Published On Aug 18, 2024
Anthropic just introduced Prompt Caching, a meachnism to reuse prompts / parts of prompts to reduce costs and latency.
Timestamps:
0:00 Introduction
0:14 What is Prompt Caching and how does it work?
1:22 When to use Prompt Caching?
2:23 Costs & Latency impact
3:29 Code Walkthrough
7:00 Lifetime and max breakpoints
7:25 Can Prompt Caching replace RAG?
#anthropic
show more