This article was originally published on The New Stack on June 10, 2024. Retrieval augmented generation (RAG) has emerged as a leading pattern to combat hallucinations and other inaccuracies that affect large language model content generation. However, RAG needs the right data architecture around it to scale effectively and efficiently.

While cloud computing adoption continues to accelerate due to its tremendous value, it has also become clear that edge computing is better suited for a variety of use cases. Organizations are realizing the benefits of processing data closer to its source, leading to reduced latency, security and compliance benefits, and more efficient bandwidth utilization as well as supporting scenarios where networking has challenging constraints.

Modern edge computing is transforming industries including manufacturing, healthcare, transportation, defense, retail, energy, and much more—pushing data management to far-reaching data sources to enable connected, low latency operations and enhanced decision making. These new use cases shift workloads to the left—requiring real-time data streaming and processing at the edge, right where the data is generated.

Until recently, customers didn't have an easy way to send data from Confluent’s data streaming platform to Amazon OpenSearch. They had to either write custom code using AWS Lambda as an intermediary, refactor the HTTP Sink connector, or self-manage an old Elasticsearch connector version. Earlier this year, we announced the fully managed OpenSearch Sink connector, providing a seamless way to sink data from Confluent to Amazon OpenSearch.

Confluent is thrilled to be named Microsoft’s 2024 OSS on Azure Global Partner of the Year. As a three-time Partner of the Year award winner, this recognition reflects our commitment to delivering outstanding open source-based applications and infrastructure solutions on Microsoft Azure.

In today’s hyper-connected world, systems are more intertwined and complex than ever. Myriad data sources including applications, databases, network and IoT devices continuously generate vast amounts of data, capturing every event and interaction. Imagine harnessing this data–login logs, firewall logs, IPS logs, web logins–aggregating it, and analyzing it to create a holistic view of your entire infrastructure.

In this post, we demonstrate how a robust and scalable generative artificial intelligence (GenAI) chatbot is built using Amazon Bedrock and Confluent Cloud. We walk through the architecture and implementation of this generative AI chatbot, and see how it uses Confluent's real-time event streaming capabilities along with Amazon's infrastructure to continually stay up to date with the latest advances from the AI landscape.

In the space of APIs for consuming up-to-date data (say, events or state available within an hour of occurring) many API paradigms exist. There are file- or object-based paradigms, e.g., S3 access. There’s database access, e.g., direct Snowflake access. Last, we have decoupled client-server APIs, e.g., REST APIs, gRPC, webhooks, and streaming APIs.

As government agencies work to improve both customer experience and operational efficiency, two tools have become critical: cloud services and data. Confluent and Amazon Web Services (AWS) have collaborated to make the move to and management of cloud easier while also enabling data streaming for real-time insights and action. We’ll be at the AWS Public Sector Summit in Washington, DC on June 26-27 to talk about and demo how our solutions work together.