Automated README summary
Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A DuckDB SQL extension that labels, filters and scores table rows using TypeSafe Jev, a decision model. It targets analysts who want classification inside queries instead of exporting rows to a separate service.
How it uses Jev
Each SQL function maps to a Jev question: jev_label/jev_classify send one choice, jev_if/jev_prob/jev_tags send noul questions, jev_score sends a score, and jev_ask sends arbitrary questions in one request. Results return as labels, probabilities, booleans or JSON for use in SELECT, WHERE and GROUP BY.
Primitives:choicescorenoul
Technique worth stealing
Dedupe identical requests, cache answers in memory and on disk, and batch requests 32 at a time to cut cost and latency.
Try it
INSTALL querio_jev FROM community; LOAD querio_jev; CREATE SECRET (TYPE jev, API_KEY '...'); then call jev_label in a query.
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 material0.94
- Shows a System One patternunclear0.59
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalunclear0.47
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.18 / 2
- About JevFound in material0.99
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 19 Oct 2026.