Add support for PDF file uploads as context for LLM queries

[andrewwan0131]

Why are these changes needed?

These changes enable users to upload PDF files as context for LLM queries.

Changes made

1. Added PDF file handling capabilities:

   • Implemented PDF file upload support in the web interface
   • Added PDF text extraction functionality
   • Integrated extracted PDF content as context for LLM queries

2. Modified relevant files:

   • Updated gradio web server components to handle PDF uploads
   • Added PDF processing utilities
   • Enhanced chat protocol to include document context

Checks

• I've tested the PDF upload and context integration with various document types by running Chatbot Arena locally

[infwinston]

Thanks @andrewwan0131 left some comments!

[infwinston]

thanks more comments

[CodingWithTim]

@andrewwan0131 @PranavB-11 I resolved the old comments because it is no longer relevant. We can start commenting this new code as it is pretty different from before. The pdfchat is now operational, I will extensively test it and improve it next.

Next steps:

1. Fix some existing UI issues which is bothering me at the moment.
2. Integrate our language detection code into parse_pdf.
3. Add pdf moderator.

[infwinston]

thanks @CodingWithTim ! left some quick comments

[CodingWithTim]

71 files changed?? 😭😭

[PranavB-11]

ohhh it was the formatting commit, it added a billion spaces to every file

[CodingWithTim]

@andrewwan0131 @PranavB-11 @yixin-huang1 Great work guys! I only fixed a few small bugs and cleaned up the logics. Everything now works!

[infwinston]

why we need to remove this?

[andrewwan0131]

This was accidentally created when I pushed the Black formatting commit so we reverted the changes.

[CodingWithTim]

This PR was transfered to internal repo.