返回行业内容

教程

llm-typesafe 0.1a0：给 LLM 接上 TypeSafe AI 的 Jev 模型——yes/no noul 概率、按类别 criteria 的分诊选择题、按梯度打分的评分题三类用法示例齐附

llm-typesafe 0.1a0

评分 46

导读

作者发布 llm-typesafe 0.1a0，为 LLM 接入 TypeSafe AI 新模型 Jev：llm install llm-typesafe、llm keys set typesafe 后即可问 yes/no 型“noul”问题（“这条消息是否明确请求退款”→ 概率 noul 0.99）；或给 criteria 字典做分诊选择题（billing/technical/other）；或给有序选项做评分题（可复现程度分三档）。细节见 README。

主体与标签

#教程/实操#API/工具

正文

Release: llm-typesafe 0.1a0

I built this new plugin for LLM to add support for TypeSafe AI's new Jev model . Install it like this:

llm install llm-typesafe

Then set an API key ( get one here , the waitlist seems to move pretty fast):

llm keys set typesafe
# Paste key

And now you can ask yes/no "noul" questions like this:

llm -m jev 'Please refund my last payment.' \
  -s 'Does this message explicitly request a refund?'
{"type": "noul", "noul": 0.99}

Or choice questions like this:

cat message.txt | llm -m jev \
  -s 'Which team should handle this message? If billing and technical issues both occur, choose billing.' \
  -o answer_type choice \
  -o criteria '{
    "billing":"Charges, invoices, payments, or refunds",
    "technical":"Problems installing or using the product",
    "other":"Neither category fits"
  }'

Or scoring questions like this:

cat report.txt | llm -m jev \
  -s 'How reproducible is the problem described in this report?' \
  -o answer_type score \
  -o criteria '[
    "No reproduction instructions",
    "Some instructions, but important steps are missing",
    "Complete steps with expected and actual results"
  ]'

See the README for more details.

Tags: projects , llm , jev

打开原文 ↗