refRAG. REFRAG-style RAG (compress → sense/select → expand) — Single-file reference implementation,REFRAG框架通过压缩、选择和扩展流程显著提高RAG应用的效率,实现最高30.85倍的TTFT加速,并将LLM的有效上下文长度扩展16倍,解决了传统方法中上下文窗口过长的问题。

github.com/MaoTouHU/refRAG

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.