Jev glossary
Patterns
Document splitting
Asking Jev where one packet becomes the next document, then letting code export the page ranges.
- Category
- Patterns
- Also known as
- None
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 2
- Docs
- Not listed
- Added
- 2026-09-28
Definition
DocJev extracts page text locally and asks Jev for ordered categories and page ranges. Splitting instructions tell the model to keep continuation pages together and to treat a new invoice reference as a new document even when the category matches. On a 40-document pilot Jev split 7 of 8 packets exactly.
Classification of a whole file is the simpler call: one category, probabilities, and a review flag. Both still need a TypeSafe key. Local OCR does not make inference offline.
Tagspatternsclassification
Related terms
Definitions that connect to this one.
Inbox triageOne Jev call per message, with a threshold and an action per label, so code moves or flags mail the model only scores.PatternsChoicePick one option from a set you define; returns the selected option, a probability for every option, and confidence.PrimitivesHuman reviewThe explicit path for uncertain or high-stakes cases: route to a person instead of acting on a low-confidence answer.PatternsPre-parsed value extractionRegex finds candidate spans, then Jev picks the requested one so code copies a verbatim value that cannot be invented.Patterns
From the Jev directory
Directory entries that go deeper on this term.
Classifies and splits PDFs, DOCX, and PPTX with local page text from LiteParse and category decisions from Jev.
Jev Tools & CLIs#community#python#document
Community
jerryjliu/docjevPython
jerryjliu/docjevPythonA localization pre-review gate that pairs source and target strings and judges meaning, terminology, tone, and placeholders as separate questions, so one failing dimension blocks a release without blending scores.
Jev Tools & CLIs#community#python#localization
Community
From the Jev AI model community
Posts from builders shipping with Jev right now.