RAG 段落门控

检索后按段落 Noul 过滤；代码组装 accepted/conflict 再生成。

Who: RAG / search engineers. Steps: Retrieve top-k → per passage Nouls (relevant / usable evidence / contradicts premise / injection) → route() in code → build prompt with accepted vs conflict blocks → LLM answers. Expected effect: drop injections/off-topic; surface premise conflicts; cookbook shows reshuffle vs similarity rank alone (cookbook-reported).

提示词

Audience: RAG / search eng.
Steps:
1) Retrieve top-k candidates.
2) Per passage: Nouls relevant, usable_evidence, contradicts_premise, injection.
3) Code route(): accept / conflict / drop.
4) Build LLM prompt with separate accepted vs conflict blocks.
Expected effect: cleaner context than similarity rank alone (cookbook-reported).
Cross-link: Hands-on [RAG filtering](/guides/rag-filtering/).

需要授权：typesafe-sdkyour-retriever

它是怎么搭起来的

以下说明为英文原文（来自社区作者），提示词本身建议保留英文。

Catalog card; Hands-on keeps the recipe. Sources: classifying_rag_passages · rerank_typesafe · awesome-jev-usecases · Search.

Suggested route order: injection → conflict → evidence sufficiency. Cross-link Hands-on RAG filtering.

Sources (wave-2 deepen)

为什么它好用

Embeddings measure nearness; Jev asks whether a passage is usable evidence.

本案例收集自公开的 Jev 社区，版权归原作者所有。提示词属于参考资料：运行前请先审阅内容，并且不要让 bot 超出你实际授予的权限行事。