Experimental
@aws-cdk/aws-bedrock-alpha is an experimental (alpha) package: its API may change in any release, without a major version bump.
OpenSearchServerlessVectorStoreProps Struct
Properties for an Amazon OpenSearch Serverless vector store.
The collection and its vector index must already exist. Amazon Bedrock validates at creation time that the index exists in the collection and that its vector field matches the embeddings model. Specify the field names exactly as they are defined in the index.
| Stability | Experimental |
|---|---|
| Source | bedrock/knowledge-bases/vector-store.ts |
| Type last changed |
Example
ts
declare const collection: opensearchserverless.ICollectionRef;
const knowledgeBase = new bedrock.KnowledgeBase(this, 'KnowledgeBase', {
type: 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',
}),
}),
});
python
# collection: opensearchserverless.ICollectionRef
knowledge_base = bedrock.KnowledgeBase(self, "KnowledgeBase",
type=bedrock.KnowledgeBaseType.vector(
embeddings_model=bedrock.BedrockFoundationModel.TITAN_EMBED_TEXT_V2_1024,
vector_store=bedrock.VectorStore.open_search_serverless(
collection=collection,
vector_index_name="bedrock-knowledge-base-default-index",
vector_field="bedrock-knowledge-base-default-vector",
text_field="AMAZON_BEDROCK_TEXT_CHUNK",
metadata_field="AMAZON_BEDROCK_METADATA"
)
)
)
java
ICollectionRef collection;
KnowledgeBase knowledgeBase = KnowledgeBase.Builder.create(this, "KnowledgeBase")
.type(KnowledgeBaseType.vector(VectorKnowledgeBaseTypeProps.builder()
.embeddingsModel(BedrockFoundationModel.TITAN_EMBED_TEXT_V2_1024)
.vectorStore(VectorStore.openSearchServerless(OpenSearchServerlessVectorStoreProps.builder()
.collection(collection)
.vectorIndexName("bedrock-knowledge-base-default-index")
.vectorField("bedrock-knowledge-base-default-vector")
.textField("AMAZON_BEDROCK_TEXT_CHUNK")
.metadataField("AMAZON_BEDROCK_METADATA")
.build()))
.build()))
.build();
csharp
// Install: dotnet add package Amazon.CDK.AWS.Bedrock.Alpha
ICollectionRef collection;
var knowledgeBase = new KnowledgeBase(this, "KnowledgeBase", new KnowledgeBaseProps {
Type = KnowledgeBaseType.Vector(new VectorKnowledgeBaseTypeProps {
EmbeddingsModel = BedrockFoundationModel.TITAN_EMBED_TEXT_V2_1024,
VectorStore = VectorStore.OpenSearchServerless(new OpenSearchServerlessVectorStoreProps {
Collection = collection,
VectorIndexName = "bedrock-knowledge-base-default-index",
VectorField = "bedrock-knowledge-base-default-vector",
TextField = "AMAZON_BEDROCK_TEXT_CHUNK",
MetadataField = "AMAZON_BEDROCK_METADATA"
})
})
});
go
// Install: go get github.com/aws/aws-cdk-go/awsbedrockalpha/v2
var collection ICollectionRef
knowledgeBase := bedrock.NewKnowledgeBase(this, jsii.String("KnowledgeBase"), &KnowledgeBaseProps{
Type: bedrock.KnowledgeBaseType_Vector(&VectorKnowledgeBaseTypeProps{
EmbeddingsModel: bedrock.BedrockFoundationModel_TITAN_EMBED_TEXT_V2_1024(),
VectorStore: bedrock.VectorStore_OpenSearchServerless(&OpenSearchServerlessVectorStoreProps{
Collection: *Collection,
VectorIndexName: jsii.String("bedrock-knowledge-base-default-index"),
VectorField: jsii.String("bedrock-knowledge-base-default-vector"),
TextField: jsii.String("AMAZON_BEDROCK_TEXT_CHUNK"),
MetadataField: jsii.String("AMAZON_BEDROCK_METADATA"),
}),
}),
})
Properties
collectionICollectionRefcollectionICollectionRefcollectionICollectionRefCollectionICollectionRefCollectionICollectionRef required #The OpenSearch Serverless collection that contains the vector index.
metadataFieldstringmetadata_fieldstrmetadataFieldStringMetadataFieldstringMetadataField*string required #The name of the index field that stores the metadata of each chunk.
The name of the index field that stores the raw text of each chunk.
The name of the index field that stores the vector embeddings.
vectorIndexNamestringvector_index_namestrvectorIndexNameStringVectorIndexNamestringVectorIndexName*string required #The name of the vector index in the collection.