add pdf support

[freetown113]

add minimal necessary logic to support handling of the files in pdf format

[Timothyxxx]

Nice work, we will go through it very soon!

[BlankCheng]

Hi, thanks for your great contribution. The code has some circular import issues. I think it is because DocumentSummaryExecutor is imported in document.py but it also imports DocumentDataModel from document.py.
Would you mind trying to fix that and testing it on the local host? Thanks.

[freetown113]

Yes, I shouldn't leave this part of the code in the PR. It was a kind of a draft for the next possible enhancement. I removed it. Please check it now.

[github-actions]

This PR is stale because it has been open 3 days with no activity.

[BlankCheng]

Hi, I've fixed extra imports to avoid circular imports and added .pdf extension support to let it successfully be run locally. I think it looks good to me overall.
However, due to some openai key issue, I cannot test the full functionality as proposed. Would you or other participants be able to local host it and test the pdf functionalities?

[Timothyxxx]

@freetown113

[github-actions]

This PR is stale because it has been open 3 days with no activity.