Skip navigation
By now, everyone knows that single-vector embedding models are hugely limiting for modern workflows.
0:00 / 0:11

By now, everyone knows that single-vector embedding models are hugely limiting for modern workflows.

Mixedbread

@mixedbreadai4.1K followers

Visit on X

41,133 views

By now, everyone knows that single-vector embedding models are hugely limiting for modern workflows. But they contain than you think: you can extract sparse Latent Terms from them. And it turns out that BM25 is all you need to turn this vocabulary into a strong retriever.

Comments

Comments from the original post on X (Twitter)

No comments yet