← Wednesday, September 30, 2026DatabasesDeep dive

Jev extensions bring typed plain-English classification to DuckDB

duckdb.org by Geertjan Wielenga, Gábor Szárnyas 7 min read Editor score 7/10

Jev returns typed answers and probabilities, and a community DuckDB extension reportedly classifies about 1,000 rows in roughly ten seconds. The approach offers a practical alternative to LIKE filters, per-row chat calls or building a classifier for some data tasks.

What

Jev is a model that returns typed answers and calibrated probabilities instead of generated sentences.

How

Its Noul, Choice, and Score answers correspond to SQL predicates, enums, and ordered values; questions in a request run in parallel.

Why it matters

DuckDB extensions let engineers apply plain-English classification and scoring to rows without training a classifier or parsing generated text.

Read on duckdb.org →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.