pplx-embed-v2-late
For developers building search: two Perplexity models that find matching text and images, including PDF pages, without converting them to text first.
Details
- Most search models squeeze each document into one summary vector. These keep a small vector for every word or image patch, so different parts of a question can match different parts of a page
- Searches rendered PDF pages straight from the image, skipping the step of pulling text out first
- Two sizes, 0.6B and 9B parameters, that share the same embedding space, so you can index with one and search with the other
- Publicly available on Hugging Face and works with the sentence-transformers and transformers libraries
- Joins pplx-embed-v2-context, a contextual embedding model Perplexity released the week before
Best for
Building internal search over long or visual documents like slide decks, reports, and scanned PDFs.
When to use it
Your current search misses details in long or image-heavy files because it boils each document down to one summary.
Who benefits
Developers and data teams building retrieval or knowledge-base tools for their company.
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →