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

PDF too large error #1

New Issue
Closed
opened 2026-02-16 00:16:34 -05:00 by yindo · 7 comments
yindo commented 2026-02-16 00:16:34 -05:00
Owner
Copy Link
Copy Source

Originally created by @barun-saha on GitHub (Feb 21, 2024).

Hello,

Thanks for making LlamaParse (and LlamaIndex, of course)!

I tried out parsing the content of a relatively small PDF file (~200 pages) using LlamaParse . In the extracted text file, the visual layout of the tables from the PDF file looked great!

Next, I tried doing the same with a relatively large PDF file (~800 pages; ~18 MB). However, I got the following error:

Started parsing the file under job_id 77ecd2da-c950-488d-8d86-821c0425602f
Error while parsing the PDF file:  Failed to parse the PDF file: Job failed: PDF_TOO_LARGE

Is there a way to work with large (much larger) PDF files?

Thanks.

Originally created by @barun-saha on GitHub (Feb 21, 2024). Hello, Thanks for making LlamaParse (and LlamaIndex, of course)! I tried out parsing the content of a relatively small PDF file (~200 pages) using LlamaParse . In the extracted text file, the visual layout of the tables from the PDF file looked great! Next, I tried doing the same with a relatively large PDF file (~800 pages; ~18 MB). However, I got the following error: ``` Started parsing the file under job_id 77ecd2da-c950-488d-8d86-821c0425602f Error while parsing the PDF file: Failed to parse the PDF file: Job failed: PDF_TOO_LARGE ``` Is there a way to work with large (much larger) PDF files? Thanks.
yindo closed this issue 2026-02-16 00:16:34 -05:00
yindo commented 2026-02-16 00:16:34 -05:00
Author
Owner
Copy Link
Copy Source

@anoopshrma commented on GitHub (Feb 21, 2024):

I think there is a limit of 1000 pages for a single pdf file for parsing.

Not sure if the limit has been changed or its due to something else.

@anoopshrma commented on GitHub (Feb 21, 2024): I think there is a limit of 1000 pages for a single pdf file for parsing. Not sure if the limit has been changed or its due to something else.
yindo commented 2026-02-16 00:16:34 -05:00
Author
Owner
Copy Link
Copy Source

@logan-markewich commented on GitHub (Feb 21, 2024):

Yea there's currently a page limit and also a file size limit.

We are working to ensure larger file sizes work for a future release. But for now, you may have to use some PDF utilities to split the PDF in to smaller chunks.

@logan-markewich commented on GitHub (Feb 21, 2024): Yea there's currently a page limit and also a file size limit. We are working to ensure larger file sizes work for a future release. But for now, you may have to use some PDF utilities to split the PDF in to smaller chunks.
yindo commented 2026-02-16 00:16:35 -05:00
Author
Owner
Copy Link
Copy Source

@barun-saha commented on GitHub (Feb 21, 2024):

Yea there's currently a page limit and also a file size limit.

We are working to ensure larger file sizes work for a future release. But for now, you may have to use some PDF utilities to split the PDF in to smaller chunks.

Thanks for the response. Indeed, this became evident later after I looked at the document returned:

[Document(id_='bb38db2a-7b6d-4172-b46a-d60d55f86bf7', embedding=None, metadata={'file_path': '/content/file.pdf'}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='PDF_TOO_LARGE, max pages supported: 250', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n')]

Any better way to catch the error or know the limits?

@barun-saha commented on GitHub (Feb 21, 2024): > Yea there's currently a page limit and also a file size limit. > > We are working to ensure larger file sizes work for a future release. But for now, you may have to use some PDF utilities to split the PDF in to smaller chunks. Thanks for the response. Indeed, this became evident later after I looked at the document returned: ``` [Document(id_='bb38db2a-7b6d-4172-b46a-d60d55f86bf7', embedding=None, metadata={'file_path': '/content/file.pdf'}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='PDF_TOO_LARGE, max pages supported: 250', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n')] ``` Any better way to catch the error or know the limits?
yindo commented 2026-02-16 00:16:35 -05:00
Author
Owner
Copy Link
Copy Source

@logan-markewich commented on GitHub (Feb 22, 2024):

Ah yea, The size is limited to 250 pages. We are working on a fix for not adding that message as a document!

cc @hexapode

@logan-markewich commented on GitHub (Feb 22, 2024): Ah yea, The size is limited to 250 pages. We are working on a fix for not adding that message as a document! cc @hexapode
yindo commented 2026-02-16 00:16:35 -05:00
Author
Owner
Copy Link
Copy Source

@rawwerks commented on GitHub (Feb 23, 2024):

would be great if there were a way to have llama parse split the pdf (if desired) into <250 page files. (especially important for books.)

@rawwerks commented on GitHub (Feb 23, 2024): would be great if there were a way to have llama parse split the pdf (if desired) into <250 page files. (especially important for books.)
yindo commented 2026-02-16 00:16:35 -05:00
Author
Owner
Copy Link
Copy Source

@anoopshrma commented on GitHub (Feb 23, 2024):

This is a great idea @rawwerks!
Something's are already in the works for tackling long PDFs

@anoopshrma commented on GitHub (Feb 23, 2024): This is a great idea @rawwerks! Something's are already in the works for tackling long PDFs
yindo commented 2026-02-16 00:16:35 -05:00
Author
Owner
Copy Link
Copy Source

@mattflo commented on GitHub (Mar 1, 2024):

I also ran into this on the first pdf of mine that I tried. For reference, it is 471 pages and 34.4 MB. Awesome product/service! Can't wait to see what can be built with LlamaParse!

@mattflo commented on GitHub (Mar 1, 2024): I also ran into this on the first pdf of mine that I tried. For reference, it is 471 pages and 34.4 MB. Awesome product/service! Can't wait to see what can be built with LlamaParse!
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#1
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?