Hi everyone! 
I’m working on a small educational project and looking for a tool that can help with vectorizing PDFs — specifically ones that include simple math formulas and visual content aimed at elementary school children (ages 6–12) (pinecone, supabase, mathpixpdfloader…Has anyone used any of these for vectorization and later integration with n8n?).
The goal is to extract the content in a structured way so it can later be used in an automated workflow with n8n, possibly for content tagging or AI-based generation.
Has anyone here used a tool or service (preferably with an API) that handles this kind of PDF content well? Bonus points if it works nicely with math notation (fractions, symbols, etc.).
Thanks in advance! 