Category: Artificial Intelligence

In this post, we present the concepts needed to use a persistent semantic cache in MemoryDB with Knowledge Bases for Amazon Bedrock, and the steps to create a chatbot application that uses the cache. We use MemoryDB as the caching layer for this use case because it delivers the fastest vector search performance at the highest recall rates among popular vector databases on AWS. We use Knowledge Bases for Amazon Bedrock as a vector database because it implements and maintains the RAG functionality for our application without the need of writing additional code.

Data within public blockchain networks such as Bitcoin and Ethereum can be accessed by anyone. However, accessing and making sense of this information has traditionally been a complex and technical undertaking. Much of the data is encoded and stored as bytes, rather than in a human-readable format. In this post, we introduce a solution that demonstrates how you can chat with blockchain data using Amazon Bedrock and the AWS Public Blockchain datasets. We discuss Amazon Bedrock, review the solution architecture, provide example prompts, share interesting findings, and go over how you can extend the solution to integrate with different data sources.

As businesses strive to integrate AI/ML capabilities into their customer-facing services and solutions, they often face the challenge of leveraging massive amounts of relational data hosted on on-premises SQL Server databases. This post showcases how Amazon Relational Database Service (Amazon RDS) for SQL Server and Amazon SageMaker Canvas can work together to address this challenge. By leveraging the native integration points between these managed services, you can develop integrated solutions that use existing relational database workloads to source predictive AI/ML models with minimal effort and no coding required.

In today’s rapidly advancing world of generative artificial intelligence (AI), businesses across diverse industries are transforming customer experiences through the power of real-time search. By harnessing the untapped potential of unstructured data ranging from text to images and videos, organizations are able to redefine the standards of engagement and personalization. A key component of this […]

Retrieval Augmented Generation (RAG) is an innovative approach that combines the power of large language models with external knowledge sources, enabling more accurate and informative generation of content. Using knowledge graphs as sources for RAG (GraphRAG) yields numerous advantages. These knowledge bases encapsulate a vast wealth of curated and interconnected information, enabling the generation of responses that are grounded in factual knowledge. In this post, we show you how to build GraphRAG applications using Amazon Bedrock and Amazon Neptune with LlamaIndex framework.

Schneider Electric is a leader in digital transformation in energy management and industrial automation. To effectively manage customer account hierarchies in its CRM at scale, Schneider Electric started leveraging advances in generative artificial intelligence (AI) large language models (LLMs) in April 2023. They created a solution to make timely updates to their customer account hierarchies in their CRM by linking customer account information to the correct parent company based on the latest information retrieved from the Internet and proprietary datasets. In this post, we explore further iterations of this project and how the team applied what they learned to the Salesforce CRM system using Amazon Aurora and Amazon Bedrock.

In this post, we discuss a design for a highly searchable movie content graph database built on Amazon Neptune, a managed graph database service. We demonstrate how to build a list of relevant movies matching a user’s search criteria through the powerful combination of lexical, semantic, and graphical similarity methods using Neptune, Amazon OpenSearch Service, and Neptune Machine Learning. To match, we compare movies with similar text as well as similar vector embeddings. We use both sentence and graph neural network (GNN) models to build these embeddings.

In this post, we explore the key factors to consider when selecting a database for your generative AI applications. We focus on high-level considerations and service characteristics that are relevant to fully managed databases with vector search capabilities currently available on AWS. We examine how these databases differ in terms of their behavior and performance, and provide guidance on how to make an informed decision based on your specific requirements.

In this post, we discuss how to implement Aurora ML performance optimizations to perform real-time inference against a SageMaker endpoint at a large scale. More specifically, we simulate an OLTP workload against the database, where multiple clients are making simultaneous calls against the database and are putting the SageMaker endpoint under stress to respond to thousands of requests in a short time window. Moreover, we show how to use SQL triggers to create an automatic orchestration pipeline for your predictive workload without using additional services.

In this post, we explore how to use Amazon Aurora PostgreSQL and Amazon Bedrock to build Federal Risk and Authorization Management Program (FedRAMP) compliant generative artificial intelligence (AI) applications using Retrieval Augmented Generation (RAG).