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

Issue with PDF page boundaries #144

New Issue
Closed
opened 2026-02-16 00:16:59 -05:00 by yindo · 8 comments
yindo commented 2026-02-16 00:16:59 -05:00
Owner
Copy Link
Copy Source

Originally created by @krzischp on GitHub (Jun 9, 2024).

Context

Hi, I'm parsing a PDF using version 0.4.4 of llama-parse and using gpt-4o:

max_timeout = 6000
num_workers = 4
check_interval = 10

parser = LlamaParse(
    result_type="markdown",
    verbose=True,
    language="pt",
    num_workers=num_workers,
    gpt4o_mode=gpt4o_mode,
    gpt4o_api_key=os.getenv('OPENAI_API_KEY'),
    max_timeout=max_timeout,
    check_interval=check_interval
)

I cannot share the PDF as it contains confidential information. It is a financial contract of 45 pages in Portuguese.

I implemented a utility function to consider the default delimiter "\n---\n" to separate the llama-parse parsed resulting document in pages.

Issue

The resulting splits doesn't match the right pages.

I don't know how you delimit the pdf pages in llamaparse functions, but it seems like a block of text in a smaller square (a stamp at the end of each page of the contract in my case) is identified as a single page.

So for example, a pdf page with this stamp at the end will be split in 2 pages instead of one.

Originally created by @krzischp on GitHub (Jun 9, 2024). ### Context Hi, I'm parsing a PDF using version 0.4.4 of llama-parse and using gpt-4o: ```python max_timeout = 6000 num_workers = 4 check_interval = 10 parser = LlamaParse( result_type="markdown", verbose=True, language="pt", num_workers=num_workers, gpt4o_mode=gpt4o_mode, gpt4o_api_key=os.getenv('OPENAI_API_KEY'), max_timeout=max_timeout, check_interval=check_interval ) ``` I cannot share the PDF as it contains confidential information. It is a financial contract of 45 pages in Portuguese. I implemented a utility function to consider the default delimiter "\n---\n" to separate the llama-parse parsed resulting document in pages. ### Issue The resulting splits doesn't match the right pages. I don't know how you delimit the pdf pages in llamaparse functions, but it seems like a block of text in a smaller square (a stamp at the end of each page of the contract in my case) is identified as a single page. So for example, a pdf page with this stamp at the end will be split in 2 pages instead of one.
yindo closed this issue 2026-02-16 00:16:59 -05:00
yindo commented 2026-02-16 00:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@hexapode commented on GitHub (Jun 10, 2024):

Hi!

  • It may be a bug on our part :(
  • It may be that the stamp are in actual separate page in the PDF.
  • It may be that the delimiter \n---\n is actually return by the parser (therefor accidentally creating an new page). For this one you may want to set the page_separator attribute to an new value, unlikely to appear in the PDF.
@hexapode commented on GitHub (Jun 10, 2024): Hi! - It may be a bug on our part :( - It may be that the stamp are in actual separate page in the PDF. - It may be that the delimiter \n---\n is actually return by the parser (therefor accidentally creating an new page). For this one you may want to set the page_separator attribute to an new value, unlikely to appear in the PDF.
yindo commented 2026-02-16 00:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@krzischp commented on GitHub (Jun 15, 2024):

Hi @hexapode, thanks for your answer!

It may be that the stamp are in actual separate page in the PDF.

So the stamp is on the same page.

It may be that the delimiter \n---\n is actually return by the parser (therefor accidentally creating an new page). For this one you may want to set the page_separator attribute to an new value, unlikely to appear in the PDF

After installing the main branch version of llamaparse, I tried with another delimiter and split_by_page True (and with gpt4-o), but parsed result pages still doesn't match the right pdf pages. For example, this time, the 2nd, 3rd, 4th pdf pages all are in the 2nd parsed page result (documents[1])...

It may be a bug on our part

And do you need me to do some tests, troubleshooting on my side and send you the results?

@krzischp commented on GitHub (Jun 15, 2024): Hi @hexapode, thanks for your answer! > It may be that the stamp are in actual separate page in the PDF. So the stamp is on the same page. > It may be that the delimiter \n---\n is actually return by the parser (therefor accidentally creating an new page). For this one you may want to set the page_separator attribute to an new value, unlikely to appear in the PDF After installing the main branch version of llamaparse, I tried with another delimiter and `split_by_page` True (and with gpt4-o), but parsed result pages still doesn't match the right pdf pages. For example, this time, the 2nd, 3rd, 4th pdf pages all are in the 2nd parsed page result (`documents[1]`)... > It may be a bug on our part And do you need me to do some tests, troubleshooting on my side and send you the results?
yindo commented 2026-02-16 00:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@krzischp commented on GitHub (Jun 15, 2024):

When using llama-index PDFReader, for example, the pages match correctly, but the quality is lower obviously.

@krzischp commented on GitHub (Jun 15, 2024): When using llama-index `PDFReader`, for example, the pages match correctly, but the quality is lower obviously.
yindo commented 2026-02-16 00:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@hexapode commented on GitHub (Jun 18, 2024):

Hi!

Ideally could you share a similar document creating the same issue?

Alternatively, I will have a look at how the logic of split_by_page is implemented

@hexapode commented on GitHub (Jun 18, 2024): Hi! Ideally could you share a similar document creating the same issue? Alternatively, I will have a look at how the logic of split_by_page is implemented
yindo commented 2026-02-16 00:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@krzischp commented on GitHub (Jun 18, 2024):

Ideally could you share a similar document creating the same issue?

All these documents are confidential unfortunately...

Alternatively, I will have a look at how the logic of split_by_page is implemented

Thanks!

@krzischp commented on GitHub (Jun 18, 2024): > Ideally could you share a similar document creating the same issue? All these documents are confidential unfortunately... > Alternatively, I will have a look at how the logic of split_by_page is implemented Thanks!
yindo commented 2026-02-16 00:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@krzischp commented on GitHub (Jun 23, 2024):

Hi @hexapode, this contract example if public:
https://www.bndes.gov.br/arquivos/contratos-exportacao/2013.0237.pdf

and it seems it also parsed into more pages than the actual document, when using gpt-4o.
It parsed into 48 pages when the document is actually 41 pages.

But when using llamaparse without gpt-4o (in text or markdown mode), it parses into the 41 pages correctly. So it might be an issue related to a gpt-4o post-processing step of the llama parser.

@krzischp commented on GitHub (Jun 23, 2024): Hi @hexapode, this contract example if public: https://www.bndes.gov.br/arquivos/contratos-exportacao/2013.0237.pdf and it seems it also parsed into more pages than the actual document, when using gpt-4o. It parsed into 48 pages when the document is actually 41 pages. But when using llamaparse without gpt-4o (in text or markdown mode), it parses into the 41 pages correctly. So it might be an issue related to a gpt-4o post-processing step of the llama parser.
yindo commented 2026-02-16 00:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@krzischp commented on GitHub (Jul 2, 2024):

HI @hexapode, do you have any update? I observed the issue is with or witout gpt-4o actually. It really seems that noises like stamp, signature, etc on a contract pdf can confuse the parser with the page number.

@krzischp commented on GitHub (Jul 2, 2024): HI @hexapode, do you have any update? I observed the issue is with or witout gpt-4o actually. It really seems that noises like stamp, signature, etc on a contract pdf can confuse the parser with the page number.
yindo commented 2026-02-16 00:16:59 -05:00
Author
Owner
Copy Link
Copy Source

@hexapode commented on GitHub (Jul 8, 2024):

Hi! By using the API, both in GPT4o and normal mode, I always found 41 pages with the given document. Could you try with result_type="json" and repport the number of page returned?

@hexapode commented on GitHub (Jul 8, 2024): Hi! By using the API, both in GPT4o and normal mode, I always found 41 pages with the given document. Could you try with result_type="json" and repport the number of page returned?
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#144
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?