Actions before raising this issue
Is your feature request related to a problem? Please describe.
It appears that the model integration option via Nuclio in the current version of CVAT is limited solely to creating new annotations. If my workflow involves reading existing annotations using a model—specifically to populate certain attributes with processed data (e.g., OCR results)—are there any viable options currently available? I came across a similar reference at https://github.com/cvat-ai/cvat/tree/develop/serverless/openvino/omz/intel/face-detection-0205/nuclio, but it seems that, at the very least, this approach does not allow one to avoid the redundant creation of labels.
Describe the solution you'd like
No response
Describe alternatives you've considered
No response
Additional context
No response
Actions before raising this issue
Is your feature request related to a problem? Please describe.
It appears that the model integration option via Nuclio in the current version of CVAT is limited solely to creating new annotations. If my workflow involves reading existing annotations using a model—specifically to populate certain attributes with processed data (e.g., OCR results)—are there any viable options currently available? I came across a similar reference at https://github.com/cvat-ai/cvat/tree/develop/serverless/openvino/omz/intel/face-detection-0205/nuclio, but it seems that, at the very least, this approach does not allow one to avoid the redundant creation of labels.
Describe the solution you'd like
No response
Describe alternatives you've considered
No response
Additional context
No response