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

Parser does not recognise superscript or subscript characters #52

New Issue
Open
opened 2026-02-16 00:16:44 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:16:44 -05:00
Owner
Copy Link
Copy Source

Originally created by @Starforged on GitHub (Mar 19, 2024).

When the PDF contains superscript or subscript numbers this is not reflected in the output.

Example Input:
grafik

Recieved Output:
Konzentrationen der Ag+- und

Raw (copy and paste from PDF) Text:
Konzentrationen der Ag+- und

As you can see the recieved Output is identical with the raw text from the PDF.
This behaviour should be replaced so that the formatting is preserved.

Option 1 with uncode character Superscript Plus Sign:
Konzentrationen der Ag⁺- und

Option 2 with markdown tags:
Konzentrationen der Ag+- und

My recommendation is to go with Option 3 as outlined here:

Option 3 with LaTeX, this example uses $ delimiters to show formatted text inline:
Konzentrationen der $Ag^+$- und

Please note that this is a seperate issue to #81 as that one requires OCR, while this issue should not require it as the superscript and subscript text position is encoded in the formatting of the PDF document.

Here are the files for reproducing the issue:
chemiebuch_124.pdf
chemiebuch_124_llamaparse.md

Originally created by @Starforged on GitHub (Mar 19, 2024). When the PDF contains superscript or subscript numbers this is not reflected in the output. Example Input: ![grafik](https://github.com/run-llama/llama_parse/assets/11255685/b91de4c6-22e8-467f-87e6-c15fa7ddc3e4) Recieved Output: Konzentrationen der Ag+- und Raw (copy and paste from PDF) Text: Konzentrationen der Ag+- und As you can see the recieved Output is identical with the raw text from the PDF. This behaviour should be replaced so that the formatting is preserved. Option 1 with uncode character Superscript Plus Sign: Konzentrationen der Ag⁺- und Option 2 with markdown tags: Konzentrationen der Ag<sup>+</sup>- und My recommendation is to go with Option 3 as outlined here: Option 3 with LaTeX, this example uses `$` delimiters to show formatted text inline: Konzentrationen der $Ag^+$- und Please note that this is a seperate issue to #81 as that one requires OCR, while this issue should not require it as the superscript and subscript text position is encoded in the formatting of the PDF document. Here are the files for reproducing the issue: [chemiebuch_124.pdf](https://github.com/run-llama/llama_parse/files/14647739/chemiebuch_124.pdf) [chemiebuch_124_llamaparse.md](https://github.com/run-llama/llama_parse/files/14648021/chemiebuch_124_llamaparse.md)
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#52
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?