--- format: "aidr-story-markdown/v1" id: "2bee64b44d33ad5692f68ea33830025ab5588ebac59045edddc50c3b821360e4" canonical_url: "https://aidr.today/2bee64b4?lang=en" title: "Perplexity Open Sources 9B and 0.6B Embedding Models for OCR-Free Search" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-07T17:09:47.000Z" category: "Open Source" topics: ["open-source"] source_urls: ["https://huggingnews.com/ai/perplexity-open-sources-9b-and-06b-embedding-models-for-ocr-free-search-beee8dff","https://marketbrief.now/ai/perplexity-open-sources-9b-and-06b-embedding-models-for-ocr-free-search-beee8dff"] summary: "Perplexity has open-sourced two late-interaction embedding models, pplx-embed-v2-late in 9B and 0.6B parameter versions, that enable OCR-free search across text and images in a shared vector space. The models, hosted on Hugging Face and supported in Sentence Transformers, scored 92.4% on MADQA and 81.3 nDCG@10 on text retrieval tasks for the 9B version. Perplexity reports that pairing the 0.6B query model with 9B indexing improves text retrieval to 79.6 nDCG@10." --- # Perplexity Open Sources 9B and 0\.6B Embedding Models for OCR\-Free Search > [Open the canonical story]() **Published:** 2026-10-07T17:09:47.000Z **Category:** Open Source **Topics:** open\-source ## Summary Perplexity has open\-sourced two late\-interaction embedding models, pplx\-embed\-v2\-late in 9B and 0\.6B parameter versions, that enable OCR\-free search across text and images in a shared vector space\. The models, hosted on Hugging Face and supported in Sentence Transformers, scored 92\.4% on MADQA and 81\.3 nDCG@10 on text retrieval tasks for the 9B version\. Perplexity reports that pairing the 0\.6B query model with 9B indexing improves text retrieval to 79\.6 nDCG@10\. ## Sources - [Story source]() - [Story source]()