rag

1/

What if #LLMs had context windows so large that an entire knowledge base could fit into a single prompt? This would revolutionize Retrieval-Augmented Generation (RAG) applications by enabling retrieval, re-ranking, reasoning, and generation all in one step. With a Long-Context Language Model (LCLM), we could simplify RAG architecture by leveraging the model’s capability for In-Context Retrieval and Reasoning (ICR²).

#NLP #NLProc #RAG #GenerativeAI #Paper

Redis做Vector Store有TTL自动回收过期key，可是它犯了傲慢之罪：无论你给Document指定什么ID，它都会按照HASH来生成key。
手搓Parent Retriever的时候被这个坑麻了⋯⋯那么很简单的选择题，逐个parent添加、等待它返回ID、给children们塞parent id之后塞Child Vector Store，5个搜索结果切100片要花1分30秒才塞完，或者说⋯⋯
或者说，用Chroma，它无条件尊重你给的ID，所以可以直接先生成ID，并且给每个parent塞好会被继承的metadata，然后光速开切、塞vector，同样的内容只需要7秒。
选哪个不用多说了吧。清理过期文件也就一个where的事，官网都有可以照抄的示例。
只能说Redis不适合。#RAG #Redis #Langchain