allenai
I am receiving WARNING - Attempt *: All connection attempts failed
(olmocr) jupyter@v:~/Test/olmocr$ python -m olmocr.pipeline ./localworkspace --pdfs /home/jupyter/Test/olmocr/tests/mypdfs/test_page_08_1224001.pdf
INFO:olmocr.check:pdftoppm is installed and working.
2025-03-04 05:36:48,006 - __main__ - INFO - Got --pdfs argument, going to add to the work queue
2025-03-04 05:36:48,007 - __main__ - INFO - Loading file at /home/jupyter/Test/olmocr/tests/mypdfs/test_page_08_1224001.pdf as PDF document
2025-03-04 05:36:48,008 - __main__ - INFO - Found 1 total pdf paths to add
Sampling PDFs to calculate optimal length: 100%|██████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 149.50it/s]
2025-03-04 05:36:48,016 - __main__ - INFO - Calculated items_per_group: 500 based on average pages per PDF: 1.00
INFO:olmocr.work_queue:Found 1 total paths
INFO:olmocr.work_queue:0 new paths to add to the workspace
2025-03-04 05:36:48,280 - __main__ - INFO - Starting pipeline with PID 536
2025-03-04 05:36:48,280 - __main__ - INFO - Downloading model 'allenai/olmOCR-7B-0225-preview'
Fetching 15 files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 20295.02it/s]
2025-03-04 05:36:48,543 - __main__ - INFO - Model download complete 'allenai/olmOCR-7B-0225-preview'
INFO:olmocr.work_queue:Initialized local queue with 1 work items
2025-03-04 05:36:48,596 - __main__ - WARNING - Attempt 1: All connection attempts failed
2025-03-04 05:36:49,609 - __main__ - WARNING - Attempt 2: All connection attempts failed
2025-03-04 05:36:50,621 - __main__ - WARNING - Attempt 3: All connection attempts failed
2025-03-04 05:36:51,633 - __main__ - WARNING - Attempt 4: All connection attempts failed
2025-03-04 05:36:52,647 - __main__ - WARNING - Attempt 5: All connection attempts failed
2025-03-04 05:36:53,659 - __main__ - WARNING - Attempt 6: All connection attempts failed
2025-03-04 05:36:54,695 - __main__ - WARNING - Attempt 7: All connection attempts failed
Why is this happening?
(olmocr) jupyter@v:~/Test/olmocr$ python -m olmocr.pipeline ./localworkspace --pdfs /home/jupyter/Test/olmocr/tests/mypdfs/test_page_08_1224001.pdf INFO:olmocr.check:pdftoppm is installed and working. 2025-03-04 05:36:48,006 - __main__ - INFO - Got --pdfs argument, going to add to the work queue 2025-03-04 05:36:48,007 - __main__ - INFO - Loading file at /home/jupyter/Test/olmocr/tests/mypdfs/test_page_08_1224001.pdf as PDF document 2025-03-04 05:36:48,008 - __main__ - INFO - Found 1 total pdf paths to add Sampling PDFs to calculate optimal length: 100%|██████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 149.50it/s] 2025-03-04 05:36:48,016 - __main__ - INFO - Calculated items_per_group: 500 based on average pages per PDF: 1.00 INFO:olmocr.work_queue:Found 1 total paths INFO:olmocr.work_queue:0 new paths to add to the workspace 2025-03-04 05:36:48,280 - __main__ - INFO - Starting pipeline with PID 536 2025-03-04 05:36:48,280 - __main__ - INFO - Downloading model 'allenai/olmOCR-7B-0225-preview' Fetching 15 files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 20295.02it/s] 2025-03-04 05:36:48,543 - __main__ - INFO - Model download complete 'allenai/olmOCR-7B-0225-preview' INFO:olmocr.work_queue:Initialized local queue with 1 work items 2025-03-04 05:36:48,596 - __main__ - WARNING - Attempt 1: All connection attempts failed 2025-03-04 05:36:49,609 - __main__ - WARNING - Attempt 2: All connection attempts failed 2025-03-04 05:36:50,621 - __main__ - WARNING - Attempt 3: All connection attempts failed 2025-03-04 05:36:51,633 - __main__ - WARNING - Attempt 4: All connection attempts failed 2025-03-04 05:36:52,647 - __main__ - WARNING - Attempt 5: All connection attempts failed 2025-03-04 05:36:53,659 - __main__ - WARNING - Attempt 6: All connection attempts failed 2025-03-04 05:36:54,695 - __main__ - WARNING - Attempt 7: All connection attempts failedWhy is this happening?
Do you solve it?
I got an error after waiting for a few minutes：
2025-03-05 11:00:34,738 - main - WARNING - Attempt 299: All connection attempts failed
2025-03-05 11:00:35,765 - main - WARNING - Attempt 300: All connection attempts failed
2025-03-05 11:00:36,765 - main - INFO - Got cancellation request for SGLang server
Traceback (most recent call last):
File "
Did not receive any update from the team! @jakep-allenai - could you please look into this issue?
You just need to wait a bit longer for sglang to initialize, sometimes it takes 3-4 minutes to startup, depending on your setup.
You just need to wait a bit longer for sglang to initialize, sometimes it takes 3-4 minutes to startup, depending on your setup.
Okay, will let you if it works!! Thanks
You just need to wait a bit longer for sglang to initialize, sometimes it takes 3-4 minutes to startup, depending on your setup.
ProcessLookupError:
ERROR:asyncio:Task exception was never retrieved
future: <Task finished name='Task-2' coro=<sglang_server_host() done, defined at /app/olmocr/olmocr/pipeline.py:614> exception=SystemExit(1)>
Traceback (most recent call last):
File "
Hello, I have a similar issue, but the error message is not exactly the same. Could you please help me with this? Thank you!
You need to wait as long as it took for you to download the 7B model from HuggingFace. Even if the program exits early due to excessive waiting time, at this point, you should observe your OS's download speed to ensure that the model has finished downloading (because huggingface maintains high speed when downloading models, at least that's what I experience.). Run the command line again; good luck!
Of course, you can also download the model from HuggingFace in advance and specify the path using command-line arguments. (I haven't tried it)
--model MODEL List of paths where you can find the model to convert this pdf. You can specify several different paths here, and the script will try to use the one which is fastest to access
I get "sglang server did not become ready after waiting" error after 300 attemts. I run it again after some time, still doesn't work. I tried downloading the model and use --model tag, it doesn't work.
I get "sglang server did not become ready after waiting" error after 300 attemts. I run it again after some time, still doesn't work. I tried downloading the model and use --model tag, it doesn't work.
I found the problem. Somehow I used the wrong version of python when executing. python3 ... instead of just python. And I had olmocr installed in both, but not the sglang.
I think it should be 3.11. But i used pip to install olmocr and sglang, not pip3 and therefore it was installed in python not python3.
Interesting, definitely recommend using a conda environment: https://www.anaconda.com/docs/getting-started/miniconda/main
Pip's dependency solver is not awesome, your system python might have had some other packages installed and that's getting a different final set of packages than what you would get if you installed clean. With a conda environment you would have a clean environment just how we test locally.