Ask NJEMS- natural language queries of NJEMS
Description
This project would pilot the use of Large Language Models (LLMs) to use natural language prompting to produce SQL queries that return data and execute data analysis. This will require pairing one or more LLMs tuned or trained in databases and SQL, with NJEMS database schemas and metadata in order to enable model outputs of figures, tables and possibly charts.
Project Justification
Unlocking greater insights from existing data is likely to directly advance NJDEP goals. Constraints in personnel time and limited report building expertise remain a likely obstacle to rapid and iterative querying that leads to insight.
Attachments
Activity
Show:
Active
Add watchers
Details
Sponsoring Leadership Area
Div. of Information Technology
Sponsoring Leadership Area's Priority
None
Program Area Lead(s)
None
DOIT technical lead(s)
Mike McCormack, Knute Jensen
All Involved Leadership Areas
Div. of Information Technology
Created: 22 October 2024, 20:01
Updated:
23 September 2025, 15:31
Work Plan 187 signed 1/24/2025