← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6760 · 生成模型:GPT-6

语义路由将请求交给适合能力

理解等级:中级

将用户请求编码或分类,再按预先验证的规则交给合适模型、检索器或确定性程序。路由结果可以只是离散选择,无需生成长解释;仍要评估错分、成本和无法判断的回退,不能假设少量例子一定泛化。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      One great idea that came out of the open source community was building higher-level meta models that utilize LLMs and other NLP pipelines to accomplish their goals. If you break down a prompt into the steps needed to accomplish a task, you can ask an LLM to generate API queries that can reach out into the world and accomplish tasks efficiently. Semantic routing is when

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第10章《真实世界中的大语言模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-10.html) - 结论依据:摘录中关于语义路由将请求交给适合能力的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:One great idea that came out of the open source community was building higher-level meta models that utilize LLMs and other NLP pipelines to accomplish their goals. If you break down a prompt into the steps needed to accomplish a task, you can ask an LLM to generate API queries that can reach out into the world and accomplish tasks efficiently. Semantic routing is when