HAQM Bedrock Knowledge Bases now supports GraphRAG (preview)
Today, we are announcing the support of GraphRAG, a new capability in HAQM Bedrock Knowledge Bases that enhances Generative AI applications by providing more comprehensive, relevant and explainable responses using RAG techniques combined with graph data. HAQM Bedrock Knowledge Bases offers fully-managed, end-to-end Retrieval-Augmented Generation (RAG) workflows to create highly accurate, low latency, and custom Generative AI applications by incorporating contextual information from your company's data sources. HAQM Bedrock Knowledge Bases now offers a fully-managed GraphRAG capability with HAQM Neptune Analytics.
Previously, customers faced challenges in conducting exhaustive, multi-step searches across disparate content. By identifying key entities across documents, GraphRAG delivers insights that leverage relationships within the data, enabling improved responses to end users. For example, users can ask a travel application for family-friendly beach destinations with direct flights and good seafood restaurants. Developers building Generative AI applications can enable GraphRAG in just a few clicks by specifying their data sources and choosing HAQM Neptune Analytics as their vector store when creating a knowledge base. This will automatically generate and store vector embeddings in HAQM Neptune Analytics, along with a graph representation of entities and their relationships.
GraphRAG with HAQM Neptune is built right into HAQM Bedrock Knowledge Bases, offering an integrated experience with no additional setup or additional charges beyond the underlying services. GraphRAG is available in AWS Regions where HAQM Bedrock Knowledge Bases and HAQM Neptune Analytics are both available (see current list of supported regions). To learn more, visit the HAQM Bedrock User Guide.