Jev glossary
PatternsSemantic find
Line-by-line search
Rank every line of a document in one request with a Choice, while a Noul checks whether the document contains an answer at all.
- Category
- Patterns
- Also known as
- Semantic find
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 49
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The cookbook tags and ranks all 218 lines of GitHub's Terms of Service in a single request. An existence Noul rides along so the system can say no: on an absent answer, one line still scored 0.86 while the exists question read 0.14, which is why both thresholds need tuning.
Choice caps at 255 options, so longer documents use a two-pass window search. The pattern is a model-based alternative to embedding search when the corpus is small enough to fit one request.
Tagspatternssearch
Related terms
Definitions that connect to this one.
Re-rankingScore each query-candidate pair with one question and reorder a shortlist; the CLERC example lifts top-1 accuracy from 5% to 18%.PatternsPrimitive limitsThe hard caps to design around: 255 Choice options, 2 to 10 Score levels, and a 64k context covering state plus questions.PrimitivesNoulThe yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is returned.PrimitivesRAG passage classificationScore each retrieved passage with four Noul questions, then decide in code which passages reach the answering model.Patterns
From the Jev directory
Directory entries that go deeper on this term.
Semantic search over GitHub's Terms of Service: one request ranks all 218 lines with a Choice while a Noul checks whether the document contains an answer at all, including when it should say no.
Jev CookbooksDocs#official#cookbook#search
Official
A full-stack, permission-aware document library from Extend: it browses document trees and parsed output with Extend UI Finder, searches the folder hierarchy with JEV, and answers source-grounded questions with inline citations through the AI SDK.
Jev Tools & CLIs#community#github#typescript
Community
extend-hq/jevboxTypeScript
extend-hq/jevboxTypeScriptLong-document search that pairs Jev's Choice primitive with PageIndex's hierarchical tree: instead of a vector DB or embeddings, Jev picks a node and then a child, so even a 300-page report can be searched a handful of options at a time.
Jev Integrations & Adapters#community#github#rag
Community
VectifyAI/jev-doc-searchPython
VectifyAI/jev-doc-searchPythonTraining code for SearchJev, a fast calibrated System-1 model for search agents: given a search state and a decision schema, it returns typed predictions over legal field values in one forward pass of a Qwen3.5 backbone.
Jev Repos & SDKs#community#github#python
Community
EvoScientist/SearchJevPython
EvoScientist/SearchJevPythonA search API over about 203 million OpenAlex English title and abstract records, running DenseOn embedding search by meaning and a tantivy index for exact words behind one HTTP service. Its whole-field topic maps use TypeSafe's Jev to judge archetype and cited papers.
Jev Tools & CLIs#community#github#python
Community
maximerivest/srl-searchPython
maximerivest/srl-searchPythonAn unofficial Chromium extension that adds a find-in-page bar: literal matches highlight instantly and locally, and with your own TypeSafe API key Jev also finds passages by meaning after you pause typing. Uncertain results never auto-scroll, and paid searches start only while you are in the bar.
Jev Tools & CLIs#community#github#chrome-extension
Community
Szewowsky/jev-findJavaScript
Szewowsky/jev-findJavaScript43 more matching entries in the full directory.
From the Jev AI model community
Posts from builders shipping with Jev right now.