User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Repos & SDKs
JevRetriever
A Python retrieval framework that wraps an existing base retriever and asks TypeSafe Jev after each pass whether the accumulated evidence is sufficient or another retrieval round is useful. Jev judges sufficiency, coverage, relevance, redundancy and missing information.
- Stars
- 0
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- Aditya-on
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open source
Highlights
- Wraps your own retriever; Jev decides whether the accumulated evidence is sufficient or another pass is useful.
- Each round Jev evaluates sufficiency, coverage, relevance, redundancy and missing information.
- On a yes it stops; on a no it retrieves again with the same query, and it always stops at a maximum retrieval limit.
- Ships as the jevretrieve package on PyPI; the README pins release 0.1.3.
- The base retriever stays responsible for finding documents; Jev acts only as evidence evaluator and retrieval controller.
Quickstart
bash
pip install jevretrieveWatch out
README reviewed 2026-10-17; the repository is MIT-licensed, but the captured text ends mid quick-start, so the full API surface, how Jev is authenticated, and any latency or accuracy numbers are not documented here.
Questions about this entry
Short answers drawn from the linked project or page.
A reusable retrieval framework for Python that wraps an existing base retriever and uses TypeSafe Jev to decide whether the evidence gathered so far is enough or whether another retrieval pass is worth running.
After the base retriever returns documents, Jev evaluates the accumulated evidence; a sufficient answer stops the loop, a no triggers another pass with the same query, and a maximum retrieval limit always stops it.
The README lists five checks: sufficiency, coverage, relevance, redundancy and missing information. Those judgments decide whether to keep retrieving; the base retriever remains responsible for finding documents.
From PyPI with pip install jevretrieve; the README also shows pinning the release with pip install jevretrieve==0.1.3. The captured quick-start imports JevRetriever and RetrievedDocument.
No. You supply a retriever class with a retrieve method returning objects such as RetrievedDocument with text, document_id and score; Jev only evaluates the evidence and controls the loop.
The captured README does not price anything or spell out how Jev is called; the only usage step it documents is the jevretrieve package itself, so check the repository for current Jev billing details.
It is Aditya-on's repository, MIT-licensed, created 2026-10-02 and last pushed 2026-10-03; it has no stars or forks, and the README documents release 0.1.3 published to PyPI.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: A RAG loop where Jev decides what is real
X: Measuring what Jev does in a RAG pipeline
X: Jev-powered reranking for RAG. Likitd_’s jev-ranker uses Jev to rerank results in a RAG pipeline.
X: Coverage is not product value
More Jev resources like this
A System One layout optimizer for decision-model workloads: it reorders rows and fields so a prefix-caching backend reuses input computation, then returns per-record decisions in original order. Its bundled backend serves AutoTrust JEV-9B through vLLM.
Jev Repos & SDKs#community#github#python
Community
0814wdwd/solo_jevPython
0814wdwd/solo_jevPythonA Python library that turns Jev-style decision models into ordinary function calls: check returns a bool, classify picks one option, label picks every option that applies, and score rates on a scale, with probabilities behind every answer.
Jev Repos & SDKs#community#github#python
Community
jlowin/vibecheckPython
jlowin/vibecheckPythonA semantic database built on the DuckDB ecosystem that runs classification, semantic joins and scoring over text as ordinary SQL. It batches decisions on a Jev model and returns probabilities, labels and scores directly, without generated explanations.
Jev Repos & SDKs#community#github#database
Community
pdais/jevdbC++
pdais/jevdbC++A frozen decision server that serves Gemma 4 31B — quantized to FP8 at startup — in TypeSafe's /v1/systemone format, reading the next-token distribution instead of generating tokens. It needs one FP8 NVIDIA GPU with 80 GB and has no authentication.
Jev Repos & SDKs#community#github#python
Community
krishna-gogineni-765/deck31bPython
krishna-gogineni-765/deck31bPythonA reproducible PyTorch stack for cross-sectional factor research: 213 mask-aware factors, cost-aware backtests and auditable reports, plus a preview typed portfolio-decision adapter in the System-One/Jev style.
Jev Repos & SDKs#community#github#python
Community
initial-d/ml-quant-tradingPython
initial-d/ml-quant-tradingPythonA Bangla-focused adaptation of Laya, the non-autoregressive typed-decision model: targeted data preparation, fine-tuning and evaluation for classification, routing and scoring on Bangla, Banglish and code-switched text, with the checkpoint still to come.
Jev Repos & SDKs#community#github#python
Community
shamspias/laya-banglaPython
shamspias/laya-banglaPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.