CBRE and AWS perform natural language queries of structured data using Amazon Bedrock
Machine Learning Blog
This article discusses a collaboration between CBRE and AWS to develop a natural language query (NLQ) environment for CBRE's structured data using Amazon Bedrock, AWS Lambda, Amazon RDS, and Amazon OpenSearch Service.
Specifically, the article covers:
- CBRE's business need for a solution allowing customers to query their data using natural language prompts
- Key requirements for the NLQ solution, including performance and accuracy targets
- The technical architecture leveraging Amazon Bedrock, Lambda, RDS, OpenSearch Service, and other AWS services
- Performance tuning approaches for the solution, such as prompt engineering and inference parameter optimization
- Monitoring and deployment using AWS CDK and various service stacks
- A web UI and API management layer for user testing and integration
- Conclusion highlighting the success of the prototype and its potential for broader adoption
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
Apr 29
2026
2026
Enabling natural language access to structured data using Amazon S3 Tables and Amazon Bedrock Knowledge Bases
Aug 8
2024
2024
Analyze blockchain data with natural language using Amazon Bedrock
Dec 4
2024
2024
Amazon Bedrock Knowledge Bases now supports structured data retrieval
Jan 2
2025
2025
Analyze blockchain data with natural language using Amazon Bedrock
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.