Find answers from the community

Updated 3 months ago

Let's say you have a pdf with a variety

Let's say you have a pdf with a variety of instructions, including pictures between each instruction. The parsers I'm using seem to only store text. Is there another setup that also support images? I'd like the answers it returns to include the screenshots.
O
L
3 comments
My sense here is that I need to preprocess the PDF.
  1. Open the PDF,
  2. extract image and save with a reference
  3. replace image in text with link to image
  4. Save new file for indexing.
Have you tried llama-parse? This is pretty much what it was made for
Alternatively, I know stuff like unstructured or marker will work if you need a local solution, but probably not as well
Add a reply
Sign up and join the conversation on Discord