-
Hi, I got some corrupted documents, e.g. mutilated cross-reference tables. May I ask, does podofo library provide repair function for corrupted pdf?
-
DocumentCloud currently supports a number of special extensions that can just be added to the DocumentCloud URL ([some are documented here](https://www.documentcloud.org/help/publishing#linking)):
…
-
During [their TUG talk][1], @u-fischer mentioned a [list][2] of LaTeX packages (and classes) that are (in)compatible with the PDF tagging project. We should review the list, compare it with the LaTeX …
-
**Describe the bug**
Typically, `DownloadHandler::CanDownload` is called before any download, giving the developer the opportunity to decide whether a file should be downloaded. `DownloadHandler::Can…
-
Hi,
I would like to use the functionality of Gemini described here: https://ai.google.dev/gemini-api/docs/document-processing?lang=python , in particular, the PDF upload functionality.
But the libra…
IngLP updated
1 month ago
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
How to add sub question and router query engine in single code
-
I tried parsing PDFs today but GROBID seems to leave the author affiliation out for every document.
I used Docker with the GROBID DL model (0.8.1-name-address) and did not specify a consolidation …
-
Pdf should be load in Upstash redis
-
When generating a document with GenerateXps some random spaces between letters of a word appers. In the GeneratePDF of the same document this doesn't occurs.
**To Reproduce**
Any document generate…
-
I was researching on document understanding and i was brought here when i read this
https://arxiv.org/pdf/2403.02969 . Unfortunately the repo is empty? Can you please share the weights/code?