Build a knowledge base with graphs from Amazon Neptune
Note
Building a knowledge base with graphs from Amazon Neptune is in preview and is subject to change.
Amazon Bedrock Knowledge Bases offers a fully managed GraphRAG feature with Amazon Neptune. This functionality uses Retrieval Augmented Generation (RAG) techniques combined with graphs to enhance generative AI applications so that end users can get more accurate and comprehensive responses.
GraphRAG automatically identifies and uses relationships between related entities and structural elements (such as section titles) across documents that are ingested into Amazon Bedrock Knowledge Bases. This means that generative AI applications can deliver more relevant responses in cases where connecting data and reasoning across multiple document chunks is needed.
Amazon Bedrock Knowledge Bases automatically manages the creation and maintenance of the graphs from Amazon Neptune, so you can provide relevant responses to your end users, without relying on expertise in graph techniques.
Amazon Bedrock Knowledge Bases with GraphRAG offers the following benefits:
-
More relevant responses by using contextual information from related entities and document sections.
-
Better summarization by incorporating key content from your data sources while filtering out unnecessary information.
-
More explainable responses by understanding the relationships between different entities in the dataset and providing citations.
GraphRAG is available in AWS Regions where both Amazon Bedrock Knowledge Bases and Amazon Neptune Analytics are both available.
How to build GraphRAG
GraphRAG is fully integrated into Amazon Bedrock Knowledge Bases and uses Amazon Neptune Analytics for graph and vector storage. You can get started using GraphRAG in your knowledge bases with the AWS Management Console, the AWS CLI, or the AWS SDK.
Note
During preview, GraphRAG only supports Amazon S3 as the data source.
To build GraphRAG, you must choose Amazon Neptune Analytics as your vector store. Neptune Analytics is also available if you use Quick create a new vector store flow in the Amazon Bedrock console, which doesn't require you to have any existing Neptune Analytics resources. The knowledge base automatically generates and stores document embeddings in Amazon Neptune, along with a graph representation of entities and their relationships derived from the document corpus.
When your GraphRAG-based application is running, you can continue using the Knowledge Bases API operations to provide end users with more comprehensive, relevant, and explainable responses.
