Week 1 · D2🔒 LockedAbout 4 hours
Long Documents, Multimodal Input, and a First Look at the API: Using Large Context, Saving Money With Prompt Caching, PDF and Image Input, Citation-Backed Answers; a Minimal Messages API Call
Make your first code call to Claude: feed it a whole PDF and get back a summary with page-numbered citations, then use prompt caching to cut the cost of repeated questions by an order of magnitude.
Make your first code call to Claude: feed it a whole PDF and get back a summary with page-numbered citations, then use prompt caching to cut the cost of repeated questions by an order of magnitude.
Interview questions
Why is the context window called the scarcest resource in LLM applications? With million-token windows, does that still hold?为什么说上下文窗口是 LLM 应用里最稀缺的资源?窗口已经有一百万 token 了,这个说法还成立吗?
Common in ChinaCommon overseasBasic#context-window#cost🔒 Unlock this chapter to see the answer keys.
Where does prompt caching save money, when does it cost more, and how do you debug a zero cache-hit rate in production?prompt caching 省在哪?什么情况下反而不省?线上发现缓存命中率是零,你怎么排查?
Common in ChinaCommon overseasIntermediate#prompt-caching#cost🔒 Unlock this chapter to see the answer keys.
How do API citations fundamentally differ from prompting the model to quote sources with page numbers, and when can't you use them?citations 和在提示词里要求模型「引用原文并注明页码」有什么本质区别?什么场景下不能用 citations?
Common in ChinaCommon overseasIntermediate#citations#grounding🔒 Unlock this chapter to see the answer keys.
