Llama3.2-vision throws exception: KeyError: 'text'

[bjornmp]

Describe the bug
Trying to use Llama 3.2-vision, after pasting the image from clipboard, the following error appears:

Traceback (most recent call last):
  File "/app/share/Alpaca/alpaca/window.py", line 585, in <lambda>
    clipboard.read_text_async(None, lambda clipboard, result: self.cb_text_received(clipboard.read_text_finish(result)))
                                                                                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
gi.repository.GLib.GError: g-io-error-quark: No compatible transfer format found (15)

Then, after adding some prompt text and pressing Enter, the following exception below is thrown.

Screenshots

Debugging information

Exception in thread Thread-8 (generate_message):
Traceback (most recent call last):
  File "/usr/lib/python3.12/threading.py", line 1075, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.12/threading.py", line 1012, in run
    self._target(*self._args, **self._kwargs)
  File "/app/share/Alpaca/alpaca/instance_manager.py", line 54, in generate_message
    messages = chat.convert_to_ollama()[:list(chat.messages.values()).index(bot_message)]
               ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/share/Alpaca/alpaca/custom_widgets/chat_widget.py", line 252, in convert_to_ollama
    message_data['content'][0]['text'] += message.text
    ~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^
KeyError: 'text'