Skip to content

Feature/bedrock api #85

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.

Sign up for GitHub

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

Merged
tjdtn0219 merged 2 commits into from
Nov 20, 2024
Merged

Feature/bedrock api #85

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8c7a604
fix: 콘텐츠 추천 및 재추천 시 DB 저장 로직 제거
junseokkim Nov 20, 2024
ee8971c
fix: 콘텐츠 추천 시 bedrock lambda prompt 수정
tjdtn0219 Nov 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 3 additions & 46 deletions src/main/java/swm/betterlife/antifragile/domain/content/service/ContentService.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@
import java.util.function.Function;
import java.util.stream.Collectors;
import lombok.RequiredArgsConstructor;
import org.checkerframework.checker.units.qual.A;
import org.springframework.data.mongodb.core.MongoTemplate;
import org.springframework.data.mongodb.core.query.Criteria;
import org.springframework.data.mongodb.core.query.Query;
Expand Down Expand Up @@ -50,18 +49,15 @@ public ContentListResponse saveRecommendContents(String memberId, LocalDate date
diaryAnalysisService.getDiaryAnalysisByMemberIdAndDate(memberId, date);
Member member = memberService.getMemberById(memberId);

String prompt = "이 일기의 감정에 정신적으로 도움이 되는 메타데이터를 10개 추천해줘";
String prompt = "이 일기와 조금이라도 관련있는 메타데이터를 10개 추천해줘";
prompt = recommendService.createPrompt(
analysis.getEmotions(), analysis.getEvent(), member, prompt
);
List<Content> recommendedContents
= getRecommendContentsByAnalysis(analysis, member, prompt);

List<Content> savedContents = saveOrUpdateContents(recommendedContents);
diaryAnalysisService.saveRecommendContents(analysis, savedContents);

return ContentListResponse.from(
savedContents.stream()
recommendedContents.stream()
.map(content -> ContentListResponse.ContentResponse.from(
content,
contentQueryService.getContentLikeNumber(content),
Expand All @@ -81,7 +77,6 @@ public ContentListResponse saveReRecommendContents(
DiaryAnalysis analysis =
diaryAnalysisService.getDiaryAnalysisByMemberIdAndDate(memberId, date);
Member member = memberService.getMemberById(memberId);
List<String> recommendedUrls = extractRecommendContentUrls(analysis);

String prompt = "지금 사용자의 상태에 따라 관련되거나 정신적으로 도움 되는 콘텐츠 10개를 추천해줘";
prompt = recommendService.createPrompt(
Expand All @@ -91,12 +86,8 @@ public ContentListResponse saveReRecommendContents(
= getRecommendContentsByAnalysis(analysis, member, prompt);
// TODO: 추후에 feedback을 통해서 재추천 컨텐츠를 가져와야 함

List<Content> savedContents = saveOrUpdateContents(recommendedContents);

diaryAnalysisService.saveRecommendContents(analysis, savedContents);

return ContentListResponse.from(
savedContents.stream()
recommendedContents.stream()
.map(content -> ContentListResponse.ContentResponse.from(
content,
contentQueryService.getContentLikeNumber(content),
Expand Down Expand Up @@ -152,41 +143,7 @@ private List<Content> getRecommendContentsByAnalysis(
}
}

private List<Content> getRecommendContentsByAnalysis(
DiaryAnalysis analysis,
List<String> recommendedUrls,
String feedback
) {
// TODO: gpt api와 youtube api를 통해서 재추천 컨텐츠를 가져와야 함
return null;
}

private List<Content> saveOrUpdateContents(List<Content> recommendedContents) {
List<String> urls = recommendedContents.stream().map(Content::getUrl).toList();
Map<String, Content> existingContents = contentRepository.findByUrlIn(urls).stream()
.collect(Collectors.toMap(Content::getUrl, Function.identity()));

List<Content> toSaveContents = new ArrayList<>();
for (Content content : recommendedContents) {
Content existingContent = existingContents.get(content.getUrl());
if (existingContent != null) {
existingContent.updateContent(content);
toSaveContents.add(existingContent);
} else {
toSaveContents.add(content);
}
}

return contentRepository.saveAll(toSaveContents);
}

private void validateRecommendLimit(String memberId) {
memberService.decrementRemainRecommendNumber(memberId);
}

private List<String> extractRecommendContentUrls(DiaryAnalysis analysis) {
return analysis.getRecommendContents().stream()
.map(RecommendContent::getContentUrl)
.toList();
}
}
Loading