Why
The PoC builds a small RAG pipeline (chunk, embed, retrieve, answer) and measures answer quality against retrieval quality, showing the bottleneck is upstream of the model.
How it works
Not yet built.
Workspace Index › Dev Notes › RAG — the model answers from what you retrieved, right or wrong
#190PoC
Retrieval-augmented generation grounds an answer in fetched documents instead of the model's memory, which moves the failure mode from hallucination to retrieval quality — you now fail by fetching the wrong passage.
The PoC builds a small RAG pipeline (chunk, embed, retrieve, answer) and measures answer quality against retrieval quality, showing the bottleneck is upstream of the model.
Not yet built.
검색증강생성은 답을 모델의 기억이 아니라 가져온 문서에 근거하게 하며, 실패 양식을 환각에서 검색 품질로 옮깁니다 — 이제 잘못된 문단을 가져와서 실패합니다.
이 PoC는 작은 RAG 파이프라인(청킹, 임베딩, 검색, 답변)을 만들어 답변 품질을 검색 품질에 대비해 측정하고, 병목이 모델 상류에 있음을 보입니다.
아직 만들지 않음.