DXC transforms data exploration for their oil and gas customers with LLM-powered tools
Machine Learning Blog
This article discusses how DXC Technology and AWS collaborated to build an AI assistant using large language models (LLMs) to enable users to access and analyze different data types from various data sources in the oil and gas industry. The AI assistant, powered by Anthropic's Claude models on Amazon Bedrock, consists of several key components:
Specifically, the article covers:
- LLM-powered router that analyzes user queries and routes them to the appropriate tool
- Custom-built tools optimized for different data sources like file systems, tables, and LAS files
- Conversational capabilities that enable understanding context and rewriting queries
- Amazon Bedrock Knowledge Bases for semantic content-based search
- Implementation details of the file search, tables, and LAS tools
- Approach for enabling conversational context and query rewriting
- Conclusion highlighting the benefits of using LLMs and specialized tools for efficient data exploration
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
2024
2026
2025
2024
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.