[Feat] 동적 Few-shot 선택 임계값 및 후보 수 튜닝 - #319
Conversation
- Few-shot similarity 분포와 후보 선택 개수 분석 - top-k 및 min-similarity 조합별 품질·비용 평가 - minimum-selected-count fallback 품질 비교 - 권장값을 top-k 5, min-similarity 0.40, minimum-selected-count 2로 확정 - dev, prod, evaluation 프로필에 권장 설정 반영 - feature flag 기본 비활성 상태 유지 - 튜닝 결과와 결정 근거 문서화
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Advanced Run ID: 📒 Files selected for processing (5)
Included review availability: Your plan provides up to 1 included review per hour; 0 remain after this review. 📝 WalkthroughWalkthroughFew-shot 검색 튜닝 평가 문서를 추가했습니다. 평가 결과에 따라 여러 환경의 기본 ChangesFew-shot 검색 튜닝
Priority: ⬇️ Low Estimated code review effort: 1 (Trivial) | ~10 minutes Change: Other Merge Risk: ⚪ Minimal · up to The few-shot settings are bound and consumed as intended, with no established production or evaluation failure blocking merge. 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
✨ 어떤 이유로 PR를 하셨나요?
📋 세부 내용 - 왜 해당 PR이 필요한지 작업 내용을 자세하게 설명해주세요
📸 작업 화면 스크린샷
🚨 관련 이슈 번호 [#294 ]
Summary by CodeRabbit
변경 사항
문서