About
Parsing-free RAG pipeline backed by vision-language models — index PDFs and slides as images instead of text.
Why it made the leaderboard
RAG without the parsing step: a vision-language model indexes PDFs and slides as images, so layout, tables, and figures survive retrieval instead of being mangled by text extraction.
Tags
ragvlmretrievaldocumentmultimodal
Tech Stack
Python
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.