Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

RAG Feature Inoperable Due to Korean Document Encoding Error(한글 문서 인코딩 오류로 인한 RAG 기능 미작동 문제) #176

Open
gandareman opened this issue Dec 20, 2024 · 1 comment

Comments

@gandareman
Copy link

smart composer 에서 valt chat을 시도하면 인덱싱 작업을 하다가 도중에 멈추면서 invalid byte sequence for encoding "UTF8":0x00 메시지가 나옵니다. 저의 문서들은 다 한국어 기반의 문서입니다. 인덱싱 도중 한글 인코딩에서 문제가 발생한 것 같은데 옵시디언 버전과 smart composer 버전 모두 최신버전입니다. 좋은 프로그램 너무 감사한데, 기대했던 RAG가 안되니 아쉽습니다. 곧 문제가 해결되기를 기대해 봅니다. 감사합니다.

===

When I attempt to use Valt Chat in Smart Composer, the indexing process stops midway and displays the message: invalid byte sequence for encoding "UTF8":0x00. All my documents are Korean-based, so it seems there’s an issue with Korean encoding during indexing. Both the Obsidian and Smart Composer versions are up to date. Thank you for such an excellent program, but it’s disappointing that the RAG feature I was looking forward to isn’t working. I hope the issue gets resolved soon. Thank you.

@glowingjade
Copy link
Owner

혹시 사용하고 계신 임베딩 모델이 어떻게 되실까요?


What embedding model are you currently using?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants