Experimental node for using a VLM within dora.
This node is supposed to be used as follows:
- id: dora-qwenvl
build: pip install dora-qwenvl
path: dora-qwenvl
inputs:
image:
source: camera/image
queue_size: 1
text: dora-distil-whisper/text
outputs:
- text
env:
DEFAULT_QUESTION: Describe the image in a very short sentence.