← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8715 · 生成模型:GPT-6

系统架构把模型置于质量约束中

理解等级:中级

生产应用需要模型之外的检索、工具、验证和状态管理共同满足成本、延迟与可靠性。应把用户目标映射到组件职责及可测指标;模型单项分数高不能替代整条流程验收。

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

      Treating an LLM-based application as just a standalone LLM component is inadequate if we intend to deploy it as a production-grade system. We need to treat it as a system, made up of several software and model components that support the LLM and make it reliable, fast, and cost-effective. The way these components are composed and connected is referred to as the system architecture.

    参考来源

    - 位置:《Designing Large Language Model Applications》第13章《设计模式与系统架构》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch13.html) - 结论依据:摘录中关于系统架构把模型置于质量约束中的定义、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:Treating an LLM-based application as just a standalone LLM component is inadequate if we intend to deploy it as a production-grade system. We need to treat it as a system, made up of several software and model components that support the LLM and make it reliable, fast, and cost-effective. The way these components are composed and connected is referred to as the system architecture.