Classifying RAG passages
Official TypeSafe cookbook showing how to judge retrieved passages with Jev before passing them to an answering model.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
An official TypeSafe cookbook on classifying retrieval-augmented generation passages. It shows how to judge each retrieved passage with Jev before handing the useful ones to an answering model.
It is part of the docs' cookbook series and a starting point for retrieval filtering and reranking.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this retrieved passage relevant to the question?(inferred) | yes · no |
How it works
- Retrieve candidate passages
- Ask Jev to judge each passage
- Keep relevant ones
- Send them to the answering model
Strengths
- Official reference pattern
Caveats
- Only list summary available
Getting started
Read https://docs.typesafe.ai/cookbooks/classifying_rag_passagesAt a glance
- Type
- Article
- Status
- production
- Has code
- yes
Use cases and integrations
How curated lists describe it
Official example of judging retrieved passages before passing them to an answering model.
cobanov/awesome-jev
Frequently asked questions
What does it teach?
Filtering retrieved passages with Jev before answering.
Is it official?
Yes, it is in TypeSafe's docs.
Where is it?
https://docs.typesafe.ai/cookbooks/classifying_rag_passages
Related projects
Agent skill that teaches coding agents to hand bulk semantic judgments to Jev and to find where a product could use Jev decisions.
Agent skillbetaWorked Jev examples for ticket triage and reranking, runnable through OpenRouter without an early-access key, with offline tests.
ProjectprototypePythonDeepSeek Harness paper-reading workbench whose PDF search reranks keyword candidates with Jev, falling back to keyword order.
BenchmarkbetaTypeScriptMilvus bootcamp notebooks combining Gemini embeddings, Milvus retrieval and Jev judgments for reranking, filtering, routing and stopping.
ArticleproductionPythonOfficial TypeSafe cookbook recipes for guardrails, re-ranking, RAG passage classification, citation checks and more with Jev.
ArticleproductionTypeSafe cookbook showing how to evaluate many typed questions over one shared state in a single Jev request.
Articleproduction