Perplexity Releases Open-Weight pplx-embed-v2-context Embedding Models in 9B and 0.6B
antoine_chaffin · x · 2026-11-03
Perplexity has released pplx-embed-v2-context, open-weight vision-language embedding models in 9B and 0.6B sizes, with a paper co-written with turbopuffer.
Key design: each document or chunk returns a single int8 vector, and chunk embeddings still see the whole surrounding document — so retrieval gets small chunks with full-document context. Text and images are supported, and a practical asymmetry lets you index with the 9B model while serving queries with the 0.6B one. tomaarsen's repost links a thread explaining how they work.
More from Models
- Google AI Chat Long Conversations Break, Only Returning Error Message — batimfan4ever · 2026-11-04
- Open-source FM-Pochi-32B claims IMO 2026 bronze, first fully open LLM to medal — Ryan__Rhys · 2026-11-04
- Testing LongCat-2.5 on Real Long-Horizon Work via Claude Code — FellMentKE · 2026-11-04
- LongCat 2.5 Tested in Claude Code: One Prompt Builds a Cinema Landing Page — FellMentKE · 2026-11-04
- 'Astra Can Read and Write Weights to Improve Qwen' Claim Debunked as Misleading — AlyoshaV · 2026-11-04
- JFPuget's team takes 3rd on both Kaggle ARC-AGI competitions ending the same day — JFPuget · 2026-11-04