JEV Book Tags
Calibre plugin that asks Jev yes/no questions to suggest genre and subject tags for books, with per-tag thresholds and review.
Overview
JEV Book Tags is a free, open-source calibre plugin that uses Jev to suggest subject and genre tags for books in a calibre library. Per the yibie list, it asks a Noul question for each candidate tag and applies configurable per-tag probability thresholds, preserving existing tags and leaving uncertain results for review. You can classify the current book, a selection or the whole library.
Features include clickable tag selection, batch filtering with a shared detail panel, review of the exact request input before applying, caching of successful evaluations, retry and resume of interrupted runs, CSV export, and restoring the most recent application if books have not changed. Tag categories, thresholds, input mode and single- or multi-tag behaviour are configurable, and vocabularies and profiles can be imported and exported without API keys. A demo on 32 English books with real Jev responses shows 31 ready and one needing review, with a 95% threshold for Programming and 85% elsewhere. It is GPL-3.0-or-later and not affiliated with TypeSafe or calibre.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this book belong to this genre or subject tag? | yes · no |
How it works
- Select books in calibre
- Plugin sends metadata and questions per candidate tag
- Apply per-tag thresholds; flag uncertain results
- Review and apply tags; cache results
Strengths
- Preserves existing tags
- Per-tag thresholds and review before applying
- Caching and resume for large libraries
Caveats
- Requires a TypeSafe key and may incur charges
- Not affiliated with calibre or TypeSafe
At a glance
- Type
- Plugin
- Status
- beta
- Language
- Python
- Runtime
- calibre plugin
- Has code
- yes
- License
- GPL-3.0-or-later
Use cases and integrations
How curated lists describe it
Library cataloguing: a calibre plugin asks Jev `Noul` questions about book genres and subjects, applies configurable per-tag probability thresholds, and preserves existing tags while leaving uncertain results for review.
yibie/awesome-jevA free calibre plugin that suggests genre and subject tags for individual books, selected books or an entire library, with configurable thresholds and review controls.
logicrw/awesome-jev-projects
Frequently asked questions
What does Jev decide?
Whether each book matches each candidate genre or subject tag.
Will it overwrite my tags?
No, existing tags are preserved and suggestions are reviewed first.
Can I set stricter thresholds for some tags?
Yes, thresholds are configurable per tag category.
Related projects
Privacy-first personal knowledge management system, listed as integrating Jev for document classification and tag routing.
PluginproductionTypeScriptPipeline that audits and refines topic-model clusters by checking each document against its topic label with a zero-shot decision model.
DemoresearchPythonChinese-language Zotero AI reading assistant that uses Jev judgments to classify papers in your library.
LibraryproductionJavaScriptClassifies tax PDF pages into 261 IRS forms and 7 page kinds with one Jev request per page and a confidence gate.
ProjectproductionTypeScriptRust tool that asks Jev which PDF pages genuinely need OCR, extracting text pages locally and sending only the rest to OCR.
ProjectbetaRustGo terminal app that files documents using five Jev questions: category, sensitivity, urgency, whether action is needed and action state.
ProjectbetaGo