I want OCR-assisted matching for figure and table graphics in the full text parser.

I want OCR-assisted matching for figure and table graphics in the full text parser.: a task in MiMo-V2.6-RL-harbor-code: MiMo-V2.6-RL Code (Harbor) (Harbor dataset). I also want a public OpticalCharacterRecognitionGraphicMatcher(ocr model, max resolution=1024) matcher with get graphic…