특정 도메인 또는 소수의 데이터: 모델이 해당 데이터에 대해 배우기에 데이터가 충분하지 않습니다.
이전 절에서
LLM
을 맞춤화하는 파인 튜닝에 대해 살펴보며 직접 테스트했습니다. 그러나 연구
(
https
://
oreil
.
ly
/
gO08M
)에 따르면 파인 튜닝과
RAG
를 지식 주입 측면에서 비교한 결
과
RAG
가 더 믿을만한 해결책인 것으로 밝혀졌습니다. 상황에 따라 적절한 방법을 선택하는
기준은
4
.
4
절에서 찾을 수 있습니다.
이제 다양한
RAG
구현 전략을 알아봅시다.
4.3.1
기본
RAG
기본
RAG
naive
RAG
부터 시작하겠습니다. 이는 가능한 가장 단순한
RAG
구현을 의미합니다.
3
장에서 보았듯이, 원리는 다음과 같습니다 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.