run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-26 16:56:36 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Llamaparse sometimes translates non-English text to English in Markdown output #235

New Issue
Open
opened 2026-02-16 00:17:13 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:13 -05:00
Owner
Copy Link
Copy Source

Originally created by @ilyav123 on GitHub (Aug 19, 2024).

Describe the bug
I am parsing Russian PDF documents and sometimes Llamaparse starts to translate the text to English in Markdown. I.e. the full document and all its pages are in Russian, but in the MD output 1 or 2 pages appear as a translation of the content to English. It happens not very often, like 1 page out of 100.

Example job ID: 655c1bde-2a4b-4b3d-8699-58135e35391b, page starting with md output "md": "# Additional Information on Oil and Gas Exploration" (it's page 57 of the original document but parsing was from page 7 (target_pages_list=7,8...))

Client:

  • Python Library

Options
parser = LlamaParse(parsing_instruction="Ты обязательно должен вернуть ВСЮ информацию и ВЕСЬ текст, содержащийся в документе. Таблицы должны быть возвращены в виде таблиц.",invalidate_cache=False,do_not_cache=False,verbose=True, language=Language.RUSSIAN,target_pages=comma_separated_pages,result_type=ResultType.JSON)
parser.get_json_result(filename)

Originally created by @ilyav123 on GitHub (Aug 19, 2024). **Describe the bug** I am parsing Russian PDF documents and sometimes Llamaparse starts to translate the text to English in Markdown. I.e. the full document and all its pages are in Russian, but in the MD output 1 or 2 pages appear as a translation of the content to English. It happens not very often, like 1 page out of 100. Example job ID: 655c1bde-2a4b-4b3d-8699-58135e35391b, page starting with md output "md": "# Additional Information on Oil and Gas Exploration" (it's page 57 of the original document but parsing was from page 7 (target_pages_list=7,8...)) **Client:** - Python Library **Options** parser = LlamaParse(parsing_instruction="Ты обязательно должен вернуть ВСЮ информацию и ВЕСЬ текст, содержащийся в документе. Таблицы должны быть возвращены в виде таблиц.",invalidate_cache=False,do_not_cache=False,verbose=True, language=Language.RUSSIAN,target_pages=comma_separated_pages,result_type=ResultType.JSON) parser.get_json_result(filename)
yindo added the bug label 2026-02-16 00:17:13 -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 bug
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#235
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?