Neo4j entered into a multi-year Strategic Collaboration Agreement (SCA) with AWS in a collaboration that aims to enhance generative AI outcomes by combining knowledge graphs and native vector search. 

The goal is to reduce generative AI hallucinations, making results more accurate, transparent, and explainable. This partnership addresses a common challenge for developers working with LLMs, providing a solution for establishing long-term memory in LLMs grounded in specific enterprise data and domains.

“Neo4j has been an AWS Partner since 2013 – with this latest collaboration representing an essential union of graph technology and cloud computing excellence in a new era of AI,” said Sudhir Hasbe, the chief product officer at Neo4j. “Together, we empower enterprises seeking to leverage generative AI to better innovate, provide the best outcome for their customers, and unlock the true power of their connected data at unprecedented speed.”

Neo4j has made its fully managed graph database offering, Neo4j Aura Professional, generally available on AWS Marketplace. It offers a quick start for developers working on generative AI. 

Neo4j is a graph database featuring native vector search, capable of capturing explicit and implicit relationships and patterns. It is utilized in creating knowledge graphs, which enhance the ability of AI systems to reason, infer, and retrieve pertinent information. The database’s  capabilities position it as an enterprise database suitable for grounding LLMs while also serving as long-term memory, according to the company. 

Neo4j is also releasing a new integration with Amazon Bedrock, a fully managed service that makes foundation models from leading AI companies accessible via an API to build and scale generative AI applications. The new integration will reduce AI hallucinations, offer personalized experiences, allow users to get complete answers during real-time search, and kickstart knowledge graph creation to process unstructured data so it becomes structured and load it into a knowledge graph. 

“At AWS, we remain committed to empowering organizations with a diversity of tools and resources to build generative AI solutions that align with their unique customer experiences, applications, and business requirements, said Atul Deo, the general manager at Amazon Bedrock, AWS. “With Neo4j’s graph database and Amazon Bedrock’s integration, we aim to provide customers sophisticated options to deliver more accurate, transparent, and personalized experiences for their end-users in a fully managed manner.”