PDF file parse failure #465

Open
opened 2026-02-16 00:17:55 -05:00 by yindo · 1 comment
Owner

Originally created by @skyblueutd on GitHub (May 2, 2025).

Describe the bug
I have tried this for 3 time, same 3 PDF files got parse errors:
"Error while parsing the file '<bytes/buffer>':
Loading files: 80%|██████████████████████████████████████████████▏ | 224/281 [1:49:05<18:35, 19.57s/file]Started parsing the file under job_id 66496d49-8ede-412f-9178-16264fa2baa7
Error while parsing the file '<bytes/buffer>':"

Files
attached

Job ID
09674647-ff11-4295-8403-d0b5af852dac | Solution-Brief_ProphetStor_p1-10.pdf
a0d216e0-6c44-4892-8eb1-ca0b27780bdb | white_paper_Supermicro_SBB_Xinnor_xiRAID.pdf
0b37c8f0-fe5d-4ff7-a21d-dab28f16b413 | white_paper_Immersion-Cooling.pdf

Client:
Please remove untested options:

  • Python Library
  • API

Additional context

Solution-Brief_ProphetStor_p1-10.pdf

white_paper_Supermicro_SBB_Xinnor_xiRAID.pdf

white_paper_Immersion-Cooling.pdf

Add any additional context about the problem here.

parsing_instruction = """Do not parse images and it's captions."""
llama_parser = LlamaParse(
api_key=llama_parse_api_key, num_workers=8, result_type="markdown", verbose=True, parsing_instruction=parsing_instruction

)
Originally created by @skyblueutd on GitHub (May 2, 2025). **Describe the bug** I have tried this for 3 time, same 3 PDF files got parse errors: "Error while parsing the file '<bytes/buffer>': Loading files: 80%|██████████████████████████████████████████████▏ | 224/281 [1:49:05<18:35, 19.57s/file]Started parsing the file under job_id 66496d49-8ede-412f-9178-16264fa2baa7 Error while parsing the file '<bytes/buffer>':" **Files** attached **Job ID** 09674647-ff11-4295-8403-d0b5af852dac | Solution-Brief_ProphetStor_p1-10.pdf a0d216e0-6c44-4892-8eb1-ca0b27780bdb | white_paper_Supermicro_SBB_Xinnor_xiRAID.pdf 0b37c8f0-fe5d-4ff7-a21d-dab28f16b413 | white_paper_Immersion-Cooling.pdf **Client:** Please remove untested options: - Python Library - API **Additional context** [Solution-Brief_ProphetStor_p1-10.pdf](https://github.com/user-attachments/files/20018428/Solution-Brief_ProphetStor_p1-10.pdf) [white_paper_Supermicro_SBB_Xinnor_xiRAID.pdf](https://github.com/user-attachments/files/20018430/white_paper_Supermicro_SBB_Xinnor_xiRAID.pdf) [white_paper_Immersion-Cooling.pdf](https://github.com/user-attachments/files/20018432/white_paper_Immersion-Cooling.pdf) Add any additional context about the problem here. parsing_instruction = """Do not parse images and it's captions.""" llama_parser = LlamaParse( api_key=llama_parse_api_key, num_workers=8, result_type="markdown", verbose=True, parsing_instruction=parsing_instruction )
yindo added the bug label 2026-02-16 00:17:55 -05:00
Author
Owner

@skyblueutd commented on GitHub (May 3, 2025):

error like this:
Job logs
Job Errors
DOCUMENT_PIPELINE_ERROR : MARKDOWN_EXTRACTION_FAILED
Page Errors and Warning details
Page 1 [error] - RECONSTRUCTION_ERROR : Something went wrong when reconstruction page 1

@skyblueutd commented on GitHub (May 3, 2025): error like this: Job logs Job Errors DOCUMENT_PIPELINE_ERROR : MARKDOWN_EXTRACTION_FAILED Page Errors and Warning details Page 1 [error] - RECONSTRUCTION_ERROR : Something went wrong when reconstruction page 1
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#465