Find answers from the community

Updated 3 months ago

Can I implement training of images from

Can I implement training of images from PDF in llama-index?
L
o
3 comments
It's not supported right now, but you could always write your own loader for it, and create your own ImageDocument instances.

Right now there are two options for images in llama-index
  1. Generating a caption for the image and retrieving based on the caption
  2. Applying ocr on the image and retrieving based on the OCR
PyPDF can extract images it looks like, so this could be added to the loader in the future
https://pypdf.readthedocs.io/en/stable/user/extract-images.html
okay, I look forward you guys to imlement image training from pdf soon.
Add a reply
Sign up and join the conversation on Discord