-
Notifications
You must be signed in to change notification settings - Fork 519
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Sometime Documents is staying into queue for permanently #492
Comments
Hi @ravikhunt |
@ryonsteele here is the detail
|
Hi ravikhunt From the detail you posted it seems chunking completed successfully and the file is stuck in enrichment queue/ embedding process. Can you please verify if your enrichment app is up and running? |
It's running only and run all the time, after that i used another file that was processed successfully |
We are also having an issue with csv and xlsx files (the 'products' file in the example Ice Cream data set) getting stuck in embedding process, but it's a max "requeue limit" issue, which I assume can be corrected with a change to the 'max_requeue_count', but we haven't tested that yet. { |
I believe this may be due to chunking of unstructured.io. In the version we have the library doesn't chunk by size, just creates a single chunk, which will crash later steps that can only cope with a chunk of a particular size. We have a ticket on the board to address this as part of the 1.1 release. |
PR #558 was applied to main to address these issues. Pull latest from main and re-run |
resolved and closed due to inactivity |
Sometimes status is not updating and not updating the processing file ahead and stays in queue only
It's not a very big file, its like a 1.40MB file with 1500rows and 5 columns of data
The text was updated successfully, but these errors were encountered: