April 2026
Intermediate
348 pages
8h 22m
Korean
Content preview from 그림으로 배우는 생성형 AI
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,
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.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.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.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.
226
그림으로 배우는 생성형 AI
최적 부합
best match
(BM)
청크에 의미 기반 검색보다는 키워드 일치
exact
match
방식의 검색에 더 적합한 문자열이 포함될 수도 있
습니다
.
예를 들어
JPC-2345
같은 부품 번호가 그
렇지요
.
하지만 이런 문자열은 토큰화 과정에서 더
작은 조각들로 분해될 가능성이 높으며
,
그러면 임
베딩 기반 검색에서 누락되기 쉽습니다
.
이 문제는
TF
-
IDF
(
https://oreil.ly/ddCtw
)
를 이용해 청크
와 질문 모두에서 이런 특별한 텍스트를 최적 부합
방식으로 찾아내서 검색 가능한 색인에 추가하는
식으로 해결할 수 있습니다
.
오류 보정
error correction
“
쓰레기가 들어가면 쓰레기가 나온다
garbage
in
,
garbage
out
,
GIGO
”
라는 말이 있듯이
,
벡터 저장소에 저장되는
데이터를 잘 검증하는 것이 중요합니다
.
문서를 분
해해서 청크들을 추출할 때 일부 청크가 누락된다
면 수집 작업을 반복해야 합니다
.
PDF
같은 비정형
콘텐츠의 경우 추출 시 손실이 없는지 확인할 필요
가 있는데요
.
예를 들어 관련 파이썬 패키지 중에는
알 수 없는 글꼴이 포함된 스캔
PDF
를 올바르게 처
리하지 못해 비표준 글꼴의 텍스트가 누락되는 경
우가 많습니다
.
긴 컨텍스트 창
RAG
시스템이 청킹을 사용하는 이유 중 ...
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.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
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.
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.
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.
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.