Current build version wont ingest PDF's

[clearsitedesigns]

I'm not sure what changed here, but I've tried many PDFs, and they will not ingest. The system hangs when ingesting. This happens on both PC and mac. It even depends on the demo orca and doesn't ingest. I've converted the PDF to raw text, and it will be ingested.
Did something change in the document loader for PDFs?

[Grunt-prog]

hey hi @clearsitedesigns do you have the downgrade version of localgpt

[clearsitedesigns]

Hi I did not have the downgraded version. I'm using a fairly recent version, I can see that there was an extension issue, looks like that was the problem. That should be easy enough to modify the code.

[M56413893478]

I have the previous version and added a extra line in the contstraints.py file to accommodate for the uppercase extension and that worked fine.

In the new version I am not able to ingest the PDF files due to references to pdf2image and pytesseract modules.

E:\localGPT/SOURCE_DOCUMENTS\7301TopangaLeaseAgreement-TSP.pdf loading error:
No module named 'pdf2image'
E:\localGPT/SOURCE_DOCUMENTS\7301TopangaLeaseAgreement-TSP.pdf loaded.
E:\localGPT/SOURCE_DOCUMENTS\7301TopangaLeaseAgreement-TSP.pdf loading error:
No module named 'pytesseract'