Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data
* source that is returned when the knowledge base that it belongs to is queried. You have the following
* options for chunking your data. If you opt for NONE, then you may want to pre-process your
* files by splitting them up such that each file corresponds to a chunk.
*
* -
*
* FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that
* you set in the fixedSizeChunkingConfiguration.
*
*
* -
*
* HIERARCHICAL – Split documents into layers of chunks where the first layer contains large
* chunks, and the second layer contains smaller chunks derived from the first layer.
*
*
* -
*
* SEMANTIC – Split documents into chunks based on groups of similar content derived with
* natural language processing.
*
*
* -
*
* NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want
* to pre-process your documents by splitting them into separate files.
*
*
* @return Returns a reference to this object so that method calls can be chained together.
* @see ChunkingStrategy
*/
public ChunkingConfiguration withChunkingStrategy(ChunkingStrategy chunkingStrategy) {
this.chunkingStrategy = chunkingStrategy.toString();
return this;
}
/**
*
* Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as
* NONE, exclude this field.
*
*
* @param fixedSizeChunkingConfiguration
* Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as
* NONE, exclude this field.
*/
public void setFixedSizeChunkingConfiguration(FixedSizeChunkingConfiguration fixedSizeChunkingConfiguration) {
this.fixedSizeChunkingConfiguration = fixedSizeChunkingConfiguration;
}
/**
*
* Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as
* NONE, exclude this field.
*
*
* @return Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as
* NONE, exclude this field.
*/
public FixedSizeChunkingConfiguration getFixedSizeChunkingConfiguration() {
return this.fixedSizeChunkingConfiguration;
}
/**
*
* Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as
* NONE, exclude this field.
*
*
* @param fixedSizeChunkingConfiguration
* Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as
* NONE, exclude this field.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public ChunkingConfiguration withFixedSizeChunkingConfiguration(FixedSizeChunkingConfiguration fixedSizeChunkingConfiguration) {
setFixedSizeChunkingConfiguration(fixedSizeChunkingConfiguration);
return this;
}
/**
*
* Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers
* of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from
* the first layer.
*
*
* @param hierarchicalChunkingConfiguration
* Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into
* layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks
* derived from the first layer.
*/
public void setHierarchicalChunkingConfiguration(HierarchicalChunkingConfiguration hierarchicalChunkingConfiguration) {
this.hierarchicalChunkingConfiguration = hierarchicalChunkingConfiguration;
}
/**
*
* Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers
* of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from
* the first layer.
*
*
* @return Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents
* into layers of chunks where the first layer contains large chunks, and the second layer contains smaller
* chunks derived from the first layer.
*/
public HierarchicalChunkingConfiguration getHierarchicalChunkingConfiguration() {
return this.hierarchicalChunkingConfiguration;
}
/**
*
* Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers
* of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from
* the first layer.
*
*
* @param hierarchicalChunkingConfiguration
* Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into
* layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks
* derived from the first layer.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public ChunkingConfiguration withHierarchicalChunkingConfiguration(HierarchicalChunkingConfiguration hierarchicalChunkingConfiguration) {
setHierarchicalChunkingConfiguration(hierarchicalChunkingConfiguration);
return this;
}
/**
*
* Settings for semantic document chunking for a data source. Semantic chunking splits a document into into smaller
* documents based on groups of similar content derived from the text with natural language processing.
*
*
* @param semanticChunkingConfiguration
* Settings for semantic document chunking for a data source. Semantic chunking splits a document into into
* smaller documents based on groups of similar content derived from the text with natural language
* processing.
*/
public void setSemanticChunkingConfiguration(SemanticChunkingConfiguration semanticChunkingConfiguration) {
this.semanticChunkingConfiguration = semanticChunkingConfiguration;
}
/**
*
* Settings for semantic document chunking for a data source. Semantic chunking splits a document into into smaller
* documents based on groups of similar content derived from the text with natural language processing.
*
*
* @return Settings for semantic document chunking for a data source. Semantic chunking splits a document into into
* smaller documents based on groups of similar content derived from the text with natural language
* processing.
*/
public SemanticChunkingConfiguration getSemanticChunkingConfiguration() {
return this.semanticChunkingConfiguration;
}
/**
*
* Settings for semantic document chunking for a data source. Semantic chunking splits a document into into smaller
* documents based on groups of similar content derived from the text with natural language processing.
*
*
* @param semanticChunkingConfiguration
* Settings for semantic document chunking for a data source. Semantic chunking splits a document into into
* smaller documents based on groups of similar content derived from the text with natural language
* processing.
* @return Returns a reference to this object so that method calls can be chained together.
*/
public ChunkingConfiguration withSemanticChunkingConfiguration(SemanticChunkingConfiguration semanticChunkingConfiguration) {
setSemanticChunkingConfiguration(semanticChunkingConfiguration);
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 (getChunkingStrategy() != null)
sb.append("ChunkingStrategy: ").append(getChunkingStrategy()).append(",");
if (getFixedSizeChunkingConfiguration() != null)
sb.append("FixedSizeChunkingConfiguration: ").append(getFixedSizeChunkingConfiguration()).append(",");
if (getHierarchicalChunkingConfiguration() != null)
sb.append("HierarchicalChunkingConfiguration: ").append(getHierarchicalChunkingConfiguration()).append(",");
if (getSemanticChunkingConfiguration() != null)
sb.append("SemanticChunkingConfiguration: ").append(getSemanticChunkingConfiguration());
sb.append("}");
return sb.toString();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (obj instanceof ChunkingConfiguration == false)
return false;
ChunkingConfiguration other = (ChunkingConfiguration) obj;
if (other.getChunkingStrategy() == null ^ this.getChunkingStrategy() == null)
return false;
if (other.getChunkingStrategy() != null && other.getChunkingStrategy().equals(this.getChunkingStrategy()) == false)
return false;
if (other.getFixedSizeChunkingConfiguration() == null ^ this.getFixedSizeChunkingConfiguration() == null)
return false;
if (other.getFixedSizeChunkingConfiguration() != null
&& other.getFixedSizeChunkingConfiguration().equals(this.getFixedSizeChunkingConfiguration()) == false)
return false;
if (other.getHierarchicalChunkingConfiguration() == null ^ this.getHierarchicalChunkingConfiguration() == null)
return false;
if (other.getHierarchicalChunkingConfiguration() != null
&& other.getHierarchicalChunkingConfiguration().equals(this.getHierarchicalChunkingConfiguration()) == false)
return false;
if (other.getSemanticChunkingConfiguration() == null ^ this.getSemanticChunkingConfiguration() == null)
return false;
if (other.getSemanticChunkingConfiguration() != null
&& other.getSemanticChunkingConfiguration().equals(this.getSemanticChunkingConfiguration()) == false)
return false;
return true;
}
@Override
public int hashCode() {
final int prime = 31;
int hashCode = 1;
hashCode = prime * hashCode + ((getChunkingStrategy() == null) ? 0 : getChunkingStrategy().hashCode());
hashCode = prime * hashCode + ((getFixedSizeChunkingConfiguration() == null) ? 0 : getFixedSizeChunkingConfiguration().hashCode());
hashCode = prime * hashCode + ((getHierarchicalChunkingConfiguration() == null) ? 0 : getHierarchicalChunkingConfiguration().hashCode());
hashCode = prime * hashCode + ((getSemanticChunkingConfiguration() == null) ? 0 : getSemanticChunkingConfiguration().hashCode());
return hashCode;
}
@Override
public ChunkingConfiguration clone() {
try {
return (ChunkingConfiguration) 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.bedrockagent.model.transform.ChunkingConfigurationMarshaller.getInstance().marshall(this, protocolMarshaller);
}
}