Chart Extraction. This is a context aware chart element detection model that can detect 18 classes for chart basic elements, excluding plot elements.

Object Detection. This uses a base YOLO model that is fine-tuned by NVIDIA to detect charts, tables and titles in documents.

Table Extraction. This is an open-source model from Baidu Research and receives an image as input, runs OCR on the image, and returns the text within the image and their bounding boxes.

Highly efficient Mixture of Experts model for RAG, summarization, entity extraction, and classification

One-shot visual language understanding model that translates images of plots into tables.