AI to connect Building Information Databases

Retrieval Augmented Generation (RAG) is a cutting-edge approach that enhances AI models by integrating external knowledge sources during the generation process, enabling more accurate and context-aware outputs.
Existing no-code solutions, such as Azure OpenAI Search and Copilot Studio, make RAG accessible to users without programming expertise, simplifying the integration of AI into various workflows.
In the design domain, the AI-Assistants plug-in for Rhino demonstrates how no-code RAG tools can streamline complex tasks, including navigating design regulations and Environmental Product Declaration (EPD) databases.
Additionally, RAG supports Life Cycle Assessment (LCA) processes by facilitating informed resource selection, as exemplified by the integration with tools like One Click LCA, empowering designers and engineers to make data-driven sustainability decisions efficiently.

Workshop Outline

1. Introduction to Retrieval Augmented Generation (RAG)
2. Review of existing no-code approaches for RAG: Azure OpenAI search & Copilot Studio
3. No-code RAG with the AI-Assistants plug-in for Rhino
4. Navigating Design Regulations
5. Navigating EPD Databases
6. Choosing Resources for LCA with RAG and One Click LCA

Event Venue

Online