[1.1.x] Refactor the entire tool

[SkyaTura]

Since I first created this project, my understanding on OpenAI's API and LLMs got significantly improved. That being said, I think this deserve an update for implementing things I didn't knew back then, alongside with better error handling.

Goals for the new version

• Use completion api over chat api #5
• Better default prompt #6
• Better chunk management #10
• Retry failed chunks before throwing #11
• Output in the same directory as the input file is #7
• Batch translation (multiple inputs) #12
• Output file stream #8
• "Continue" mode #9
• Add tests #13