[Week3] 도메인 RAG 파이프라인 구축 및 Chunking 방식 비교 #11
Open
latteeea wants to merge 9 commits into
Open
Conversation
recursive: spotify_api 못 잡음, mardown: spotify_api 1등으로 잡음
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
RAG Pipeline
documents
-> loader
-> chunking
-> embedding
-> FAISS (vectorStore)
-> retriever
-> 2-step RAG Q&A
Chunking 방식
1. Recursive Chunking
2. Markdown Header Chunking
Chunking 방식 비교
최종 선택
노션 기반 자유 형식 트러블슈팅 메모에서는 세부 token 기반 recursive chunking보다 markdown heading 기반 chunking이 문제 해결 흐름과 구조적 문맥을 더 안정적으로 유지하는 것을 확인했다. (아마 같은 개념이 다른 트러블슈팅 사례의 각 문제로 산재되어 있어서 그런것으로 추측한다)
따라서 최종 retrieval 전략으로 markdown header chunking을 선택했다 !