Home icon

Search enterprise data assets using LLMs backed by knowledge graphs

Machine Learning Blog



This article demonstrates a solution for searching enterprise data assets using Large Language Models (LLMs) and knowledge graphs, specifically leveraging AWS services like Amazon Bedrock, Amazon Neptune, and Amazon DataZone.

  • Solution integrates metadata from multiple data sources into a unified semantic search platform
  • Uses knowledge graphs to provide reasoning and context for search results
  • Enables natural language queries across enterprise data assets
  • Utilizes AWS services including Step Functions, Lambda, Neptune, and Bedrock
  • Provides a Streamlit-based chatbot UI for querying data assets

The solution combines LLMs' natural language processing with knowledge graphs' structured reasoning to create a powerful, context-aware enterprise search tool that can unlock insights across fragmented data sources.



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

Nov 18
2024
DXC transforms data exploration for their oil and gas customers with LLM-powered tools
Apr 24
2025
Enterprise-grade natural language to SQL generation using LLMs: Balancing accuracy, latency, and scale
May 7
2024
Find and link similar entities in a knowledge graph using Amazon Neptune, Part 1: Full-text search
Mar 25
2025
Enhance enterprise productivity for your LLM solution by becoming an Amazon Q Business data accessor

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.