SKSerhiy Kucherenkoinskucherenko.hashnode.dev·Oct 2 · 12 min readThe same question, asked three waysA RAG system answers a question in two steps. A retriever turns the question into a vector, compares it with the vectors of every passage in the documents, and hands the five closest passages to a lan00
SKSerhiy Kucherenkoinskucherenko.hashnode.dev·Sep 26 · 13 min readThe answer was at rank 7A RAG system answers a question in two steps: a retriever picks a handful of passages out of the documents, and a language model writes an answer from those passages. When the answer is wrong, one of 00
SKSerhiy Kucherenkoinskucherenko.hashnode.dev·Sep 18 · 13 min readAsking a RAG in the wrong languageEvery article in this series so far assumed that the person asking speaks the language of the documents. The SEPA rulebooks my RAG indexes exist only in English, and so did every question in my golden03A
SKSerhiy Kucherenkoinskucherenko.hashnode.dev·Sep 14 · 10 min readSwapping every model in a RAGIn the comparison articles (part 1 and part 2) I put my own RAG against five other systems. The models were frozen there on purpose: same embedder, same generator everywhere, so that only the framewor00
SKSerhiy Kucherenkoinskucherenko.hashnode.dev·Sep 12 · 7 min readImproving the scores of a RAGIn the previous articles (part 1 and part 2) I compared my own RAG against five other systems. One of its numbers bothered me since then: recall@5 = 0.60. In plain terms, for 4 questions out of 10 the00
