(technicalwriting.dev)

484 points jxmorris12 | 1 comments | 12 May 25 15:05 UTC | HN request time: 0.558s | source

Show context

tucnak ◴[12 May 25 18:35 UTC] No.43966166[source]▶

Surprised they never mentioned jina.ai models such as jina-embeddings-v3 at 8K context and outperforming most "contenders" in the MTEB or jina-clip-v2 (multimodal) or "late chunking," also known as mean pooling: https://jina.ai/news/late-chunking-in-long-context-embedding...

The article feels incomplete

replies(1): >>43966580 #

1. kaycebasques ◴[12 May 25 19:18 UTC] No.43966580[source]▶

>>43966166 #

Wasn't on my radar! Thanks for the pointer. I'll look into it. It's hard to keep up with all the embedding models out there.

↑

Embeddings are underrated (2024)