-
Notifications
You must be signed in to change notification settings - Fork 4
Feature/46 retrieve 성능 향상 #52
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
The head ref may contain hidden characters: "Feature/46-retrieve-\uC131\uB2A5-\uD5A5\uC0C1_"
Conversation
- Add Reranker - Added new dependencies: langchain-huggingface==0.1.2 and transformers==4.51.2 to requirements.txt. - Removed the QueryRefinedAgainChain and its associated logic from chains.py and graph.py to streamline the query refinement process.
- add reranking feature in the Streamlit app to enhance search result accuracy. - Added new dependencies: transformers==4.51.2 and langchain-huggingface==0.1.2 to setup.py. - Created a new retrieval module to handle vector database interactions and reranking logic.
|
회사에 실험적으로 도입했을때 체감으로는 rerank 도입후에 좀 더 정확한 테이블검색이 이루어지는것 같습니다. 어떻게 그걸 정량적으로 비교할지는 아직 잘 감이 안오네요...! SQL생성시간이 전체적인 시간을 의미하는것이라면 30초대로 기존 10초 아래로 걸리던것에 비해 좀 느려지긴했습니다. (대부분 reranker에서 소요) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 도입해서 먼저 사용해보고 부족한부분 채우면 될 것 같아요!!
#76 duplicated |
#️⃣ Issue Number
📝 요약(Summary)
Dongjin-kr/ko-reranker
모델을 통해 reranking 합니다.💬 To Reviewers (선택)
PR Checklist
reference) How to Code Review