Jev glossary
PatternsSpan extraction
Pre-parsed value extraction
Regex finds candidate spans, then Jev picks the requested one so code copies a verbatim value that cannot be invented.
- Category
- Patterns
- Also known as
- Span extraction
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 13
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The cookbook uses regexes to find candidate emails, phone numbers, and amounts, then offers them to a Choice question (plus a none hatch), so the returned value is copied verbatim from the source. A receipt email was picked at 0.98 and an invoice total read as $1,315.50.
find() over-finds and dedupes while pick() offers the spans as options. The limit is the 255-option Choice cap, and candidates without a regex, such as names, need a roster, NER, or a generative model.
Tagspatternsextraction
Related terms
Definitions that connect to this one.
Function callingTurn natural language into typed function calls: closed-set arguments become Choice questions and optional ones become Nouls.PatternsPrimitive limitsThe hard caps to design around: 255 Choice options, 2 to 10 Score levels, and a 64k context covering state plus questions.PrimitivesSDE cascadeA two-stage extraction cascade: a mini model extracts, a Noul battery verifies, and a confidence gate escalates to a reasoning model.PatternsGeneration limitationJev is not trained to generate text; forcing it by chaining choices is slow and unreliable, so extraction becomes a Choice instead.Evaluation & Training
From the Jev directory
Directory entries that go deeper on this term.
Regex finds candidate emails, phone numbers, and amounts; Jev picks the requested span so code copies a verbatim value that cannot be invented, with no free-text extraction required.
Jev CookbooksDocs#official#cookbook#extraction
Official
Turn markdown into a knowledge graph with an ontology you write and a cutoff you own. A local decision model answers closed yes-or-no questions one at a time, and anything it is unsure about waits for a person instead of entering the graph.
Jev Repos & SDKs#community#github#rust
Community
raphaelmansuy/edgextractTypeScript
raphaelmansuy/edgextractTypeScriptHAL-X AI's 322M non-autoregressive decision model returns calibrated answers in one forward pass of about 10 ms, with native number, excerpt and citation outputs beyond Jev's choice, noul and score types. Apache-2.0, post-trained in 18 languages.
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
A walkthrough that pairs Unsiloed document extraction with Jev: extracted medication rows and their citations become Jev's state, one Noul question per row flags implausible or obscured doses, and the results decide which fields need review.
Jev CookbooksPost#community#catalog-import#yibie
Community
9GitHub stars
A training-free algorithm that gets numerical output from any LLM with a Jev-like structured-choice interface by recursively refining a range through a multiway decision tree. Range-normalized MAE is 1.84% versus 5.18% for direct choice, and code is available on GitHub.
Jev Models & ReimplementationsArticle#community#research#arxiv
Community
Bring-AI/jev-numericPython
Bring-AI/jev-numericPythonCalOn is a unified 0.6B-parameter encoder that jointly encodes text and type definitions to extract entities, relations, and event triggers and arguments across datasets and schemas. Across 40 benchmarks it outperforms the evaluated baselines on most and leads all reported relation extraction benchmarks.
Jev Models & ReimplementationsArticle#community#research#arxiv
Community
7 more matching entries in the full directory.
From the Jev AI model community
Posts from builders shipping with Jev right now.