Odaia

- Fixed markdown / HTML formatting
- Added config option "Use color theme in chat window" in main settings
- Added configuration for system prompt to use with vision in Vision Inline plugin settings

- Added Markdown and HTML formatting in the chat window (beta version)
- Added the display of images, files and URLs internally in the chat window
- Added fully integration with images, attachments, and files inside the chat window
- Added vision capture and image generation directly into the chat window (via the DALL-E Inline plugin)
- Improved audio speech generation (eliminated the silence that prematurely truncated the previous audio output before generating the next speech synthesis)

- Added commands part strip from speech generation
- Added img check for links sending to vision in auto mode

- Added a new plugin: GPT-4 Vision (inline - in any chat). Plugin integrates vision capabilities with any chat mode, not just Vision mode. When the plugin is enabled, the model temporarily switches to vision in the background when an image attachment or vision capture is provided.

- Added a new plugin: DALL-E 3 Image Generation (inline) which enables image generation in any chat and mode, seamlessly in the background - just request an image from any model, like GPT-4, and it will generate it "inline."
- User Interface optimizations.
- Added type hints to the code.
- Fixed issue with sending attachments in Assistant mode.

- Notepad restore fix