Automated README summary
Automatically summarized from the README on 26 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A JSON-in/JSON-out CLI for developers building retrieval and RAG pipelines. It takes an array of candidate documents from BM25, vector search, or any command, and returns them reranked, filtered, or compressed for an LLM.
How it uses Jev
Jev judges relevance, evidence, or passage retention. Rerank scores each candidate's relevance to the query, adding a rerankScore. Filter asks whether each candidate contains usable evidence, adding evidenceScore. Compress asks which sentences or lines to keep, adding compressedText. Results are used to order, drop, or shorten candidates.
Primitives:scorenoul
Technique worth stealing
Use separate Jev Noul checks for ranking, filtering, and compression so each decision stays independent.
Try it
npm install --global jev-reranker, export TYPESAFE_API_KEY, then pipe a JSON array into jev-reranker --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 patternnot found in the excerpt0.38
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.44 / 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 26 Sept 2026.