We wanted to keep the focus on (1) foundation VLMs and (2) open source OCR models.
We had Mistral previously but had to remove it because their hosted API for OCR was super unstable and returned a lot of garbage results unfortunately.
Paddle, Nanonets, and Chandra being added shortly!
We had Mistral previously but had to remove it because their hosted API for OCR was super unstable and returned a lot of garbage results unfortunately.
Paddle, Nanonets, and Chandra being added shortly!