run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-07-13 21:32:29 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Failed to interpret bar charts correctly #175

New Issue
Open
opened 2026-02-16 00:17:03 -05:00 by yindo · 2 comments
yindo commented 2026-02-16 00:17:03 -05:00
Owner
Copy Link
Copy Source

Originally created by @oy321 on GitHub (Jul 5, 2024).

image

I am trying to parse this image but the result is very wrong:

image

even though I asked it specifically in the prompt to pay attention to the relationship between text and chart elements.

Originally created by @oy321 on GitHub (Jul 5, 2024). ![image](https://github.com/run-llama/llama_parse/assets/5550065/f9ea80dd-3be4-462e-85f7-b3063b4aa362) I am trying to parse this image but the result is very wrong: ![image](https://github.com/run-llama/llama_parse/assets/5550065/7edd5b14-cc71-4d9d-aafc-b3910a388f9b) even though I asked it specifically in the prompt to pay attention to the relationship between text and chart elements.
yindo added the complex layoutfigure labels 2026-02-16 00:17:03 -05:00
yindo commented 2026-02-16 00:17:03 -05:00
Author
Owner
Copy Link
Copy Source

@hewliyang commented on GitHub (Jul 7, 2024):

+1 here. Charts / any images for that matter are being hallucinated as Markdown tables. Specifying instructions doesn't help either. Are you guys passing all images to a VLM with conversion to MD table as a instruction?

JSON return type doesn't work now either.

@hewliyang commented on GitHub (Jul 7, 2024): +1 here. Charts / any images for that matter are being hallucinated as Markdown tables. Specifying instructions doesn't help either. Are you guys passing all images to a VLM with conversion to MD table as a instruction? JSON return type doesn't work now either.
yindo commented 2026-02-16 00:17:03 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Jul 9, 2024):

We currently don't support this very well because understanding blocks of color in a PDF is a difficult problem. You should try the gpt4o mode as it may give you a more accurate result.

@BinaryBrain commented on GitHub (Jul 9, 2024): We currently don't support this very well because understanding blocks of color in a PDF is a difficult problem. You should try the gpt4o mode as it may give you a more accurate result.
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 complex layout figure
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#175
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?