User repository on GitHub
Classify Hugging Face datasets across typed semantic dimensions with TypeSafe Jev System One.
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Repos & SDKs
Hfjev
A Python and JavaScript package that loads any Hugging Face dataset, auto-adapts evaluation rubrics to the domain, and classifies every row through a single parallel Jev call with calibrated probabilities, plus a CLI and an interactive studio for uploads and export.
- Stars
- 3
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- hemanth
- Last verified
- Oct 2026
Used inJev for Data & Analytics
- Languages
- PythonTypeScriptJavaScript
- Capabilities
- Open sourceRequires API key
Highlights
- pip install hfjev or npm install hfjev; then hfjev('cornell-movie-review-data/rotten_tomatoes') and dataset.classify().
- Custom dimensions: adapt() overrides the default domain pack with your own Choice, Noul, or Score primitives, no retraining.
- stream() yields evaluations row by row for live feeds and telemetry without blocking on batch completion.
- CLIs for both runtimes: hfjev cornell-movie-review-data/rotten_tomatoes --limit 5 and the same via npx hfjev.
- Interactive studio on GitHub Pages imports datasets or uploads CSV/JSON/JSONL and exports enriched results with token telemetry.
Quickstart
python
import hfjev
dataset = hfjev('cornell-movie-review-data/rotten_tomatoes')
results = dataset.classify()
print(results[0]['answers'])Watch out
Grounded in the repository README and GitHub metadata reviewed on 2026-10-15; the README states MIT (Hemanth.HM), includes a bench/ directory described as comparing speculative fan-out latency but prints no numbers there, and the digest does not show key-setup steps even though classification runs through Jev.
Questions about this entry
Short answers drawn from the linked project or page.
It classifies Hugging Face dataset rows across typed semantic dimensions using TypeSafe Jev System One: load any dataset, let it auto-adapt evaluation rubrics to the domain, and classify each row in a single parallel call with calibrated probabilities and, as the README puts it, zero hallucinated tokens.
pip install hfjev for Python or npm install hfjev for Node.js. The Python quick start is import hfjev, load a dataset like cornell-movie-review-data/rotten_tomatoes, call dataset.classify(), and read results[0]['answers'].
Yes. adapt() overrides the default domain pack with your own Choice, Noul, or Score primitives; the README's example adds a tech_relevance noul asking whether a story is about artificial intelligence and an urgency score with Low and Breaking criteria, all without retraining.
dataset.stream() yields evaluations row by row, so live feeds and telemetry do not block on batch completion. Each yielded row carries its index and answers, making it usable for pipelines that consume results incrementally.
Yes, for both runtimes: hfjev cornell-movie-review-data/rotten_tomatoes --limit 5 from Python and the same command through npx hfjev for Node, each with a limit flag shown in the README.
Yes, an interactive studio is deployed to GitHub Pages. It can search and load any dataset or split from the Hugging Face Hub, upload local CSV, JSON, or JSONL files, auto-detect or customize rubrics, run single-row or batch classification, and export enriched data with token telemetry.
hemanth built it; the README signs MIT to Hemanth.HM and the repository holds python/, js/, playground/ (React 19), docs/, and bench/ directories. Classification runs through Jev, so a key is expected, and the bench directory's comparative numbers were not visible in the digest.
More Jev resources like this
Composio is an MIT-licensed SDK monorepo giving AI agents 1,000+ pre-authenticated toolkits with per-user sessions, authentication, triggers, and a sandbox, and it ships TypeScript and Python adapters including one for TypeSafe (Jev).
Jev Repos & SDKs#community#catalog-import#cobanov
Community
composiohq/composioTypeScript
composiohq/composioTypeScriptA MoonBit and TypeScript playground for Jev: an API client for noul, choice, and score questions, a single-question CLI, Jev-vs-Jev gomoku with real-time GIF replay, and experiments like an ESLint plugin whose verdicts come from Jev.
Jev Repos & SDKs#community#catalog-import#logicrw
Community
mizchi/jev-playgroundTypeScript
mizchi/jev-playgroundTypeScriptClassifies 1,000 recent arXiv AI papers into 24 topics with one Jev decision each, then checks those labels against an LLM judge on a seeded sample of 100. Ships three scripts and a static topic-map page.
Jev Benchmarks & Evaluations#community#catalog-import#logicrw
Community
stas4000/jev-papersPython
stas4000/jev-papersPythonPython with a smart if: .jev files add the ~ question operator and jev/case blocks that Jev answers with a number or a label, never text. Files are rewritten to plain Python at import time; every ~ is one paid TypeSafe API call.
Jev Repos & SDKs#community#catalog-import#logicrw
Community
sumanmichael/jevlangPython
sumanmichael/jevlangPythonA fork and bridge that runs jkudish/jev-browser fully locally: a local Jev-style engine built on parallel-decisions replaces the hosted API, with Qwen2.5-1.5B-Instruct picking each browser step and a 0.5B model typing search queries, measured on an RTX 2060 SUPER.
Jev Repos & SDKs#community#catalog-import#logicrw
Community
rorshopping/jev-browser-localPython
rorshopping/jev-browser-localPythonAn npm CLI that scans TypeScript, JavaScript and Python codebases for LLM calls that are really decisions, converts them into Jev modules with confidence-gated fallbacks, and shadow-tests them on recorded traffic before you swap.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
0xjba/jev-swapHTML
0xjba/jev-swapHTMLFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.