Add jevextract - #132
Add jevextract#132gabazureus wants to merge 1 commit into
Conversation
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
Navigate logical layers of code changes, visualize relationships, and explore their blast radius. No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Advanced Run ID: 📒 Files selected for processing (1)
Included review availability: Your plan provides up to 2 included reviews per hour; 1 remains after this review. 📝 WalkthroughWalkthroughThe project catalog now includes jevextract, a Python project in the sdks category, with its repository, description, and added date. ChangesProject catalog
Priority: ⬇️ Low Estimated code review effort: 1 (Trivial) | ~3 minutes Change: Other Suggested reviewers: Merge Risk: ⚪ Minimal · up to The new entry uses a category accepted by catalog validation and listing generation; no concrete merge-blocking issue is evident. Architecture SummaryArchitecture risk: 🔵 Low · up to The change affects 1 system. Changed systems: Architecture concerns Review detailsSystems and components
Before / after behavior
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Project: https://github.com/gabazureus/jevextract
Where Jev fits: deterministic code proposes candidate text spans with exact character offsets, and Jev only decides each span's schema class with a
Choice(plus aNoulper sentence-level class), so every extraction is grounded in the source by construction.It is a Python library (MIT) positioned as an open-source alternative to LangExtract, with an offline test suite, CI, a bilingual benchmark (jx-bench) and a paper comparing it with LangExtract, an LLM-JSON baseline and GLiNER on quality, grounding, latency and cost. The results are reported as measured, including where it loses on quality.
data/projects.jsonand rannpm run validateREADME.mdorsite/index.html(CI regenerates them)Disclosure: the project was built with substantial help from an AI coding agent (Claude Code); the benchmark numbers come from real runs whose raw predictions are committed in the repository
Need help on this PR? Tag
@codesmith-botwith what you need. Autofix is disabled.Summary by CodeRabbit