Retrieval reranking and RAG with decision models

Worked Jev examples for ticket triage and reranking, runnable through OpenRouter without an early-access key, with offline tests.

Research agent where GPT plans and Jev finds evidence in parallel across document regions with Choice and Noul.

Agent memory system where Jev or local Laya controls memory organisation, query routing, retrieval budgets and stopping.

Compares Jev's zero-shot reranking with specialist rerankers on MS MARCO passage and document benchmarks and a TREC WSJ transfer test.

Benchmark of BM25, embeddings, rerankers and Jev for picking the right MCP tool among 525, plus an experimental Jev search engine.

Pull request adding Jev to station-suggestion reranking in the TrainLCD transit app's Cloudflare Worker backend.

248 small installable TypeScript recipes that each make one typed Jev decision: route, rerank, gate, grade, compare or label.

Zilliz's cross-agent Markdown memory with an optional Jev reranker that asks yes/no relevance questions about retrieved chunks.

Milvus's model library with a Jev reranker that sends candidate documents as yes/no relevance questions and returns them sorted.

Android AI chat client and SillyTavern-compatible endpoint where Jev screens memories for relevance and serves as a judge tool.

Graph-database-agnostic GraphRAG framework where swappable Laya or Jev decisions score edges, route intents and gate hallucinations.

Precision-first RAG service where Jev routes queries, triages each retrieved chunk and verifies every claim before an answer is released.

Python library for typed decisions with Jev or your own provider, adding validated distributions, batching, budgets, ranking and records.

Local-first knowledge search with BM25 shortlisting and Jev Noul reranking by default, seven selectable pipelines and cited answers.

npm CLI that screens large agent tool outputs with Jev, returning compact typed decisions and IDs while originals stay recoverable.

Grep-shaped Rust CLI for coding agents: BM25 recall plus Jev Noul window checks and a listwise Choice return path:line results with scores.

TypeScript library of decision contracts, confidence thresholds, fallbacks, human review and evaluation patterns on top of the TypeSafe SDK.

Unofficial LlamaIndex reranker and router where Jev scores retrieved passages and selects query engines, with BEIR results.

Evidence gate for RAG: a System One model judges whether retrieved excerpts support an answer before the LLM is allowed to speak.

Java SDK for TypeSafe's System One API plus Spring AI integrations using Jev as judge, guardrail, RAG filter/reranker and tool index.

Decision-to-action harness that puts Jev between an agent and your data to find the file, check the claim and permit actions.

Demo that navigates a Neo4j graph hop by hop, asking Jev which relationship to follow and whether the goal is reached.

Federated knowledge retrieval engine for agents that uses Jev to route queries to backends and re-rank evidence, with keyword fallback.

CLI and agent skill that shortlist notes in Obsidian or Logseq locally, then have Jev rerank them, returning original passages.

shadcn/ui site-search block that shows keyword hits instantly, then has Jev re-rank the top 20 by what the visitor meant.

Web app that has Jev score emoji categories and candidates 0 to 3 for relevance to a short text and returns many matches.

Browser PDF search by meaning: Jev answers a yes/no per line on whether it answers your query, and matching lines light up.

Fingerprints a target, has Jev score every Nuclei template 0-4 for relevance, then runs all templates highest-relevance first.

Python harness stress-testing Jev's confidence, its accuracy as a RAGTruth hallucination judge, and its use as a RAG reranker.

AutoTrust's Apache-2.0 student of Jev 1.13 on Qwen3.8-27B, serving typed decisions and ordinary generation from one vLLM engine.