-
Task
-
Resolution: Done
-
Not Evaluated
-
None
-
None
-
None
Use the existing QuteAI app https://git.qt.io/ai-ui/qt-ai-app/-/tree/main/UI/QtQML_AI as the base, combining with the functionality implemented in the PoC https://git.qt.io/ai-ui/qt-ai-inference-api/-/blob/main/Screen01.ui.qml.
The app should
- have the ability to chat with the AI via text [DONE]
- have the ability to record audio to communicate with the AI [DONE]
- have the ability to pass images for the AI
- use the Qt AI Inference API [DONE]
Additional ideas:
- option to switch to generating images via AI
- adding object detection/recognition
- a settings view for e.g. adjusting URLs/models [DONE]
1.
|
Add support for providing images to AI |
|
In Progress | Juho Annunen |
2.
|
Add dynamic chat view for talking to the assistant |
|
Closed | Tinja Paavoseppä |
3.
|
Add the support for talking to the AI |
|
Closed | Tinja Paavoseppä |
4.
|
Add the Qt AI Inference API into the demo |
|
Closed | Tinja Paavoseppä |
5.
|
Add a spinner or other indicator to show processing state |
|
Closed | Unassigned |
6.
|
Add Settings menu |
|
Closed | Tinja Paavoseppä |
7.
|
Clean up project structure and code |
|
Closed | Unassigned |
8.
|
Write a README |
|
Closed | Tinja Paavoseppä |
9.
|
Modify the app for desktop use |
|
Closed | Tinja Paavoseppä |
10.
|
Image support improvements |
|
Closed | Unassigned |
11.
|
Add text-to-image support |
|
Closed | Tinja Paavoseppä |