Exclusive Content:

Haiper steps out of stealth mode, secures $13.8 million seed funding for video-generative AI

Haiper Emerges from Stealth Mode with $13.8 Million Seed...

Running Your ML Notebook on Databricks: A Step-by-Step Guide

A Step-by-Step Guide to Hosting Machine Learning Notebooks in...

“Revealing Weak Infosec Practices that Open the Door for Cyber Criminals in Your Organization” • The Register

Warning: Stolen ChatGPT Credentials a Hot Commodity on the...

CBRE partners with AWS to utilize Amazon Bedrock for performing natural language queries on structured data

“Unlocking Value with AI in Commercial Real Estate: A Partnership with CBRE”

In today’s rapidly evolving world, the use of artificial intelligence (AI) is becoming increasingly common across various industries. One such industry that is harnessing the power of AI is commercial real estate. CBRE, the world’s largest commercial real estate services and investment firm, is leading the way in unlocking the potential of AI to bring value across the entire commercial real estate lifecycle.

CBRE’s data environment is vast, with 39 billion data points from over 300 sources. To leverage this data efficiently, CBRE partnered with AWS Prototyping to develop a custom query environment that allows natural language query prompts using Amazon Bedrock, AWS Lambda, Amazon Relational Database Service (Amazon RDS), and Amazon OpenSearch Service. This innovative solution enables clients to quickly query existing data using natural language prompts, empowering them to gain insights and make informed decisions in a user-friendly environment.

The key use case and environment requirements for this solution included natural language queries, a scalable solution using a large language model, and the ability to provide results in plain English, reasoning, and SQL code. With a focus on performance tuning, the solution was designed to ensure high accuracy rates, reuse of embeddings for similar queries, and a quick response time of 3-5 seconds.

The technical approach involved the use of Anthropic Claude 2 on Amazon Bedrock, a powerful large language model with 100,000 maximum token support. Prompt engineering and instruction tuning were essential to optimize the input to the model and generate tailored responses. Inference parameters were carefully configured to influence the response generated by the model, ensuring optimal performance.

Monitoring of the solution components was facilitated through Amazon CloudWatch logs and metrics, providing visibility into the system’s performance and health. The deployment of resources was managed using AWS CDK stacks, with each component designed to follow best practices and ensure security and scalability.

Overall, the collaboration between CBRE and AWS Prototyping has resulted in a cutting-edge solution that showcases the potential of AI in commercial real estate. By leveraging AI technologies like Amazon Bedrock, CBRE is at the forefront of digital transformation in the industry, paving the way for smarter decision-making and enhanced client experiences.

To learn more about this innovative project and the technologies involved, feel free to connect with the authors mentioned above. It’s exciting to see how AI is revolutionizing industries like commercial real estate, and CBRE’s journey is a testament to the endless possibilities that AI can unlock.

Latest

Go.Compare Introduces Insurance App Powered by ChatGPT

Go.Compare Launches ChatGPT App for Effortless Insurance Comparison Go.Compare Launches...

Dstl-Backed Robotics Innovation Revolutionizes Military Manufacturing – A Case Study

Revolutionizing Manufacturing: Rivelin Robotics’ Innovations in Precision Finishing for...

Understanding Patient Sentiment in Atopic Dermatitis Management

Insights into Patient Sentiment and Treatment Perceptions in Atopic...

UK Shoppers Cautious About AI-Generated Product Images, Survey Reveals

Trust Issues in AI-Generated eCommerce Content: Insights from Photoroom's...

Don't miss

Haiper steps out of stealth mode, secures $13.8 million seed funding for video-generative AI

Haiper Emerges from Stealth Mode with $13.8 Million Seed...

Running Your ML Notebook on Databricks: A Step-by-Step Guide

A Step-by-Step Guide to Hosting Machine Learning Notebooks in...

Investing in digital infrastructure key to realizing generative AI’s potential for driving economic growth | articles

Challenges Hindering the Widescale Deployment of Generative AI: Legal,...

VOXI UK Launches First AI Chatbot to Support Customers

VOXI Launches AI Chatbot to Revolutionize Customer Services in...

Create Financial Document Processing Solutions Using Pulse AI and Amazon Bedrock

Transforming Financial Document Processing: Leveraging Pulse AI and Amazon Bedrock for Accurate Data Extraction Introduction Financial institutions process thousands of complex documents daily. Optical Character Recognition...

Automating Schema Creation for Smart Document Processing

Streamlining Document Processing: Introducing Multi-Document Discovery for Intelligent Document Processing (IDP) Overcoming Schema Challenges in Large Document Collections The IDP Accelerator: Revolutionizing Document Processing Automated Solution Overview...

Creating Web Search-Enabled Agents Using Strands and Exa

Unlocking Web-Enabled AI Agents: Integrating Exa with Strands Agents SDK Co-authored by Ishan Goswami and Nitya Sridhar from Exa In this comprehensive guide, explore how the...