From the source
Lead story
Ask your AI
Top stories
Models & availability
Latest
Perplexity· PerplexityContextual embedding beyond the gold passage
Trains embedding to retrieve answer and supporting context jointly.
Perplexity released pplx-embed-v2-context-9b-preview, a contextual embedding model preview on Hugging Face.
It uses a context compression model as a teacher to train chunk-level relevance scores, aiming to retrieve both answer chunks and supporting context instead of a single gold chunk.
The model achieves state-of-the-art results on context-bench and ConTEB benchmarks.
From the source
We’re introducing pplx-embed-v2-context-9b-preview , our new contextual embedding model. The model is trained with a novel approach that uses Perplexity’s context compression model as a teacher. We aggregate its token-level predictions into chunk-level relevance scores, teaching the embedding model to retrieve both answer chunks and supporting context rather than a single gold chunk.
Other stories
Perplexity · 2 OctAI maturity: what it means for your organizationPerplexity · 1 OctPerplexity and American Express: AI for growing businessesPerplexity · 1 OctAI Tools for Consultants: Features, Pricing & Alternatives
Amazon · 2 OctSweep thousands of leases for compliance using Amazon Quick and the Adjudicated Query patternAmazon · 2 Oct