[feat] Add extraction result schema and worker extraction interface#3
Merged
1000hyehyang merged 4 commits intodevfrom Apr 28, 2026
Merged
[feat] Add extraction result schema and worker extraction interface#31000hyehyang merged 4 commits intodevfrom
1000hyehyang merged 4 commits intodevfrom
Conversation
1000hyehyang
approved these changes
Apr 28, 2026
Member
1000hyehyang
left a comment
There was a problem hiding this comment.
@KyungminPark-steck 좋습니다! 이후 HF 실제 연동 시 필요한 HF_EXTRACTION_ENDPOINT_URL, HF_EXTRACTION_API_TOKEN 값은 디스코드에 공유 부탁드립니다~~ 그리고 만약 DB 스키마 변경이 필요하다면 migration 코드도 꼭 추가해주세요!
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
✨ 무엇을 바꿨나요?
processing job 결과 응답에 LLM 추출 결과를 담을 수 있도록
extraction_resultschema와 worker 추출 단계 인터페이스를 추가했습니다.실제 HF endpoint 연결 전에도 mock/fake client로 추출 단계를 테스트할 수 있도록 HF extraction client 초안과 관련 테스트를 함께 추가했습니다.
🔗 관련 이슈
Closes #2
💡 왜 바꿨나요?
최종적으로 caption에서 가게명, 주소, 근거 문장, certainty 등을 추출해 job result API에 포함해야 합니다.
그 전에 외부 API 응답 필드명, 내부 도메인 모델, worker 파이프라인의 추출 단계 경계를 먼저 정리해 두면 실제 endpoint 연결, DB 저장, fallback 모델 추가를 더 안전하게 이어갈 수 있습니다.
📝 주요 변경 사항
extraction_result필드 추가ExtractionResultExtractionCertaintyExtractionLLMResponseextraction_result만 비워두도록 처리👀 리뷰어가 보면 좋은 부분
extraction_result로 통일한 것이 적절한지ExtractionResult/ExtractionCertainty가 이후 DB 저장, fallback, Kakao enrichment 단계까지 확장하기 적절한지🧪 테스트
방식 (해당하는 것만 체크)
메모 (시나리오, 커맨드, 스크린샷 링크 등 — 선택)
.\.venv\Scripts\python.exe -m pytest36 passed