1
We taught a small LLM to throw away 68% of our RAG context
用小LLM砍掉68%的RAG上下文，竟守住96%召回率，实战方案来了。
Article URL: https://www.kapa.ai/blog/how-we-prune-rag-context Comments URL: https://news.ycombinator.com/item?id=48809354 Points: 3 # Comments: 0