Qasem Nick
@niksefat
RAG cheat sheet: under ~500 pages, skip rag and stuff it all in context (cache the prompt). got keywords? use bm25. retrieve top 20 chunks, rerank, and have an llm add context to each chunk first. #ai
Qasem Nick
@niksefat
RAG cheat sheet: under ~500 pages, skip rag and stuff it all in context (cache the prompt). got keywords? use bm25. retrieve top 20 chunks, rerank, and have an llm add context to each chunk first. #ai