Jev in production › SQL and data pipelines
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).
Natural language to SQL and semantic operators for PostgreSQL
Website · Quick start · Existing PostgreSQL · Advantages · Performance · NL2SQL benchmark · What you can build · Project guide · Installation · User guide · 简体中文 · Function reference · Documentation
jev4pg brings semantic intelligence to PostgreSQL 14–17 with 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.
For the project's own README, linking back here: