-
12추천
-
8추천이미지 링크코드 문서는 300토큰, 일반 문서는 500~800토큰으로 쓰고 있는데요. 법률 문서처럼 구조화된 건 섹션 단위로 자르는 게 낫다는 의견도 있더라고요. 다들 어떻게 하세요?
-
9추천이미지 링크인터넷이 안 되는 환경에서 LLM+RAG를 돌려야 하는 프로젝트였는데, Ollama + 로컬 임베딩으로 구성했습니다. 오프라인 배포에 관심 있으신 분들께 도움이 되길.
-
13추천
-
10추천이미지 링크로컬 RAG 서비스 최소 구성 템플릿을 만들어봤습니다. docker compose 하나로 Ollama + FastAPI + ChromaDB가 뜹니다. 피드백 환영해요.
-
11추천
-
15추천폐쇄망용 완전 오프라인 RAG. Ollama만으로 동작, 임베딩은 bge-m3. 피드백 환영합니다.
-
8추천금융권 고객사에 설치했습니다. 인터넷 완전 차단 환경에서도 임베딩+검색+생성 전부 동작. 자세한 내용은 글에.
-
8추천한국어 문서 검색인데 bge-m3 vs multilingual-e5 고민입니다. 경험 공유 부탁해요.
-
8추천도메인 용어가 많은데 파인튜닝이 나을지 RAG가 나을지. 둘 다 해보신 분들 의견 궁금합니다.
-
9추천Ticket deflection went from 0% to 38% in a month. Here's the architecture and the mistakes we made.
-
5추천We use RAGAS but the scores don't correlate with human judgment. What do you actually use in production?
-
6추천Chroma vs Qdrant vs LanceDB for a small self-hosted RAG service. Disk and RAM matter — running on a free-tier VM.
-
8추천Replaced a custom fine-tune with a generic 8B + good retrieval. Cheaper to maintain, better scores. Data point for you.
-
7추천bge-m3에서 다른 모델로 바꾸려는데, 기존 문서 전부 다시 인덱싱해야 하는 게 맞는지요?
-
6추천Model cites chunks that don't actually support the answer. Any post-processing tricks that work?
-
8추천Our org has 10k pages of policy PDFs nobody reads. Built a RAG bot with citations that links back to the exact page. Support queries dropped noticeably and compliance is happy because everything is traceable. Side project that became the team's favorite tool.
-
3추천We need to ground answers in internal docs that update weekly. RAG feels obvious but retrieval quality is killing us. Fine-tuning is a one-time cost but the docs change. Anyone run a hybrid? What's your split?
-
6추천링크We were merging PRs blind. Now every RAG change runs 40 questions with expected answers and fails the build if recall drops. It's crude but it caught two regressions last week. Sometimes the simple stuff wins.
-
4추천Long context is expensive and my tests show the model forgets the middle anyway. Chunking into a RAG loop works but feels like giving up. Do you just pay for big context or actually engineer around it?
-
6추천링크Been dumping notes, highlights, and bookmarks into a local RAG setup for two years. Search is instant and surprisingly good. Open-sourced the whole thing so it's reproducible. Warning: your old notes are more embarrassing than you remember.
-
3추천In hindsight it was a fair question but I panicked and started rambling about chunk sizes. I've built two RAG systems in production. Doesn't matter, whiteboard me is a different person. Anyone else have interview horror stories?
-
5추천We're about to onboard our first enterprise customers and I have to decide. Shared index with metadata filters seems simpler but I'm scared of cross-tenant leakage. Per-tenant collections mean more ops. What do you run?