Refact the backend code to make it more modular and allow for easy plugin integration in the future

[snowyu]

Currently, there are 3 backend components: chat, text-to-speech (TTS), speech-to-text (STT). Also, a storage backend is needed and the UI could be considered as a special fifth backend component too.

• Chat
• TTS(text-to-speech)
• STT(speech-to-text)
• Storage
• UI(Optional)

IMO, all interfaces in the future are only auxiliary, and all interfaces should be able to be called by talking to the bot.

[snowyu]

@kasumi-1 Currently the back-end code is split in different directories, so the first step is to put them in the same directory, such as:

chatbot/
   llamacpp/
   openai/
tts/
   coqui/
   openaiTTS/
...

And the UI interface should be changed from the modal dialogue box to the modeless dialogue box: Users can use chat commands to operate the interface at the same time.

[kasumi-1]

@snowyu agree! But, what do you mean by modeless dialogue box? Like, implementing slash commands or something?

[snowyu]

A modeless dialog box (also known as non-modal) is a type of user interface element that allows users to interact with it without interrupting their current task or session. This means that while the dialog box is open, the rest of the application remains accessible and responsive.

implementing slash commands

Yes, exactly. You can type slash command to open UI or change the config in the UI.
The next step is that the bot should analyze user intent and automatically call slash commands based on those intentions.