Skip to content

PostgresDB 기반 VectorDB 사용 #97

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

Jump to bottom
Open
3 tasks
nonegom opened this issue May 4, 2025 · 0 comments
Open
3 tasks

PostgresDB 기반 VectorDB 사용 #97

nonegom opened this issue May 4, 2025 · 0 comments
Assignees
@nonegom
Labels
agent The core processing component that interprets user input, manages workflows, and orchestrates the SQ enhancement New feature or request

Comments

@nonegom
Copy link
Contributor

nonegom commented May 4, 2025

Why ❓

현재 상황 및 문제점:

  • 현재 RAG 단계에서 Vector DB로 FAISS를 사용하고 있음
  • FAISS의 경우, 가벼운 데이터에는 괜찮지만 장기적인 관리 및 하이브리드 검색 등 미지원

How 🤔

해결 방안 ✅:

  • 내부 DB로 PostgreSQL을 연결해서, 해당 DB에서 Vectorize를 사용할 수 있게 설정 (PGVector)

What 🛠️

  • PostgresDB 연결
  • VectorDB 연결
  • retriever 경로 변경 및 DB 적재 확인
@nonegom nonegom added agent The core processing component that interprets user input, manages workflows, and orchestrates the SQ enhancement New feature or request labels May 4, 2025
@nonegom nonegom self-assigned this May 4, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@nonegom nonegom

Labels
agent The core processing component that interprets user input, manages workflows, and orchestrates the SQ enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@nonegom