which vision model is R1 using for text extraction from image or pdfs.
#127
by
ashutoshroy02
- opened
i want to do ocr on a Archaeological book pdf (scanned book) . and extract text in markdown preceisly and very very accurately to make my RAG model super precise . i have tried lama-parser, docling , gemini, tessarct . i want to try deepseek for doing that
i genuinely dont know how you will be able to do that. but deepseek is a company. Also, you may/can do that in deepseek chat if your book is small enough
i genuinely dont know how you will be able to do that. but deepseek is a company. Also, you may/can do that in deepseek chat if your book is small enough
He can try to make the file smaller by using ilovepdf. Should make it small enough to parse it.