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.

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

Semantic embedding models retrievers #9

Open
olbackuper opened this issue Oct 14, 2024 · 1 comment
Open

Semantic embedding models retrievers #9

olbackuper opened this issue Oct 14, 2024 · 1 comment

Comments

@olbackuper
Copy link

olbackuper commented Oct 14, 2024 •
edited
Loading

Hi, I just looked into the paper and code briefly and I wonder if currently, BM25 is in fact the only retrieval model that is supported? No semantic models as retrievers functionality is built-in by default?
@ronakice
Copy link
Member

Hey! Most models should be supported, it's all about surfacing that as a REST endpoint which the RAGnarok models can access (which we do in the demos) or make sure they are in the standard retrieve results format shared by this codebase and RankLLM). In fact in most cases we end up running generation over reranked results (after several rounds)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@ronakice @olbackuper