Hooking Jev into BigQuery: SQL rows scored as 0-1 probability columns via remote functions

rseroter · x · 2026-09-23

Developer Jeff Nelson connected typesafeai's Jev to BigQuery via a Cloud Run remote function: SQL queries call external code, and every row gets evaluated with Choice and Noul, turning nuanced judgment calls on unstructured data into 0–1 probability columns that can be filtered, aggregated, and joined in SQL.

The approach removes the need for manual labeling — model scores become queryable table fields. A blog post and GitHub repo were promised, and Google developer advocate rseroter amplified it as a great remote-functions use case.

Original post →

More from coding & agent

coding & agent channel →