Jev in production › SQL and data pipelines

duckdb-jev

DuckDB extension whose jev_choice, jev_score, jev_noul and jev_ask SQL functions send each row's text to Jev with constant criteria and return a typed column: an ENUM, a DOUBLE score or probability, or a STRUCT.

Open on GitHub ↗

The source publishes no measured number.
Use
SQL and data pipelines
Industry
Data and analytics
Form
Open-source tool
Stage
Beta
Plugs into
DuckDB
Listed
2026-09-19
Found via
github
Repository
colliber/duckdb-jev
Stars
29
Forks
1
Last push
2026-09-18
Language
C++
License
MIT
duckdb-jev screenshot
docs/demo.gif in the colliber/duckdb-jev README, MIT; shown from GitHub.

The README opens with

Ask a question about every row of a table, in SQL, and get a real SQL type back. A DuckDB extension over Jev, TypeSafe's model for typed answers instead of text.

The data you want to ask about already sits in a table or a Parquet file, and SQL is the query language everyone has. So ask the question where the data is, instead of pulling it out, wrapping an API in a script and writing the answer back.

Jev picks from a set you define instead of writing an answer you then check. The result is typed by construction, not by validation, and not generating is what makes it cheap enough to run on every row.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for sql and data pipelines