Perplexity Releases pplx-embed-v2-context-9b-preview: A Contextual Embedding Model That Retrieves Answers and Their Supporting Evidence
MarkTechPost
Read Full Article at MarkTechPost →Ad Slot — In-Article (728x90)
Perplexity Research and turbopuffer have released pplx-embed-v2-context-9b-preview, a contextual embedding model for RAG pipelines. Each chunk is embedded with the full document in view. The real change is the training signal.
The model learns to retrieve the answer along with the context needed to verify it, not one ‘gold passage. ’ P Is it deployable?
This is a summary. For the full story, read the original article at MarkTechPost.
Original source: MarkTechPost