AWS CDK Reference

Appearance

v2.274.0

Experimental

@aws-cdk/aws-bedrock-alpha is an experimental (alpha) package: its API may change in any release, without a major version bump.

VectorKnowledgeBaseTypeProps Struct Added in v2.274.0-alpha.0 ​

Properties for a vector knowledge base.

Stability
Experimental
Source
bedrock/knowledge-bases/knowledge-base-type.ts
Type last changed
v2.274.0-alpha.0 · 21 Oct 2026

Example ​

ts
declare const collection: opensearchserverless.ICollectionRef;
declare const role: iam.Role;

new aws_bedrock_cfn.CfnKnowledgeBase(this, 'KnowledgeBase', {
  name: 'product-documentation',
  roleArn: role.roleArn,
  knowledgeBaseConfiguration: { type: 'VECTOR' },
}).with(new bedrock.mixins.KnowledgeBaseTypeConfiguration(bedrock.KnowledgeBaseType.vector({
  embeddingsModel: bedrock.BedrockFoundationModel.TITAN_EMBED_TEXT_V2_1024,
  vectorStore: bedrock.VectorStore.openSearchServerless({
    collection,
    vectorIndexName: 'bedrock-knowledge-base-default-index',
    vectorField: 'bedrock-knowledge-base-default-vector',
    textField: 'AMAZON_BEDROCK_TEXT_CHUNK',
    metadataField: 'AMAZON_BEDROCK_METADATA',
  }),
})));

Properties ​

embeddingsModelBedrockFoundationModelembeddings_modelBedrockFoundationModelembeddingsModelBedrockFoundationModelEmbeddingsModelBedrockFoundationModelEmbeddingsModelBedrockFoundationModelrequired#
The model used to create vector embeddings for the knowledge base.
supplementalDataStorageBucketIBucketRefsupplemental_data_storage_bucketIBucketRefsupplementalDataStorageBucketIBucketRefSupplementalDataStorageBucketIBucketRefSupplementalDataStorageBucketIBucketRef= no supplemental data storage; on…#
The Amazon S3 bucket in which multimedia content extracted from multimodal documents (images, audio, video) is stored.

Required when the knowledge base ingests multimodal content.

default

Default: no supplemental data storage; only text content is ingested

vectorStoreVectorStorevector_storeVectorStorevectorStoreVectorStoreVectorStoreVectorStoreVectorStoreVectorStorerequired#
The vector store in which the embeddings are stored and searched.
vectorTypeVectorTypevector_typeVectorTypevectorTypeVectorTypeVectorTypeVectorTypeVectorTypeVectorType= VectorType.FLOATING_POINT#
The data type of the vector embeddings.