TGViewer
Perplexity Perplexity @perplexity_ai · 3.72K subscribers
Post #299 958
We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view.

pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB and turbopuffer's new, privately held context-bench.

https://pplx.ai/context-embed-tg
  • 👍 2
  • 👏 2
  • ❤ 1
  • 💯 1
Open in Telegram All posts from @perplexity_ai
More from @perplexity_ai
  1. Oct 16, 2026Gemini 4 Argon sets a new record on WANDR. It is now available in Perplexity for Max subsc…
  2. Oct 15, 2026NVIDIA’s Nemotron 3.5 Super VL is now available in Perplexity for Pro and Max subscribers,…
  3. Oct 14, 2026Ultrafast versions of GPT-6 Astra and SOL 6.1 are now available in Perplexity Computer for…
  4. Oct 11, 2026Computer's new website editor lets you queue up requested changes to specific elements on…
  5. Oct 9, 2026pplx-decider-v1.1-27b scores the highest on Decision Bench for accuracy, with the lowest c…
  6. Oct 7, 2026We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve te…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →