run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 01:15:06 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Parse .pdf that contains images what build from small pieace of images #229

New Issue
Closed
opened 2026-02-16 00:17:12 -05:00 by yindo · 2 comments
yindo commented 2026-02-16 00:17:12 -05:00
Owner
Copy Link
Copy Source

Originally created by @cay89 on GitHub (Aug 13, 2024).

What solution exists if the processed file has images made up of smaller images, but I need the entire image as it appears in the document? For example, here is this user manual: https://partners.gorenje.com/fts/GetDigitDoc.aspx?sifra=588561&jezik=en&tipVsebine=1&docName=gv61010uk_en.pdf

Now, if I process this with LlamaParse and download the images, I get something like this:

image

Is there a solution for this?

Originally created by @cay89 on GitHub (Aug 13, 2024). What solution exists if the processed file has images made up of smaller images, but I need the entire image as it appears in the document? For example, here is this user manual: https://partners.gorenje.com/fts/GetDigitDoc.aspx?sifra=588561&jezik=en&tipVsebine=1&docName=gv61010uk_en.pdf Now, if I process this with LlamaParse and download the images, I get something like this: ![image](https://github.com/user-attachments/assets/9013d356-bef9-4ead-8825-63490942c33b) Is there a solution for this?
yindo closed this issue 2026-02-16 00:17:12 -05:00
yindo commented 2026-02-16 00:17:12 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Aug 15, 2024):

Hi @cay89,
I don't know any tool that handles re-stitching tiles together.
Thus said, if you use the Json output, you have the dimensions and coordinates of every images so you can create a script that detect if two images are side by side and merge them together.

I'm sorry but this is currently not in the scope of LlamaParse, so I'll close it as "won't fix".
I you have an important use case with it, please tell us.

@BinaryBrain commented on GitHub (Aug 15, 2024): Hi @cay89, I don't know any tool that handles re-stitching tiles together. Thus said, if you use the Json output, you have the dimensions and coordinates of every images so you can create a script that detect if two images are side by side and merge them together. I'm sorry but this is currently not in the scope of LlamaParse, so I'll close it as "won't fix". I you have an important use case with it, please tell us.
yindo commented 2026-02-16 00:17:12 -05:00
Author
Owner
Copy Link
Copy Source

@cay89 commented on GitHub (Aug 16, 2024):

@BinaryBrain It's fine, I was just wondering if there was an easier solution than piecing it together myself. But since I won't be dealing with this type of PDF files for the time being, thanks for the answer!

@cay89 commented on GitHub (Aug 16, 2024): @BinaryBrain It's fine, I was just wondering if there was an easier solution than piecing it together myself. But since I won't be dealing with this type of PDF files for the time being, thanks for the answer!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#229
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?