jevbooks

← All projects

flink-jev

gbesse/flink-jev

Flink SQL ML_PREDICT provider for TypeSafe Jev semantic yes/no decisions.

Automated README summary

Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A community connector that adds a Jev provider to Apache Flink 2.3 ML_PREDICT. For each eligible row it asks TypeSafe Jev a yes/no question and returns a probability, a route (yes, no, review, failure), and a SHA-256 digest of the text.

How it uses Jev

Jev answers one yes/no question per eligible row, using the row's text column as state. The returned probability is compared to a configurable threshold to pick a route: uncertain answers go to review, network errors and invalid responses to failure. The connector returns probability, route, and state_sha256.

Primitives:choice

Technique worth stealing

Separating uncertain (review) and error (failure) routes from no, so failures never become negative decisions.

Try it

Build with mvn -B verify, put the jar in Flink lib, set JEV_API_KEY, then run the example SQL.

View on GitHub

Start using Jev: API key and your first request →

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-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

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 material0.69
  • Shows a System One patternnot found in the excerpt0.19
  • Describes handling uncertaintynot found in the excerpt0.15
  • Reports measured numbersnot found in the excerpt0.02
  • Is a runnable toolFound in material0.80
  • Top-10 learning shortlist signalnot found in the excerpt0.20
  • Is a replica of the modelnot found in the excerpt0.08
  • Solves a common problem (0–2)score on a 0–2 scale1.14 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.69Shows a System One pattern0.19Describes handling uncertainty0.15Reports measured numbers0.02Is a runnable tool0.80Top-10 learning shortlist signal0.20Is a replica of the model0.0800.51Solves a common problem (0–2)1.14 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.96Inspection0.72Grey zone0.66Funnel0.47Traffic light0.4100.51

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 24 Oct 2026.