Automated README summary
Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An unofficial LlamaIndex adapter that adds a Jev-powered reranker (JevRerank) and router selectors (JevSingleSelector, JevMultiSelector) for retrieval-augmented generation pipelines, aimed at developers who want cheaper, typed decisions than LLM-as-judge.
How it uses Jev
JevRerank sends state {query, passage} per passage and asks a Score question (0–3 relevance rubric) to rerank retrieved nodes, keeping top_n. JevSingleSelector asks one Choice over query engine tools; JevMultiSelector asks one Noul per option. Results select the engine or rerank order.
Primitives:scorechoicenoul
Technique worth stealing
One Jev call per passage for reranking to avoid context rot; batch only for routing where state is just the query.
Try it
pip install llama-index-postprocessor-jev or llama-index-selectors-jev; set TYPESAFE_API_KEY or provider keys.
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 excerpt0.39
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersFound in material0.96
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalunclear0.53
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.11 / 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 25 Sept 2026.