LangSmith 推出 Jev-as-a-judge，给生产 trace 全量打分
Jev-as-a-judge is now available in LangSmith. ✅ Score every production trace instead of a sample. ...
LangSmith 现在能给生产 trace 全量打分了，不用再抽样，多标准评估成本不涨，安全问题还能自动响应。
LangChain 宣布 Jev-as-a-judge 在其评估平台 LangSmith 上线，用于自动给 LLM 应用输出质量打分。该功能会对每一条生产 trace 打分，不再是过去只抽样评估部分请求的做法。每条 trace 可同时检查多个评估标准，成本不会随标准数量增加而上涨。Jev-as-a-judge 的打分速度足够快，发现安全或安保问题后可以触发自动化响应。
Jev-as-a-judge is now available in LangSmith. ✅ Score every production trace instead of a sample. ...
Jev-as-a-judge is now available in LangSmith. ✅ Score every production trace instead of a sample. ✅ Check more criteria per trace without the cost climbing. ✅ Catch safety or security issues fast enough to trigger an automated response. Give it a try and let us know what you think! langchain.com/blog/jev-is-no… 💬 3 🔄 7 ❤️ 22 👀 3758 📊 9 ⚡