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

LlamaParse closes connection unexpectedly #407

New Issue
Open
opened 2026-02-16 00:17:45 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:45 -05:00
Owner
Copy Link
Copy Source

Originally created by @majdalsado on GitHub (Jan 16, 2025).

Describe the bug
We've noticed that LlamaParse can occassionally return an error unable to perform operation on <TCPTransport closed=True reading=False 0x7f57480c0a40>; the handler is closed
and fail when trying to use it to parse a pdf file via the python library.

It seems to happen immediately when we make a request but goes away if we retry at least once so it feels like a network connectivity issue.

Anecdotally I've noticed it happens more often on larger files rather than smaller ones.

Files
Random files, no pattern or specific trigger.

Job ID
When this bug happens no Job ID gets created, the error seems to happen before it does so.

Client:

  • Python Library

Additional context
I call LlamaParse via LlamaParse.load_data(file_bytes). I'm not sure if the passing of file_bytes has something to do with it.

Here are logs of it happening whereby my function retries and it then goes through.
Image
Job ID of the job succeeding it: a387462e-9c4a-467e-8330-c80a76c7f6cc

App that we're running is a Python FastAPI running on Railway with Uvicorn v0.34 (latest).

Originally created by @majdalsado on GitHub (Jan 16, 2025). **Describe the bug** We've noticed that LlamaParse can occassionally return an error `unable to perform operation on <TCPTransport closed=True reading=False 0x7f57480c0a40>; the handler is closed` and fail when trying to use it to parse a pdf file via the python library. It seems to happen immediately when we make a request but goes away if we retry at least once so it feels like a network connectivity issue. Anecdotally I've noticed it happens more often on larger files rather than smaller ones. **Files** Random files, no pattern or specific trigger. **Job ID** When this bug happens no Job ID gets created, the error seems to happen before it does so. **Client:** - Python Library **Additional context** I call LlamaParse via LlamaParse.load_data(file_bytes). I'm not sure if the passing of file_bytes has something to do with it. Here are logs of it happening whereby my function retries and it then goes through. <img width="834" alt="Image" src="https://github.com/user-attachments/assets/eff27478-f0f5-46e8-9bf9-ed4a8f7c310d" /> Job ID of the job succeeding it: a387462e-9c4a-467e-8330-c80a76c7f6cc App that we're running is a Python FastAPI running on Railway with Uvicorn v0.34 (latest).
yindo added the bug label 2026-02-16 00:17:45 -05:00
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 bug
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#407
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?