Skip to content
All tags

#pplx-embed

2 posts
aideep-diveRAG 技法大全

pplx-embed-v2-late: An Open Late-Interaction Model That Searches PDF Pages Without OCR

On October 7, Perplexity open-sourced two ColBERT-style multimodal embedding models (0.6B and 9B, MIT license) that keep one 128-dim vector per token, score with MaxSim, and search PDF page images directly. The 9B scores 92.4% on MADQA (self-reported, with a Gemini 3.5 Flash agent); the cost is an index that grows with document length.

#pplx-embed#late-interaction#colbert#multimodal-rag#visual-rag#embeddings#rag
techdeep-diveAI 模型家族

pplx-embed: Perplexity's Embedding Model Family and How to Choose Between Its Three Lines

pplx-embed is the embedding family Perplexity has been releasing since February 2026, in three lines: v1 single-vector (0.6B/4B, API at $0.004/$0.03 per 1M tokens), context embeddings (v1 plus a 9B v2 preview), and v2-late multi-vector (0.6B/9B, searches PDF page images directly). They solve different problems; v2 does not replace v1.

#llm#embeddings#perplexity#pplx-embed#rag#open-weights#model-family-pplx-embed#model-selection