← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8703.b · 生成模型:GPT-6

匹配粒度与返回粒度可分开

理解等级:中级

可用句向量匹配具体问题,再返回包含该句的较大chunk提供背景。这样兼顾精确定位和上下文,但需保存句到chunk映射并控制扩展长度;小单元并不总比大单元更好。

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

      corresponding to the most similar vectors are then retrieved. This ensures that the embedding matching happens at a lower granularity, like a sentence, but the model receives the entirety of the chunk the sentence belongs to, thus providing sufficient background context to the model.

    参考来源

    - 位置:《Designing Large Language Model Applications》第11章《表示学习与嵌入》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch11.html) - 结论依据:摘录中关于匹配粒度与返回粒度可分开的定义、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:corresponding to the most similar vectors are then retrieved. This ensures that the embedding matching happens at a lower granularity, like a sentence, but the model receives the entirety of the chunk the sentence belongs to, thus providing sufficient background context to the model.