interface VectorIngestionConfigurationProperty
| Language | Type name |
|---|---|
.NET | Amazon.CDK.Mixins.Preview.AWS.Bedrock.Mixins.CfnDataSourcePropsMixin.VectorIngestionConfigurationProperty |
Go | github.com/aws/aws-cdk-go/awscdkmixinspreview/v2/awsbedrock/mixins#CfnDataSourcePropsMixin_VectorIngestionConfigurationProperty |
Java | software.amazon.awscdk.mixins.preview.services.bedrock.mixins.CfnDataSourcePropsMixin.VectorIngestionConfigurationProperty |
Python | aws_cdk.mixins_preview.aws_bedrock.mixins.CfnDataSourcePropsMixin.VectorIngestionConfigurationProperty |
TypeScript | @aws-cdk/mixins-preview » aws_bedrock » mixins » CfnDataSourcePropsMixin » VectorIngestionConfigurationProperty |
Contains details about how to ingest the documents in a data source.
Example
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { mixins as bedrock_mixins } from '@aws-cdk/mixins-preview/aws-bedrock';
const vectorIngestionConfigurationProperty: bedrock_mixins.CfnDataSourcePropsMixin.VectorIngestionConfigurationProperty = {
chunkingConfiguration: {
chunkingStrategy: 'chunkingStrategy',
fixedSizeChunkingConfiguration: {
maxTokens: 123,
overlapPercentage: 123,
},
hierarchicalChunkingConfiguration: {
levelConfigurations: [{
maxTokens: 123,
}],
overlapTokens: 123,
},
semanticChunkingConfiguration: {
breakpointPercentileThreshold: 123,
bufferSize: 123,
maxTokens: 123,
},
},
contextEnrichmentConfiguration: {
bedrockFoundationModelConfiguration: {
enrichmentStrategyConfiguration: {
method: 'method',
},
modelArn: 'modelArn',
},
type: 'type',
},
customTransformationConfiguration: {
intermediateStorage: {
s3Location: {
uri: 'uri',
},
},
transformations: [{
stepToApply: 'stepToApply',
transformationFunction: {
transformationLambdaConfiguration: {
lambdaArn: 'lambdaArn',
},
},
}],
},
parsingConfiguration: {
bedrockDataAutomationConfiguration: {
parsingModality: 'parsingModality',
},
bedrockFoundationModelConfiguration: {
modelArn: 'modelArn',
parsingModality: 'parsingModality',
parsingPrompt: {
parsingPromptText: 'parsingPromptText',
},
},
parsingStrategy: 'parsingStrategy',
},
};
Properties
| Name | Type | Description |
|---|---|---|
| chunking | IResolvable | Chunking | Details about how to chunk the documents in the data source. |
| context | IResolvable | Context | The context enrichment configuration used for ingestion of the data into the vector store. |
| custom | IResolvable | Custom | A custom document transformer for parsed data source documents. |
| parsing | IResolvable | Parsing | Configurations for a parser to use for parsing documents in your data source. |
chunkingConfiguration?
Type:
IResolvable | Chunking
(optional)
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.
contextEnrichmentConfiguration?
Type:
IResolvable | Context
(optional)
The context enrichment configuration used for ingestion of the data into the vector store.
customTransformationConfiguration?
Type:
IResolvable | Custom
(optional)
A custom document transformer for parsed data source documents.
parsingConfiguration?
Type:
IResolvable | Parsing
(optional)
Configurations for a parser to use for parsing documents in your data source.
If you exclude this field, the default parser will be used.

.NET
Go
Java
Python
TypeScript