原书出处
Designing Large Language Model Applications
Insert Once we have determined the content to be fed to the LLM that is going to generate the final response to a query, whether the original retrieved documents or their summaries or notes, we need to decide how we are going to arrange it inside the prompt. The standard approach is to stuff all the content, or at least as much as can fit,
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch12.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf