详细内容或原文请订阅后点击阅览
代理指针 RAG：无需语义预编译的时间推理
Proxy-Pointer 和 LLM-Wiki 的技术比较后 Proxy-Pointer RAG：无需语义预编译的时间推理首先出现在 Towards Data Science 上。
来源:走向数据科学Retrieval-Augmented Generation (RAG) has evolved rapidly in recent times. The original RAG paradigm was designed to be straightforward: retrieve the most relevant chunks from a corpus and use them to answer a question.虽然对于许多以文档为中心的查询有效，但当问题超出单个文档的边界时，这种方法就开始陷入困境。 Or when questions are temporal in nature, such as tracking the history of an entity over years.
A few examples would be the following:
Recently, a new architectural pattern,LLM-Wiki,has proposed an interesting solution to this challenge.不是在检索期间重复搜索原始文档，而是在摄取期间进行广泛的语义处理步骤，构建一个持久的知识库，该知识库由通过索引链接的规范页面组成。 Future queries are answered primarily from this compiled knowledge rather than the original documents.
While an elegant idea, this raises important architectural questions such as:
让我们通过现实生活场景来进行比较。