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

[ilyav123]

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)