[Week4] Self-RAG 기반 트러블슈팅 RAG - baseline 대비 6개 질문 비교 #19
Open
latteeea wants to merge 5 commits into
Open
Conversation
…into latteeea/week1-react-graph
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
구현 요약
week3에서 구축한 Domain RAG(2-step)를 Self-RAG 스타일 Agentic RAG로 리팩토링했다. Week3 baseline은
검색->생성의 단일 파이프라인이었고, 검색 miss나 관련 없는 문서가 섞여도 그대로 답변을 생성했다. 또한qa.py프롬프트상 중간 단계가 비어있으면 [추측]으로 채우도록 되어있어 인과 관계 질문에서 환각/단절이 발생할 수 있었다.이번 주차에서는 LangGraph로 아래 보정 루프를 추가했고
(BM25/RRF, Cohere reranker는 이번 주 범위에서 제외함 - retrieval 레이어 튜닝과 agentic 보정을 동시에 하지 않기 위해)
Agentic RAG Pipeline
추가한 컴포넌트
Baseline vs Agentic RAG 비교
long_polling.md
long_polling.md
long_polling.md
spotify_api.md
spotify_api.md
spotify_api.md
줄이려고 한 실패