Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A PostgreSQL extension that lets you filter, rank and classify table rows using plain-language conditions, powered by TypeSafe's Jev System One model. For analysts and developers who want semantic queries without embeddings or vector columns.
How it uses Jev
Jev judges each row against a condition, returning calibrated probabilities. Used in SQL via jev() as a boolean predicate, jev_prob() for ranking, jev_choice() for classification, and jev_score() for ordered levels. Results compose with standard SQL operations.
Primitives:choicescorenoul
Technique worth stealing
Batch rows (20 per request) into one shared state with per-row Noul questions to amortize request overhead and maintain accuracy.
Try it
CREATE EXTENSION jev CASCADE; then use jev(table, 'condition') in queries.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.87
- Shows a System One patternnot found in the excerpt0.19
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.06 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 3 Oct 2026.