Generative AI and machine learning

Why graphs?

As organizations build and deploy generative artificial intelligence (AI) applications, their expectations for accuracy, comprehensiveness, and explainability are increasing. Providing enterprise and domain-specific context through techniques such as Retrieval Augmented Generation (RAG) can help to an extent— RAG is cost-efficient for providing current and relevant information for generative AI while retaining data governance and control.

Graph Retrieval Augmented Generation (GraphRAG) takes RAG to the next level by harnessing the power of both graph analytics and vector search to enhance the accuracy, comprehensiveness and explainability of AI responses. GraphRAG achieves this by leveraging relationships between entities or structural elements in data, such as sections or titles with chunks of documents, to provide the most relevant data as input to RAG applications. It can make multi-hop connections between related entities or topics and use these facts to augment a generative response.

Amazon Neptune capabilities

1

GraphRAG

Amazon provides fully managed and self managed options for creating and running GraphRAG applications.

  • Fully managed: Amazon Bedrock Knowledge Bases offer one of the world's first fully managed GraphRAG capabilities. It automatically manages the creation and maintenance of graphs and embeddings, enabling customers to provide more relevant responses to end users. With this capability, you avoid the need for deep graph expertise, including creation of chunking strategies or complex RAG integrations with LLMs and vector stores.
  • Self managed: If you are looking to self-host or connect to custom data sources/third-party products (foundational models, vector stores, data stores), you have two choices.
    • AWS GraphRAG Python toolkit: The new open source GraphRAG toolkit supports up-to-date foundational and graph models. It provides a framework for automating the construction of a graph from unstructured data, and for querying this graph when answering user questions.
    • Open source frameworks: Neptune simplifies the creation of GraphRAG applications by integrating with both LangChain and LlamaIndex. This makes it easy to build applications with LLMs such as those available in Amazon Bedrock. AWS supports and contributes to both these popular open source projects.
2

Machine learning

  • Neptune Machine Learning (ML): Neptune ML automatically creates, trains, and applies ML models on your graph data. It uses Deep Graph Library (DGL) to automatically choose and train the best ML model for your workload so that you can make ML-based predictions on graph data in hours instead of weeks.
  • Natural language query generation for graphs: If you’re unfamiliar with query languages such as Gremlin or Cypher, Neptune integration with NeptuneOpenCypherQAChain enables you to question your Neptune graph database using natural language. For example, you can translate English questions into openCypher queries and return a human-readable response. This chain can be used to answer questions such as “Which US airport has the longest and shortest outgoing routes?”.

Use cases

GraphRAG can be used to improve IT service desk and contact center. For instance, GraphRAG can enable Security Operations Center (SOC) teams to interpret alerts more accurately to help secure critical systems. A healthcare member support chatbot can quickly find relevant information from large volumes of medical literature to answer complex questions about patient symptoms, treatments, and outcomes.

GraphRAG applications can serve deep insights for teams in corporate functions such as financial planning & accounting (FP&A), marketing, legal, HR, etc. For instance, corporate legal teams can more effectively find information about tax laws, regulations, and case precedents to ideate on case strategies. Marketing teams can create customer 360 views based on a prospect’s social connections and purchase history.

Companies across industries benefit from GraphRAG. For example, in the pharmaceutical industry, R&D teams can use GraphRAG to speed up drug research and trials. In the investment banking space, GraphRAG's ability to map complex relationships and provide a holistic view of corporate filings, which helps due diligence teams to uncover insights - such as regulatory rights and competitive dynamics - with RAG that are otherwise not readily apparent.

Customers

BMW

“At BMW, we are constantly innovating to deliver superior efficiency and accuracy in data-driven decision-making. We have over 10 PB of data to support analyses across 1,000 use cases in our Cloud Data Hub. Ensuring that the insights are based on reasoning across datasets is a challenge given the diversity of use cases and queries from our 9,000 users. We recently worked with AWS on a prototype where we created a knowledge graph to represent relationships between the data. The accuracy of this solution has transformed how we think about leveraging our unique data in generative AI applications. We are thrilled about the fully managed GraphRAG capability of Amazon Bedrock Knowledge Bases, with its automated graph modeling in Amazon Neptune. This will allow us to serve more relevant and comprehensive insights to teams across all of BMW, so we can continue creating premium experiences for millions of drivers.” Ruben Simon, Head of Product - Cloud Data Hub at BMW Group

Trend Micro

"At Trend Micro, we're leveraging knowledge graph technology via Amazon Bedrock and Amazon Neptune to supercharge our Vision One Companion, the flagship GenAI-powered cybersecurity assistant. With knowledge graphs, Companion seamlessly connects diverse data sources and uncovers complex relationships, all while ensuring multi-tenant and RBAC for our SaaS customers. This enables Companion to swiftly interpret incidents and alerts, generate comprehensive security reports, and initiate real-time, data-driven response actions with enhanced privacy. By harnessing the full potential of security data through Bedrock Knowledge Bases' GraphRAG capabilities and Amazon Neptune's advanced graph technology, we empower SOC teams with contextual and more actionable insights, enabling faster and more accurate responses to critical threats while maintaining robust data security, significantly enhancing overall cybersecurity effectiveness," said Fernando Cardoso, Director of Product Management at Trend Micro

Getting started

There are many ways to get started including: