Skip to content
System One

Laya Jev Lab

An independent benchmark of Jev against Laya on 40 Chinese support-ticket classifications, plus a confidence-gated cascade that calls Laya first and escalates to Jev, matching Jev's 78% accuracy at 1.8x the speed.

yibie/laya-jev-lab on GitHub

Stars
9
Forks
3
Language
Python
License
MIT
Last push
20 Sep 2026

Read from GitHub on . Counts change daily.

How it uses Jev

const res = await fetch("https://api.typesafe.ai/v1/systemone", {
  method: "POST",
  headers: { authorization: `Bearer ${KEY}`, "content-type": "application/json" },
  body: JSON.stringify({ state: text, model: "jev-latest",
    questions: { q: { type: "choice", instructions: "这条客服消息属于哪个类别?", criteria } } }),
});
const j = await res.json();
if (res.status !== 200) { err = `HTTP ${res.status}: ${JSON.stringify(j).slice(0,100)}`; }
else { r = j.answers.q; }

View in cascade/run2-jev.mjs

Open on GitHub

More like this

Use cases this is tagged with