Interface CfnDataSource.ChunkingConfigurationProperty
- All Superinterfaces:
software.amazon.jsii.JsiiSerializable
- All Known Implementing Classes:
CfnDataSource.ChunkingConfigurationProperty.Jsii$Proxy
- Enclosing class:
CfnDataSource
A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
Example:
// The code below shows an example of how to instantiate this type. // The values are placeholders you should change. import software.amazon.awscdk.services.bedrock.*; ChunkingConfigurationProperty chunkingConfigurationProperty = ChunkingConfigurationProperty.builder() .chunkingStrategy("chunkingStrategy") // the properties below are optional .fixedSizeChunkingConfiguration(FixedSizeChunkingConfigurationProperty.builder() .maxTokens(123) .overlapPercentage(123) .build()) .hierarchicalChunkingConfiguration(HierarchicalChunkingConfigurationProperty.builder() .levelConfigurations(List.of(HierarchicalChunkingLevelConfigurationProperty.builder() .maxTokens(123) .build())) .overlapTokens(123) .build()) .semanticChunkingConfiguration(SemanticChunkingConfigurationProperty.builder() .breakpointPercentileThreshold(123) .bufferSize(123) .maxTokens(123) .build()) .build();
- See Also:
-
Nested Class Summary
Modifier and TypeInterfaceDescriptionstatic final class
A builder forCfnDataSource.ChunkingConfigurationProperty
static final class
An implementation forCfnDataSource.ChunkingConfigurationProperty
-
Method Summary
Modifier and TypeMethodDescriptionbuilder()
Knowledge base can split your source data into chunks.default Object
Configurations for when you choose fixed-size chunking.default Object
Settings for hierarchical document chunking for a data source.default Object
Settings for semantic document chunking for a data source.Methods inherited from interface software.amazon.jsii.JsiiSerializable
$jsii$toJson
-
Method Details
-
getChunkingStrategy
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 thefixedSizeChunkingConfiguration
.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 Also:
-
getFixedSizeChunkingConfiguration
Configurations for when you choose fixed-size chunking.If you set the
chunkingStrategy
asNONE
, exclude this field.- See Also:
-
getHierarchicalChunkingConfiguration
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.
- See Also:
-
getSemanticChunkingConfiguration
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.
- See Also:
-
builder
-