You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have used llmsherpa to process this PDF.
This is a Network Protocol Specification document.
I have utilized the demo provided by you in Colab.
It does not get any error.
When I convert it to text, it is converting only a portion of the pdf. Essentially it is missing lots of information.
I utilized both pdf url and local pdf file path.
I printed all the section titles and the output does not match the pdf. Output is provided here.
I also converted the pdf to text and it is significantly smaller. Converted text file is here.
My main concern: is there any particular reason why llmsherpa might not work for Network Protocol Specification Pdf documents?
The text was updated successfully, but these errors were encountered:
hasandot
changed the title
Pdf Processing is Missing Information
llmsherpa is Missing Information
Jul 2, 2024
I have used llmsherpa to process this PDF.
This is a Network Protocol Specification document.
I have utilized the demo provided by you in Colab.
It does not get any error.
When I convert it to text, it is converting only a portion of the pdf. Essentially it is missing lots of information.
I utilized both pdf url and local pdf file path.
My main concern: is there any particular reason why llmsherpa might not work for Network Protocol Specification Pdf documents?
The text was updated successfully, but these errors were encountered: