Neo4j has signed a multi-year Strategic Collaboration Agreement (SCA) with Amazon Web Services (AWS). The agreement will see the combination of Amazon Bedrock, LangChain and Neo4j enabling organisations to surface insights from their data with fewer hallucinations.
With AWS re:Invent rapidly approaching, companies are announcing new partnerships with Amazon that often go little further than having their product listed on the AWS marketplace. This agreement goes several steps further, providing an integrated solution that meets the needs of customers.
Where this can make a difference from competitor solutions is the vector search capability within the Neo4j Graph database. The company have now integrated it with Amazon Bedrock. A fully managed service that offers a choice of high-performing foundation models from a variety of platforms.
Sudhir Hasbe, Chief Product Officer, Neo4j, explained, “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. 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.”
In addition, Neo4j also announced the availability of Neo4j Aura Professional in the AWS Marketplace. Neo4J Aura Professional is an always-on graph database as a service for intelligent, context-driven applications using connected data sets. It is build on the leading and widely used graph platforms.
The listing will allow developers to purchase, develop and test applications. Including generative AI capabilities and then scale them using the compute power of the Amazon platform. The Neo4j graph platform allows the customer to create knowledge graphs. Enabling AI systems to reason, infer, and retrieve relevant information effectively. They can help detect correlations between data points that are less obvious as well as confirm those that are more readily apparent.
Stronger in threes
For organisations looking to develop applications using large language models they need access to the foundational model, a vector search engine that can identify the relationship and an application that can build context-aware, reasoning applications. It is the latter part where Langchain fits in this relationship.
Harrison Chase, CEO, of LangChain, said, “LangChain with Neo4j and Amazon Bedrock can now work together using Retrieval Augmented Generation (RAG) to create virtual assistants that are grounded in enterprise knowledge, removing hallucinations and providing more accurate, transparent, and explainable results. It’s a great step forward in helping teams close the gap between the magical user experience that generative AI enables and the work it requires to actually get there.”
For customers, this provides a trinity of solutions that will empower their own efforts. Pablo Lima, CEO, TAG Infraestrutura do Mercado Financeiro commented, “The combination of knowledge graphs by Neo4j and generative AI capabilities by Amazon Bedrock will allow us to build generative AI applications at scale and democratize credit analysis and insights for our market.
“We have all types of data from transactions that include merchants, creditors, location, processing devices, transactions nature, amounts, values, and others – and Neo4j is the perfect database to store these highly connected transactions more efficiently and adjust them to new rules more responsively. Neo4j’s analytical tools and algorithms also help us create new products that provide insights to our partners on how to tailor their products and services better to the merchants and creditors.”
Bedrock and Neo4J combined
The Neo4j integration to Amazon Bedrock will allow organisations to leverage the APIs available to build and scale generative AI applications. Neo4j’s native integration with Amazon Bedrock enables the following benefits:
- Reduced Hallucinations: Neo4j with Langchain and Amazon Bedrock can now work together using Retrieval Augmented Generation (RAG) to create virtual assistants grounded in enterprise knowledge. This helps customers by reducing hallucinations and providing more accurate, transparent, and explainable results.
- Personalized experiences: Neo4j’s context-rich knowledge graphs integration with Amazon Bedrock can invoke a rich ecosystem of foundation models that generate highly personalized text generation and summarization for end users.
- Get complete answers during real-time search: Developers can leverage Amazon Bedrock to generate vector embeddings from unstructured data (text, images, and video) and enrich knowledge graphs using Neo4j’s new vector search and store capability. For example, users can search a retail catalog for products explicitly based on ID or category, or implicitly search based on product descriptions or images.
- Kickstart a knowledge graph creation: Developers can leverage new generative AI capabilities using Amazon Bedrock to process unstructured data so it becomes structured and load it into a knowledge graph. Once in a knowledge graph, users can extract insights and make real-time decisions based on this knowledge.
Atul Deo, General Manager, Amazon Bedrock, AWS, said, “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. 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.”
Enterprise Times: What does this mean?
With the emphasis of enterprises on generative AI, this announcement is timely. AWS re:Invent will provide a host of industry leaders a view of these solutions and consider whether they can take advantage of what is being offered. Neo4j will be demonstrating the new and existing features of its graph database in booth 1304 next week at AWS re:Invent 2023 in Las Vegas, NV.