Home icon

Using knowledge graphs to build GraphRAG applications with Amazon Bedrock and Amazon Neptune

Database Blog



This article discusses using knowledge graphs with Amazon Bedrock and Amazon Neptune to build GraphRAG (Retrieval Augmented Generation) applications. GraphRAG combines large language models with external knowledge sources like knowledge graphs to generate more accurate and informative content.

Specifically, the article covers:

  • Benefits of using knowledge graphs as sources for RAG (GraphRAG)
  • Overview of the GraphRAG solution with Amazon Bedrock and Amazon Neptune
  • Setting up a Customer 360 knowledge graph in Amazon Neptune
  • Configuring Amazon Bedrock with LlamaIndex framework
  • Integrating Amazon Neptune with LlamaIndex
  • Configuring the retriever for Neptune to perform retrieval and reasoning
  • Interacting with the knowledge graph by providing prompts and getting personalized responses
  • Conclusion on implementing GraphRAG using Amazon services


Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Jun 2
2025
Build GraphRAG applications using Amazon Bedrock Knowledge Bases
Dec 4
2024
Amazon Bedrock Knowledge Bases now supports GraphRAG (preview)
Mar 7
2025
Amazon Bedrock Knowledge Bases supports GraphRAG now generally available
Mar 7
2025
Announcing general availability of Amazon Bedrock Knowledge Bases GraphRAG with Amazon Neptune Analytics

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.