run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 19:30:01 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Differences in text and markdown output for pdf. Markdown is missing some text on page boundaries #174

New Issue
Open
opened 2026-02-16 00:17:03 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:03 -05:00
Owner
Copy Link
Copy Source

Originally created by @nickcaine on GitHub (Jul 3, 2024).

DORA_Full_Llamaparse2.md
DORA_Full_Llamaparse2.txt
input_orig_DORA Regulations CELEX_32022R2554_EN_TXT-Copy.pdf

Bugs

Enclosed are three files

  • a pdf copy of public european DORA regulations.
  • the llamaparse text output - correct (as far as i can tell)
  • the llamaparse markdown output - some missing text, some added text - do a compare of the two files in VSCode
    • the missing text - example - article 5 text in md file ends with section 2.g missing sections 2.h, 2.i and 3 and 4
      - article 13 has the same issue as does article 18 - subnumbering has also gone awry (18.2 lost)
    • the added text - example - article 31 header text inserted into middle of article 30

Looking at the missing / inserted text seems to be a bug where a section crosses page boundaries ?
not sure about the subnumbering missing / tagging issues.

Added Features

  • It would be useful to have an option to remove page breaks in md output
  • It would be useful to markup headers and footers as such and also have the option to remove them from the md output
Originally created by @nickcaine on GitHub (Jul 3, 2024). [DORA_Full_Llamaparse2.md](https://github.com/user-attachments/files/16089200/DORA_Full_Llamaparse2.md) [DORA_Full_Llamaparse2.txt](https://github.com/user-attachments/files/16089201/DORA_Full_Llamaparse2.txt) [input_orig_DORA Regulations CELEX_32022R2554_EN_TXT-Copy.pdf](https://github.com/user-attachments/files/16089208/input_orig_DORA.Regulations.CELEX_32022R2554_EN_TXT-Copy.pdf) # Bugs Enclosed are three files - a pdf copy of public european DORA regulations. - the llamaparse text output - correct (as far as i can tell) - the llamaparse markdown output - some missing text, some added text - do a compare of the two files in VSCode - the missing text - example - article 5 text in md file ends with section 2.g missing sections 2.h, 2.i and 3 and 4 - article 13 has the same issue as does article 18 - subnumbering has also gone awry (18.2 lost) - the added text - example - article 31 header text inserted into middle of article 30 Looking at the missing / inserted text seems to be a bug where a section crosses page boundaries ? not sure about the subnumbering missing / tagging issues. # Added Features - It would be useful to have an option to remove page breaks in md output - It would be useful to markup headers and footers as such and also have the option to remove them from the md output
yindo added the enhancement label 2026-02-16 00:17:03 -05:00
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 enhancement
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#174
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?