Hey all, for some reason there is no PDF processing packages in the code-interpreter, just a while ago

import fitz

was working but even then other packages available in OpenAI's code interpreter wasn't available there but now even fitz isn't available. I'd really appreciate the help

Hey @Siraj, could you share: - A list of PDF processing packages (beyond fitz/PyMuPDF) or other packages you need - Any other packages from OpenAI's code interpreter that you found useful This will help us prioritize which libraries to add. Thanks!

Thanks for the response, @Abhishek! for now I'm looking for just PDF text extractors as thats needed for the tasks I'm working on. These are packages available in OpenAI's code interpreter: PyPDF2 pdfminer fitz (PyMuPDF) I can already see numpy and pandas are available, which is cool! it would be great if there are other scientific libraries like biopython, rdkit etc.,

Thanks for sharing, I'll check and get back soon.

Thank you!

Hey, team is working on this and I'll get back to you on our progress by EOD.

Cool! thanks a lot

Hi @Siraj, sorry for the delay in responding here. Let me check with team and get back ASAP.

Thank you!

Hi Siraj, we've added support for PDF packages and testing it internally, I'll keep you posted.

Cool! thank you 🙂