Multimodal Report Generation #356

Open
opened 2026-02-16 00:17:37 -05:00 by yindo · 0 comments
Owner

Originally created by @rferrazd on GitHub (Nov 26, 2024).

I was going over this notebook and I wondered if it can extract images from pdfs and store those images as the images chunk. When testing it, it appears that the entire pdf pages where stored as images instead of the images in the pdf. Is it possible for it to store just the images in the pdfs instead of the entire pdf pages?

Thank you!

https://github.com/run-llama/llama_parse/blob/main/examples/multimodal/multimodal_report_generation.ipynb

Originally created by @rferrazd on GitHub (Nov 26, 2024). I was going over this notebook and I wondered if it can extract images from pdfs and store those images as the images chunk. When testing it, it appears that the entire pdf pages where stored as images instead of the images in the pdf. Is it possible for it to store just the images in the pdfs instead of the entire pdf pages? Thank you! https://github.com/run-llama/llama_parse/blob/main/examples/multimodal/multimodal_report_generation.ipynb
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#356