Skip to content
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.

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

Feature for native DB based RAG or Retrievers component #13

Open
Anindyadeep opened this issue Aug 12, 2024 · 3 comments
Open

Feature for native DB based RAG or Retrievers component #13

Anindyadeep opened this issue Aug 12, 2024 · 3 comments

Comments

@Anindyadeep
Copy link
Member

Full end to end support for DB based RAG where user can choose

  1. retriever
  2. The LLM
  3. The embedding model
  4. The algorithm
    etc and they will get an end to end solution for DB based rag. For just the starter, start with Qdrant as the vector DB and sqlite as the DB.
@Anindyadeep Anindyadeep changed the title Feature for native DB based RAG Feature for native DB based RAG or Retrievers component Sep 9, 2024
@ansarizafar
Copy link

We can also use LibSQL which is a fork of SQLite with built-in support for vector search https://turso.tech/blog/turso-brings-native-vector-search-to-sqlite?webui=true&type=signup&content=ai

@Anindyadeep
Copy link
Member Author

yes great point, even I also have been looking into this project for some time. We will be adding a whole new class of retrievers in the upcoming releases. Thanks for sharing

@ansarizafar
Copy link

KuzuDB https://kuzudb.com/ is another good option much better than Sqlite.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants