[HN Gopher] voyage-3.5 and voyage-3.5-lite: improved quality for...
___________________________________________________________________
voyage-3.5 and voyage-3.5-lite: improved quality for a new
retrieval frontier
Author : fzliu
Score : 20 points
Date : 2025-05-22 06:19 UTC (2 days ago)
(HTM) web link (blog.voyageai.com)
(TXT) w3m dump (blog.voyageai.com)
| serjester wrote:
| There's the interesting question here - has embedding performance
| reached saturation? In practice, most people are pulling in 25 to
| 100 candidates and reranking the results. Does it really matter
| if a model is 1 - 3% better on pulling in the top 10 when it's
| probably going to be captured in the top 50? I think at this
| point the real frontier is making these models as small as
| possible to minimize hosting costs.
| opdahl wrote:
| I think it really depends on the use case. It is well known
| that most users really only look and engage with the top few
| (1-3) results in a search. If you can get the most relevant
| result from position, let's say 7 to 2, that can have a big
| impact on the user experience. And I know they market this for
| RAG, but I think that's just marketing and this is as relevant
| for traditional search.
| kaycebasques wrote:
| So, based on the emphasis on "retrieval" in the blog title, are
| these models narrowly focused on retrieval tasks only? E.g. I
| shouldn't use them for clustering, STS, and so on?
|
| How does voyage-3.5 compare against Gemini Embedding (GE)? I
| thought GE had top spot for retrieval tasks on MMTEB. Is Voyage
| saying here that voyage-3.5 now has the top spot? Or is it just
| that, for the 10 specified datasets, voyage-3.5 outperforms the
| specified OpenAI and Cohere models.
| greenavocado wrote:
| How do these models compare to BGE M3
___________________________________________________________________
(page generated 2025-05-24 23:01 UTC)