run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-07-18 07:44:41 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Server disconnected without sending a response #111

New Issue
Closed
opened 2026-02-16 00:16:54 -05:00 by yindo · 16 comments
yindo commented 2026-02-16 00:16:54 -05:00
Owner
Copy Link
Copy Source

Originally created by @gideononyewuenyi on GitHub (May 10, 2024).

Originally assigned to: @BinaryBrain on GitHub.

why does it take so much time to parse, 30 minutes and still waiting .......

Originally created by @gideononyewuenyi on GitHub (May 10, 2024). Originally assigned to: @BinaryBrain on GitHub. why does it take so much time to parse, 30 minutes and still waiting .......
yindo added the server_issue label 2026-02-16 00:16:54 -05:00
yindo closed this issue 2026-02-16 00:16:54 -05:00
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@rwclayton commented on GitHub (May 10, 2024):

Hey, @gideononyewuenyi - I've been having issues all day. Will you let me know if you get a server error?

@rwclayton commented on GitHub (May 10, 2024): Hey, @gideononyewuenyi - I've been having issues all day. Will you let me know if you get a server error?
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@gideononyewuenyi commented on GitHub (May 10, 2024):

Started parsing the file under job_id 50001bc4-ca6c-4c7b-842b-ef9942ebf5df
Error while parsing the PDF file '/Users/mac/Project-Hillda-AI/Gideon-Onyewuenyi-Resume.pdf': Server disconnected without sending a response.
Failed to load file /Users/mac/Project-Hillda-AI/Gideon-Onyewuenyi-Resume.pdf with error: Server disconnected without sending a response.. Skipping...
[]

@rwclayton

@gideononyewuenyi commented on GitHub (May 10, 2024): Started parsing the file under job_id 50001bc4-ca6c-4c7b-842b-ef9942ebf5df Error while parsing the PDF file '/Users/mac/Project-Hillda-AI/Gideon-Onyewuenyi-Resume.pdf': Server disconnected without sending a response. Failed to load file /Users/mac/Project-Hillda-AI/Gideon-Onyewuenyi-Resume.pdf with error: Server disconnected without sending a response.. Skipping... [] @rwclayton
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@rwclayton commented on GitHub (May 10, 2024):

Have had the same issue all day, @gideononyewuenyi. Must be an issue with the API. Maybe the server is down? Hopefully we'll have answers soon.

@rwclayton commented on GitHub (May 10, 2024): Have had the same issue all day, @gideononyewuenyi. Must be an issue with the API. Maybe the server is down? Hopefully we'll have answers soon.
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@gideononyewuenyi commented on GitHub (May 11, 2024):

I think it works now, thank you.

@gideononyewuenyi commented on GitHub (May 11, 2024): I think it works now, thank you.
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@xyzQ2 commented on GitHub (May 13, 2024):

This is one pdf document (48mb) and running for over 1 hour.
A nice start but too slow.
llparse_1doc

RemoteProtocolError: Server disconnected without sending a response.

@xyzQ2 commented on GitHub (May 13, 2024): This is one pdf document (48mb) and running for over 1 hour. A nice start but too slow. <img width="555" alt="llparse_1doc" src="https://github.com/run-llama/llama_parse/assets/14353482/bafc6123-aeda-44a2-b514-88da248d83b7"> RemoteProtocolError: Server disconnected without sending a response.
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@logan-markewich commented on GitHub (May 14, 2024):

@qboy21 can you share the PDF? Some documents will be slower if they have many images that need to be OCR'd

@logan-markewich commented on GitHub (May 14, 2024): @qboy21 can you share the PDF? Some documents will be slower if they have many images that need to be OCR'd
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@xyzQ2 commented on GitHub (May 19, 2024):

@qboy21 can you share the PDF? Some documents will be slower if they have many images that need to be OCR'd

Hi. Unfortunately, it's proprietary data that I cannot share. I can try with a public file of similar size and then revert back to you.

@xyzQ2 commented on GitHub (May 19, 2024): > @qboy21 can you share the PDF? Some documents will be slower if they have many images that need to be OCR'd Hi. Unfortunately, it's proprietary data that I cannot share. I can try with a public file of similar size and then revert back to you.
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Aug 8, 2024):

Closing this one since we improve quite a lot on this point. If you see any performance issue again, please reopen!

@BinaryBrain commented on GitHub (Aug 8, 2024): Closing this one since we improve quite a lot on this point. If you see any performance issue again, please reopen!
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@NicklasKleemann commented on GitHub (Jan 31, 2025):

@BinaryBrain Still happens in 2025. I have a 340 page document with lots of pictures which needs to be OCR'ed. It finishes on the Llama parse website in about 8/9 minutes, but I get the:

Error while parsing the file <FILE NAME>: Server disconnected without sending a response.

Before it finishes for some reason.
Partially redacted Document for reference that fails for me. https://medicinraadet-dk.b-cdn.net/media/bnyndp0d/bilag-til-medicinradets-anbefaling-vedr-voclosporin-som-tillaegsbehandling-til-lupus-nefritis-vers-1-0-xx.pdf
If I parse it again, it'll correctly get the cached version.

@NicklasKleemann commented on GitHub (Jan 31, 2025): @BinaryBrain Still happens in 2025. I have a 340 page document with lots of pictures which needs to be OCR'ed. It finishes on the Llama parse website in about 8/9 minutes, but I get the: `Error while parsing the file <FILE NAME>: Server disconnected without sending a response.` Before it finishes for some reason. Partially redacted Document for reference that fails for me. https://medicinraadet-dk.b-cdn.net/media/bnyndp0d/bilag-til-medicinradets-anbefaling-vedr-voclosporin-som-tillaegsbehandling-til-lupus-nefritis-vers-1-0-xx.pdf If I parse it again, it'll correctly get the cached version.
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Feb 4, 2025):

Hi @NicklasKleemann,
Are you using the API call, the frontend, the Python lib, or the TS lib?

@BinaryBrain commented on GitHub (Feb 4, 2025): Hi @NicklasKleemann, Are you using the API call, the frontend, the Python lib, or the TS lib?
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@NicklasKleemann commented on GitHub (Feb 5, 2025):

@BinaryBrain I'm using the Python lib in combination within an Azure Function App, although currently everything is ran locally. I'm a bit puzzled as to why it happens, since it works perfectly fine on smaller pdfs.

Specifically this is my parser setup;

    parser = LlamaParse(
        api_key=LLAMA_CLOUD_API_KEY,
        result_type="markdown",
        verbose=True,
        language='da',
        skip_diagonal_text=True,
    )

Where both the get_json_result and aload function's seem to "disconnect" but finishes on the llamacloud website; whereafter i once again can try to parse the same file and instead get the cached version.

@NicklasKleemann commented on GitHub (Feb 5, 2025): @BinaryBrain I'm using the Python lib in combination within an Azure Function App, although currently everything is ran locally. I'm a bit puzzled as to why it happens, since it works perfectly fine on smaller pdfs. Specifically this is my parser setup; ``` parser = LlamaParse( api_key=LLAMA_CLOUD_API_KEY, result_type="markdown", verbose=True, language='da', skip_diagonal_text=True, ) ``` Where both the get_json_result and aload function's seem to "disconnect" but finishes on the llamacloud website; whereafter i once again can try to parse the same file and instead get the cached version.
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@yaswanthnsn-bph commented on GitHub (Feb 20, 2025):

@BinaryBrain

I have been facing the same issue. I'm sending a PDF of 1 page and I'm getting
Error while parsing the file 'tmp5uo8tl3w.pdf': Server disconnected without sending a response. It was working yesterday.

I'm using python api with result_type as structured.

Is this a server issue?

@yaswanthnsn-bph commented on GitHub (Feb 20, 2025): @BinaryBrain I have been facing the same issue. I'm sending a PDF of 1 page and I'm getting Error while parsing the file 'tmp5uo8tl3w.pdf': Server disconnected without sending a response. It was working yesterday. I'm using python api with result_type as structured. Is this a server issue?
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@JohanBekker commented on GitHub (Feb 20, 2025):

Same problem here, I've seen it both in the create_job and _get_job_result methods.

@JohanBekker commented on GitHub (Feb 20, 2025): Same problem here, I've seen it both in the `create_job` and `_get_job_result` methods.
yindo commented 2026-02-16 00:16:54 -05:00
Author
Owner
Copy Link
Copy Source

@SabaAnjum2002 commented on GitHub (Feb 26, 2025):

Same problem, sometimes it is taking 15-20 min to parse a pdf of only 50 pages

@SabaAnjum2002 commented on GitHub (Feb 26, 2025): Same problem, sometimes it is taking 15-20 min to parse a pdf of only 50 pages
yindo commented 2026-02-16 00:16:55 -05:00
Author
Owner
Copy Link
Copy Source

@matheus-rossi commented on GitHub (Mar 13, 2025):

Any updates on this?
I'm still encountering the same error with big PDF files that contain images.

[2025-03-13 14:38:44,599: WARNING/ForkPoolWorker-1] Error while parsing the file '<bytes/buffer>':
[2025-03-13 14:38:44,599: WARNING/ForkPoolWorker-1] Server disconnected without sending a response.
[2025-03-13 14:38:44,599: ERROR/ForkPoolWorker-1] Error extracting text from PDF: No data extracted from PDF.

It seems to be random; the same file sometimes works and sometimes does not.

@matheus-rossi commented on GitHub (Mar 13, 2025): Any updates on this? I'm still encountering the same error with big PDF files that contain images. ``` [2025-03-13 14:38:44,599: WARNING/ForkPoolWorker-1] Error while parsing the file '<bytes/buffer>': [2025-03-13 14:38:44,599: WARNING/ForkPoolWorker-1] Server disconnected without sending a response. [2025-03-13 14:38:44,599: ERROR/ForkPoolWorker-1] Error extracting text from PDF: No data extracted from PDF. ``` It seems to be random; the same file sometimes works and sometimes does not.
yindo commented 2026-02-16 00:16:55 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Jun 27, 2025):

Fixed by #771

@BinaryBrain commented on GitHub (Jun 27, 2025): Fixed by #771
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 server_issue
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#111
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?