HhotchpotchApplications

jev-reranker

Jev-powered relevance filtering and reranking for RAG in Python.

Explore repository

How it uses Jev

jev-reranker: Relevance Filtering & Reranking for RAG

Highlights

  • Relevance filtering scores documents for their contribution to an answer,
  • A configurable threshold determines which documents to keep. Results are sorted
  • Prompts are Python dictionaries. You can change the instructions and criteria
  • Long candidate lists are split automatically. Document limits and split budgets
  • Sync and async methods share request handling, concurrency limits, retries,
  • Optional details record all scores, including excluded documents, along with

Getting started

Requires Python 3.11+ and a TypeSafe API key. Jev API usage is billed by the service.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jev-reranker

Browse all
jev-rag-benchmark project preview

jev-rag-benchmark

Benchmarks & research
Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG
EMade byerendikmenn14
jev-rerank project preview

jev-rerank

Applications
Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.
HMade byhev11
jselect project preview

jselect

Applications
Selects source-linked evidence within a token budget using Jev Noul relevance judgments and local diversity-aware selection.
KMade bykeltokhy3
bili-hardcore-jev project preview

bili-hardcore-jev

Applications
用 JEV（TypeSafe System One 判断模型）自动完成 B 站「硬核会员试炼」的单文件 Python 脚本：手机只扫码登录一次，100 题在电脑上自动答完，零第三方依赖。
YMade byyanglei070-ux2
llama-index-jev project preview

llama-index-jev

Integrations
LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge.
WMade byWiktorB20044
jev-filter project preview

jev-filter

Benchmarks & research
Semantic filtering for AI tool results. Native npm CLI, caller-controlled context, batching, and reproducible benchmarks.
AMade byapixly-ai1
Milvus Model project preview

Milvus Model

Integrations
Python reranker adapter that sends candidate documents as Jev Noul questions in one request, then sorts the returned scores and preserves original document indices.
MMade bymilvus-io0

Search with Jev and Milvus

Demos & playgrounds
Nine runnable notebooks combine Gemini embeddings and Milvus retrieval with Jev judgments for reranking, filtering, search stopping, routing, cache reuse, curation, guardrails, and evaluation.
CMade byCommunity contributor
jev-starter project preview

jev-starter

Benchmarks & research
Typed, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.
HMade byhamakyo2