Author: Ian Robinson

Amazon Neptune recently released the GraphRAG Toolkit, an open source Python library that makes it straightforward to build graph-enhanced Retrieval Augmented Generation (RAG) workflows. In this post, we describe how you can get started with the toolkit. We begin by looking at the benefits of adding a graph to your RAG application. Then we show you how to set up a quick start environment and install the toolkit. Lastly, we discuss some of the design considerations that led to the toolkit’s graph model and its approach to content retrieval.

Many Amazon Neptune connected data applications for knowledge graphs, identity graphs, and fraud graphs use AWS Lambda functions to query Neptune. This post provides general connection management, error handling, and workload balancing guidance for using any of the popular Gremlin drivers and language variants to connect to Neptune from a Lambda function. The connection management […]

[Updated August 2021] The Gremlin Client for Amazon Neptune is now available from Maven Central. Some APIs have changed since this article was published. Please review the demo code in the GitHub repository for the latest examples of how to use the APIs. Amazon Neptune is a fast, reliable, fully managed graph database service that makes it easy to build and […]

August 30, 2023: Amazon Kinesis Data Analytics has been renamed to Amazon Managed Service for Apache Flink. Read the announcement in the AWS News Blog and learn more. Many graph applications can benefit from the ability to capture changes to items stored in an Amazon Neptune database, at the point in time when such changes […]

December 2022: Whether you’re new to graphs and want to learn and experiment, or you’re experienced and want to refine your queries, Neptune graph notebooks offer a great development platform and can be a huge time-saver. About the Authors Ian Robinson is an architect with the Database Services Customer Advisory Team. He is a coauthor […]