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

Support for Qdrant bm42 document encoder #337

Open
cdxker opened this issue Jul 10, 2024 · 1 comment · May be fixed by #338
Open

Support for Qdrant bm42 document encoder #337

cdxker opened this issue Jul 10, 2024 · 1 comment · May be fixed by #338

Comments

@cdxker
Copy link

cdxker commented Jul 10, 2024

Feature request

Support for https://huggingface.co/Qdrant/all_miniLM_L6_v2_with_attentions model's document embeddings

Motivation

We want to test out bm42's performance when placed in a server when compared to splade-v2.

Your contribution

I have a PR that proposes a way to add support for the sparse embedding model
@cdxker cdxker linked a pull request Jul 10, 2024 that will close this issue
Open
4 tasks
@OlivierDehaene
Copy link
Member

Already answered on the PR:

BM42 is super controversial.
See https://x.com/Nils_Reimers/status/1809334134088622217
I'm on the side of waiting a bit to see how this evolve.

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

Successfully merging a pull request may close this issue.

feature: support bm42 embeddings devflowinc/text-embeddings-inference
2 participants
@OlivierDehaene @cdxker