[Enhancement]: DeepL API for direct document to document translation

[leondape]

What features would you like to see added?

When trying to translate documents and keeping the styling and everything, DeepL is still the best choice.
Code interpreter cannot solve this reliably. It can't handle powerpoint at all for example.

DeepL works well.

More details

I started to create a tool for DeepL API but am having issues of how to expose uploaded files to the tool.
Code interpreter files can obviously be forwared but I don't know how it could work for a custom tool. Though it does work for openai image tools (for images) now.

Could somebody give me a hint for how to achieve that?
Or does anybody want to cooperate on that?

API Reference: https://developers.deepl.com/docs/api-reference/document

Which components are impacted by your request?

No response

Pictures

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

The Code Interpreter API can create and edit powerpoints:

You could use DeepL as an MCP server or action in conjunction with the Code Interpreter API.

[leondape]

Thank you for the reply! Somehow pptx didn't work when I tried it, but now all is good.

Speaking of Code interpreter API: Could you be able to respond to my emails on [email protected]? I currently cannot integrate code interpreter API into our company because of legal reasons. It's just paperwork and I can help you resolve it.
That would make the code interpreter api much more accessible in legal frameworks of the EU.