Since roughly today, using the new model (non-legacy), we consistently get the following response for async vertex OCR tasks (DOCUMENT_TEXT_DETECTION) when processing PDFs with >5 pages:
{"error":{"code":3,"message":"Internal server error. Failed to process features."},"fullTextAnnotation":{},"context":{"uri":"scrubbed","pageNumber":6}}
We managed to get around this by switching to the old (legacy) model temporarily using the model: 'builtin/legacy' parameter, with the legacy model, everything works as expected.
We're using eu-vision.googleapis.com and making IBatchAnnotateFilesRequest using the JS SDK.
As there is no status for the Vision AI OCR service offering and the problem has been persisting for a couple of hours now, we are wondering whether this is just us or it is a known issue.
If you're experiencing consistent internal server errors when using the new Vertex AI OCR model for processing PDFs with more than 5 pages, and switching to the legacy model resolves the issue, it's possible that there might be a problem with the new model's handling of large PDF documents.
Internal server errors can sometimes occur due to temporary issues on the server side or with the service itself. While you've already taken appropriate action by switching to the legacy model as a temporary workaround, it's advisable to report this issue to Google Cloud Support.
Google Cloud Support can provide more insights into whether this is a known issue, whether it's specific to your project, or if it's a widespread problem affecting other users as well. Additionally, they can offer guidance on potential fixes or workarounds, and they can escalate the issue to the appropriate engineering teams if necessary.
You can submit a support ticket through the Google Cloud Console or contact Google Cloud Support through other channels available to your support plan. This ensures that your concerns are properly addressed by the Google Cloud team.
I might be a bit paranoid, but this sounds like a LLM-generated answer to my question, and doesn't really help.
Google Cloud Support is not available to us as we do not have a paid support plan, and there is no public service status available for this offering.
User | Count |
---|---|
2 | |
1 | |
1 | |
1 | |
1 |