InfiniFlow
extract chunk with vision LLM? #7203
Chunshan-Theta
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I'm wondering if LLMs with vision capabilities could be used to process documents. I'm having trouble with OCR(deepdoc) when dealing with educational materials for young children. The formatting is often quite unique, and OCR often makes mistakes. Could an LLM with vision provide a more accurate way to extract information?
Beta Was this translation helpful? Give feedback.
All reactions