←back to thread

All-in-one embedding model for interleaved text, images, and screenshots

(blog.voyageai.com)
261 points fzliu | 5 comments | 17 Nov 24 07:42 UTC | HN request time: 1.036s | source
Show context
carschno ◴[17 Nov 24 09:25 UTC] No.42163036[source]▶
This does read very impressive. Any critical perspectives on the presented evaluation? What about noon-English text?

I understand the model is, like for other commercial ones, available exclusively through their API, right?

replies(1): >>42163169 #
1. stephantul ◴[17 Nov 24 09:59 UTC] No.42163169[source]▶
Yes, voyage models are API only.

There was a part here about multilingualism but that was wrong! Sorry!

FWIW: Voyage also has separate `law`, `code`, and `finance` models. See [1]

Really cool results, anyway.

[1]: https://docs.voyageai.com/docs/embeddings

replies(1): >>42163250 #
2. fzliu ◴[17 Nov 24 10:23 UTC] No.42163250[source]▶
Glad you liked the results! We do have multilingual models (and rerankers) -- voyage-3, in particular, is multilingual: https://blog.voyageai.com/2024/09/18/voyage-3/

voyage-multimodal-3 is multilingual as well, supporting the same set of languages as voyage-3.

replies(1): >>42163267 #
3. stephantul ◴[17 Nov 24 10:26 UTC] No.42163267[source]▶
Sorry for spreading false information. I edited the post above.

It is interesting that you’re not as up front about multilingualism compared to cohere. They seem to mention it a lot, which led to my confusion.

replies(1): >>42163279 #
4. fzliu ◴[17 Nov 24 10:30 UTC] No.42163279{3}[source]▶
No worries at all. That's great feedback and an area of improvement for us when it comes to future posts -- we'll be more explicit about multilingualism in blogs and in our docs.
replies(1): >>42164398 #
5. ◴[17 Nov 24 14:38 UTC] No.42164398{4}[source]▶