README
¶
OpenSearch Managed Cluster Vector Store Construct Library
---
All classes are under active development and subject to non-backward compatible changes or removal in any future version. These are not subject to the Semantic Versioning model. This means that while you may use them, you may need to update your source code when upgrading to a newer version of this package.
| Language | Package |
|---|---|
 TypeScript |
@cdklabs/generative-ai-cdk-constructs |
 Python |
cdklabs.generative_ai_cdk_constructs |
 Java |
io.github.cdklabs.generative_ai_cdk_constructs |
 .Net |
CdkLabs.GenerativeAICdkConstructs |
 Go |
github.com/cdklabs/generative-ai-cdk-constructs-go/generative-ai-cdk-constructs |
This construct library provides a class that defines an existing OpenSearch managed cluster to be used as a vector store for a Knowledge Base.
Table of contents
API
See the API documentation.
OpenSearch Managed Cluster Vector Store
TypeScript
opensearchmanagedcluster.NewOpenSearchManagedClusterVectorStore(&OpenSearchManagedClusterVectorStoreProps{
DomainArn: jsii.String("arn:aws:es:region:account:domain/your-domain"),
DomainEndpoint: jsii.String("https://your-domain.region.es.amazonaws.com"),
VectorIndexName: jsii.String("your-vector-index"),
FieldMapping: &OpenSearchFieldMapping{
MetadataField: jsii.String("metadata"),
TextField: jsii.String("text"),
VectorField: jsii.String("vector"),
},
})
Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func NewOpenSearchManagedClusterVectorStore_Override ¶
func NewOpenSearchManagedClusterVectorStore_Override(o OpenSearchManagedClusterVectorStore, props *OpenSearchManagedClusterVectorStoreProps)
Experimental.
Types ¶
type OpenSearchFieldMapping ¶
type OpenSearchFieldMapping struct {
// The name of the field in which Amazon Bedrock stores metadata about the vector store.
// Experimental.
MetadataField *string `field:"required" json:"metadataField" yaml:"metadataField"`
// The name of the field in which Amazon Bedrock stores the raw text in chunks from your data.
// Experimental.
TextField *string `field:"required" json:"textField" yaml:"textField"`
// The name of the field in which Amazon Bedrock stores the vector embeddings.
// Experimental.
VectorField *string `field:"required" json:"vectorField" yaml:"vectorField"`
}
Field mapping configuration for OpenSearch vector store. Experimental.
type OpenSearchManagedClusterVectorStore ¶
type OpenSearchManagedClusterVectorStore interface {
// Experimental.
DomainArn() *string
// Experimental.
DomainEndpoint() *string
// Experimental.
FieldMapping() *OpenSearchFieldMapping
// Experimental.
VectorIndexName() *string
}
Class to define an OpenSearchManagedClusterVectorStore. Experimental.
func NewOpenSearchManagedClusterVectorStore ¶
func NewOpenSearchManagedClusterVectorStore(props *OpenSearchManagedClusterVectorStoreProps) OpenSearchManagedClusterVectorStore
Experimental.
type OpenSearchManagedClusterVectorStoreProps ¶
type OpenSearchManagedClusterVectorStoreProps struct {
// The ARN of your OpenSearch Customer Managed Domain.
// Experimental.
DomainArn *string `field:"required" json:"domainArn" yaml:"domainArn"`
// The url of your OpenSearch Managed cluster domain.
// Experimental.
DomainEndpoint *string `field:"required" json:"domainEndpoint" yaml:"domainEndpoint"`
// Configuration for field mappings in the vector store.
//
// Bedrock uses these fields to store your data.
// If you haven't configured these fields in your vector database, your Knowledge Base
// will fail to be created.
// Experimental.
FieldMapping *OpenSearchFieldMapping `field:"required" json:"fieldMapping" yaml:"fieldMapping"`
// The vector index name of your OpenSearch Customer Managed Domain.
// Experimental.
VectorIndexName *string `field:"required" json:"vectorIndexName" yaml:"vectorIndexName"`
}
Properties for an OpenSearchManagedClusterVectorStore. Experimental.
Source Files
Click to show internal directories.
Click to hide internal directories.