Categorygithub.com/cdklabs/generative-ai-cdk-constructs-go/generative-ai-cdk-constructsopensearchserverless
package
0.1.289
Repository: https://github.com/cdklabs/generative-ai-cdk-constructs-go.git
Documentation: pkg.go.dev
Overview
Versions
1
Dependencies
10
Dependents
1
Files
1.2k SLOC

# README

Amazon OpenSearch Serverless Construct Library

---

Stability: Experimental

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 This means that while you may use them, you may need to update your source code when upgrading to a newer version of this package.

LanguagePackage
Typescript Logo TypeScript@cdklabs/generative-ai-cdk-constructs
Python Logo Pythoncdklabs.generative_ai_cdk_constructs

This construct library extends the automatically generated L1 constructs to provide an L2 construct for a vector collection.

Table of contents

API

See the API documentation.

Vector Collection

This resource creates an Amazon OpenSearch Serverless collection configured for VECTORSEARCH. It creates default encryption, network, and data policies for use with Amazon Bedrock Knowledge Bases. For encryption, it uses the default AWS owned KMS key. It allows network connections from the public internet, but access is restricted to specific IAM principals.

Granting Data Access

The grantDataAccess method grants the specified role access to read and write the data in the collection.

# Functions

Experimental.
Experimental.
Import an existing collection using its attributes.
Checks if `x` is a construct.
Returns true if the construct was created by CDK, and false otherwise.
Check whether the given construct is a Resource.
Return metrics for all vector collections.
Metric for the total number of index requests across all collections.
Metric for average search latency across all collections.
Metric for the total number of search requests across all collections.

# Constants

Experimental.
Experimental.
Experimental.
Experimental.
Experimental.
Experimental.
Experimental.
Experimental.
Experimental.
Experimental.
Disable standby replicas to reduce costs.
Enable standby replicas for high availability.
Search – Full-text search that powers applications in your internal networks (content management systems, legal documents) and internet-facing applications, such as ecommerce website search and content search.
Time series – The log analytics segment that focuses on analyzing large volumes of semi-structured, machine-generated data in real-time for operational, security, user behavior, and business insights.
Vector search – Semantic search on vector embeddings that simplifies vector data management and powers machine learning (ML) augmented search experiences and generative AI applications, such as chatbots, personal assistants, and fraud detection.

# Structs

Attributes for importing an existing vector collection.
Properties for configuring the vector collection.

# Interfaces

Interface representing a vector collection.
Provides a vector search collection in Amazon OpenSearch Serverless.

# Type aliases

Copyright Amazon.com, Inc.
Experimental.
Experimental.
Configuration for standby replicas in a vector collection.
The type of collection.