Data Analysis

A DuckDB extension that classifies rows with JEV

H Hamilton Ulmer @hamiltonulmer · 2026-09-16

ENData AnalysisHuman-reviewed entry

Cover is generated by this site (not the creator's media).

WHAT IT DOES

The extension puts the classification inside SQL: point it at a CSV, a Parquet file or a DuckDB table and JEV labels the rows where they live.

The author reports about 10 seconds per 1,000 rows, calls it better than reaching for an LLM for the same job, and notes it is far more ergonomic than standing up a classifier.

Reported by the creator on X; the extension was not run here.

Summary written by this site

FROM THE ORIGINAL POST

I made a DuckDB extension where you can use @typesafeai's Jev to do quick classification of rows in any csv/parquet file or duckdb table about 10sec for 1k rows — Hamilton Ulmer · Original post

JEV ROLE

Classification Choice #sql#classification#latency#demo

WHERE IT SITS

HOW IT WORKS

INPUTrows in a CSV / Parquet file or DuckDB table

JEVClassification

OUTPUTa label per row

REPORTED RESULT

Latency~10 s per 1,000 rows

Reported by the creator, not independently verified.

WHAT THE POST SHOWED

No observable metrics recorded. Metrics are only published when they can be tied to a source link.

SOURCE

↗ Original post

Source checked

Evidence is a status, not a ranking. It says how the claim can be checked — not whether the case is good.