Skip to main content

News

  • Perplexity
  • pplx-embed-v2-context-9b-preview
  • Developer

Perplexity previews contextual embeddings that keep retrieved chunks tied to their document

Perplexity released a contextual retrieval preview on Hugging Face: document chunks are encoded together and each returns an embedding informed by surrounding content. The model supports 1024- and 2048-dimensional representations and int8 output. Its card warns that later releases may break compatibility and that queries need a separate encoder method. The official blog index dates the announcement September 30; this is not a new search-agent launch.

Published (date only)Updated 2 sources

Primary source

Perplexity on Hugging Face

Read the original: Contextual embedding preview model card

Opens Perplexity on Hugging Face in a new tab. Read it there before you rely on the summary above.

Unlock the full brief free.

  • What to check before you trust this story, written down
  • Each verified source, with why it matters and who published it
  • A note whenever a source has been withdrawn
  • Thirty days of stories to browse, not seven

This is not an account: there is no password, and the unlock is a cookie in this browser. You also join the Rise Productive newsletter from Demetri Panici, about once a week: what I built and what changed in AI. We'll email you a link to confirm, and you can unsubscribe in one click. The same signup unlocks every free tool on the site. How your email is handled.

Related on Rise Productive

Perplexity previews contextual embeddings that keep retrieved chunks… | Rise Productive