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 MariaDB native plugin exposing SQL functions that evaluate natural-language conditions against text columns, letting SQL users filter rows by model judgments rather than exact matches or vector search.
How it uses Jev
For each row, jev_all, jev_any and jev_probability send the text plus up to eight conditions in one Jev request and receive calibrated probabilities. jev_all requires all conditions at or above 0.5, jev_any requires one, and jev_probability returns the raw probability; NULL yields NULL without a network call.
Primitives:score
Technique worth stealing
Batch up to eight natural-language conditions into a single Jev request per row, with a per-expression cache keyed on text, conditions and model.
Try it
Build with CMake, copy build/mariadb_jev.so to plugin_dir, run sql/install.sql, and set JEV_API_KEY in the MariaDB server environment.
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 material0.80
- Shows a System One patternFound in material0.79
- Describes handling uncertaintyFound in material0.69
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.77
- Top-10 learning shortlist signalunclear0.40
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 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 19 Oct 2026.