README
¶
MongoDB Atlas 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 This means that while you may use them, you may need to update your source code when upgrading to a newer version of this package.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 |
MongoDBAtlasVectorStore
The MongoDBAtlasVectorStore construct allows you to define a MongoDB Atlas instance as a vector store for your Amazon Bedrock Knowledge Base.
Usage
vectorStore := mongodbAtlas.NewMongoDBAtlasVectorStore(&MongoDBAtlasVectorStoreProps{
CollectionName: jsii.String("embeddings"),
CredentialsSecretArn: jsii.String("arn:aws:secretsmanager:region:account:secret:secret-name"),
DatabaseName: jsii.String("vectordb"),
Endpoint: jsii.String("https://your-mongodb-atlas-endpoint.mongodb.net"),
EndpointServiceName: jsii.String("mongodb-atlas"),
FieldMapping: &MongoDbAtlasFieldMapping{
VectorField: jsii.String("embedding"),
TextField: jsii.String("text"),
MetadataField: jsii.String("metadata"),
},
VectorIndexName: jsii.String("vector_index"),
})
Properties
The MongoDBAtlasVectorStore construct accepts the following properties:
| Property | Type | Description |
|---|---|---|
collectionName |
string | The name of the collection in MongoDB Atlas |
credentialsSecretArn |
string | The ARN of the AWS Secrets Manager secret containing MongoDB Atlas credentials |
databaseName |
string | The name of the database in MongoDB Atlas |
endpoint |
string | The endpoint URL for MongoDB Atlas |
endpointServiceName |
string | The name of the endpoint service |
fieldMapping |
MongoDbAtlasFieldMapping | The mapping of fields in the MongoDB collection |
vectorIndexName |
string | The name of the vector index in MongoDB Atlas |
Field Mapping
The fieldMapping property defines how fields in your MongoDB collection map to vector store concepts:
| Property | Type | Description |
|---|---|---|
vectorField |
string | The field name for storing vector embeddings |
textField |
string | The field name for storing the original text |
metadataField |
string | The field name for storing additional metadata |
Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func NewMongoDBAtlasVectorStore_Override ¶
func NewMongoDBAtlasVectorStore_Override(m MongoDBAtlasVectorStore, props *MongoDBAtlasVectorStoreProps)
Creates a new instance of the MongoDBAtlas class. Experimental.
Types ¶
type MongoDBAtlasVectorStore ¶
type MongoDBAtlasVectorStore interface {
// The name of the collection.
// Experimental.
CollectionName() *string
// The ARN of the secret containing MongoDB Atlas credentials.
// Experimental.
CredentialsSecretArn() *string
// The name of the database.
// Experimental.
DatabaseName() *string
// The endpoint URL for MongoDB Atlas.
// Experimental.
Endpoint() *string
// The name of the endpoint service.
// Experimental.
EndpointServiceName() *string
// The field mapping for MongoDB Atlas.
// Experimental.
FieldMapping() *MongoDbAtlasFieldMapping
// The name of the text index.
// Experimental.
TextIndexName() *string
// The name of the vector index.
// Experimental.
VectorIndexName() *string
}
Construct for MongoDB Atlas vector store. Experimental.
func NewMongoDBAtlasVectorStore ¶
func NewMongoDBAtlasVectorStore(props *MongoDBAtlasVectorStoreProps) MongoDBAtlasVectorStore
Creates a new instance of the MongoDBAtlas class. Experimental.
type MongoDBAtlasVectorStoreProps ¶
type MongoDBAtlasVectorStoreProps struct {
// The name of the collection.
// Experimental.
CollectionName *string `field:"required" json:"collectionName" yaml:"collectionName"`
// The ARN of the secret containing MongoDB Atlas credentials.
// Experimental.
CredentialsSecretArn *string `field:"required" json:"credentialsSecretArn" yaml:"credentialsSecretArn"`
// The name of the database.
// Experimental.
DatabaseName *string `field:"required" json:"databaseName" yaml:"databaseName"`
// The endpoint URL for MongoDB Atlas.
// Experimental.
Endpoint *string `field:"required" json:"endpoint" yaml:"endpoint"`
// The field mapping for MongoDB Atlas.
// Experimental.
FieldMapping *MongoDbAtlasFieldMapping `field:"required" json:"fieldMapping" yaml:"fieldMapping"`
// The name of the vector index.
// Experimental.
VectorIndexName *string `field:"required" json:"vectorIndexName" yaml:"vectorIndexName"`
// The name of the endpoint service.
// Experimental.
EndpointServiceName *string `field:"optional" json:"endpointServiceName" yaml:"endpointServiceName"`
// The name of the text index.
// Experimental.
TextIndexName *string `field:"optional" json:"textIndexName" yaml:"textIndexName"`
}
Interface for MongoDB Atlas vector store configuration. Experimental.
type MongoDbAtlasFieldMapping ¶
type MongoDbAtlasFieldMapping struct {
// The field name for the metadata field.
// Experimental.
MetadataField *string `field:"required" json:"metadataField" yaml:"metadataField"`
// The field name for the text field.
// Experimental.
TextField *string `field:"required" json:"textField" yaml:"textField"`
// The field name for the vector field.
// Experimental.
VectorField *string `field:"required" json:"vectorField" yaml:"vectorField"`
}
Interface for MongoDB Atlas field mapping. Experimental.
Source Files
Click to show internal directories.
Click to hide internal directories.