README
¶
Pinecone 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 This means that while you may use them, you may need to update your source code when upgrading to a newer version of this package.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 Pinecone database to be used for a vector store for a Knowledge Base.
Table of contents
API
See the API documentation.
Pinecone Vector Store
pinecone.NewPineconeVectorStore(&PineconeVectorStoreProps{
ConnectionString: jsii.String("https://your-index-1234567.svc.gcp-starter.pinecone.io"),
CredentialsSecretArn: jsii.String("arn:aws:secretsmanager:your-region:123456789876:secret:your-key-name"),
TextField: jsii.String("question"),
MetadataField: jsii.String("metadata"),
})
Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func NewPineconeVectorStore_Override ¶
func NewPineconeVectorStore_Override(p PineconeVectorStore, props *PineconeVectorStoreProps)
Experimental.
Types ¶
type PineconeVectorStore ¶
type PineconeVectorStore interface {
// Experimental.
ConnectionString() *string
// Experimental.
CredentialsSecretArn() *string
// Experimental.
KmsKey() *string
// Experimental.
MetadataField() *string
// Experimental.
Namespace() *string
// Experimental.
TextField() *string
}
Class to define a PineconeVectorStore. Experimental.
func NewPineconeVectorStore ¶
func NewPineconeVectorStore(props *PineconeVectorStoreProps) PineconeVectorStore
Experimental.
type PineconeVectorStoreProps ¶
type PineconeVectorStoreProps struct {
// Connection string for your Pinecone index management page.
// Experimental.
ConnectionString *string `field:"required" json:"connectionString" yaml:"connectionString"`
// ARN of the secret containing the API Key to use when connecting to the Pinecone database.
//
// Learn more in the link below.
// See: https://www.pinecone.io/blog/amazon-bedrock-integration/
//
// Experimental.
CredentialsSecretArn *string `field:"required" json:"credentialsSecretArn" yaml:"credentialsSecretArn"`
// 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 from your data.
// Experimental.
TextField *string `field:"required" json:"textField" yaml:"textField"`
// If you encrypted your secret, provide the KMS key here so that Bedrock can decrypt it.
// Experimental.
KmsKey *string `field:"optional" json:"kmsKey" yaml:"kmsKey"`
// Name space that will be used for writing new data to your Pinecone database.
// Experimental.
Namespace *string `field:"optional" json:"namespace" yaml:"namespace"`
}
Properties for a PineconeVectorStore. Experimental.
Source Files
Click to show internal directories.
Click to hide internal directories.