Skip to content

Perplexity releases pplx-embed-v2-context-9b-preview contextual embedding model

Perplexity

The model trains contextual chunk retrieval by distilling relevance scores from a query-aware context compression model instead of single gold chunks.

Key points

  • The preview model is available on Hugging Face.
  • Uses 1 KB per vector with 1,024 dimensions in int8 format, compared to 8 KB for voyage-context-4.
  • Achieves the highest average nDCG@10 on ConTEB among tested models and leads turbopuffer's context-bench in answer and evidence retrieval.

Why it matters

Engineers building RAG pipelines get higher chunk retrieval accuracy with lower storage overhead by capturing full-document context.

Sources