Jev in production › SQL and data pipelines

JevSDSQL

PostgreSQL-backed database with 41 semantic SQL operators built on Jev's Choice, Score and Noul for classification, extraction, ranking, matching and checks. Jev query planning cost $0.389 per 100 BIRD attempts vs $3.262 for an LLM, at lower accuracy (author).

Open on GitHub ↗

$0.389measured against a baseline, as published by the source
Use
SQL and data pipelines
Industry
Data and analytics
Form
Open-source tool
Stage
In production
Plugs into
PostgreSQL
Listed
2026-09-24
Found via
github
Repository
Sheltercosmo/JevSDSQL
Stars
238
Forks
17
Last push
2026-10-07
Language
Python
License
Apache-2.0

The README opens with

Natural language to SQL and semantic operators for PostgreSQL

Website · Quick start · Existing PostgreSQL · Advantages · Benchmark · What you can build · Project guide · Installation · User guide · 简体中文 · Function reference · Documentation

jev4pg is a carefully designed JEV harness, brings semantic intelligence to PostgreSQL with a comprehensive toolkit of 41 JEV operators for filtering, extraction, ranking, matching and verification. Build semantic search, document workflows and analyst tools on your existing data, with natural-language queries in English and Simplified Chinese.

Badge

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

Listed in Jev in production

Also used for sql and data pipelines