Perplexity releases pplx-embed-v2-late: 0.6B & 9B text+image retrievers
tomaarsen · x · 2026-10-08
Perplexity released pplx-embed-v2-late with 0.6B and 9B models for text and image retrieval, natively supported in Sentence Transformers. You can search PDFs, slide decks, screenshots, and charts as images without OCR. Sentence Transformers maintainer tomaarsen posted a thread with benchmark highlights.
Related event: Perplexity Open-Sources Multimodal Embedding Models pplx-embed-v2-late(38 posts)→
More from Models
- ChatGPT on Browser Shows 'Capabilities Reduced' Warning — A New Kind of Rate Limit? — jasondeanlee · 2026-10-08
- ChatGPT Work mode vs Codex: same quota, far more tasks done per 5-hour window — sasik520 · 2026-10-08
- Epoch's InnovationEval: AI agents still far from producing real research innovations — Afinetheorem · 2026-10-08
- 113 decision models in 3 weeks: 70 built on Qwen, sub-cent per call — jonathanmalkin · 2026-10-08
- User reports Haiku 5.5 is a major workflow upgrade in screenshot post — Sorcerer12345 · 2026-10-08
- OpenRouter launches Decision Model Rankings, with typesafeai leading all categories — gaganghotra_ · 2026-10-08