Repeated "Internal Error" in Vertex AI Batch Prediction - Seeking Assistance

[jlrw_cama]

I recently trained a model with AutoML in Vertex AI to predict future ticket sales on the basis of past data for our classical music non-profit organization. I am attempting to perform batch predictions for a future concert as a first test of the model.

Each time I run the batch prediction, I receive the same error, copied here:

>>

Hello Vertex AI Customer,

Due to an error, Vertex AI was unable to batch predict using model "CAMA 
Ticket Sales Batch Prediction".

Additional Details:
Operation State: Failed with errors

Resource Name: [redacted]

Error Messages: Internal error occurred. Please retry in a few minutes. If 
you still experience errors, contact Vertex AI.

To view the error on Cloud Console, go back to your predictions using [redacted].

Sincerely,
The Google Cloud AI Team

<<

I have tried back and rerun the batch prediction at different times of day and in each case the same error occurs.

Has anyone encountered a similar problem who might have a solution?

Thank you!

[ruthseki]

Hi @jlrw_cama,

Welcome to Google Cloud Community!

According to this documentation, here’s an approach that you may try to troubleshoot this:

Run the following curl command to create an empty Vertex AI dataset. Ensure that you configure your project ID in the command.

PROJECT_ID=PROJECT_ID

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://europe-west4-aiplatform.googleapis.com/ui/projects/$PROJECT_ID/locations/europe-west4/datasets \
-d '{
    "display_name": "test-name1",
    "metadata_schema_uri": "gs://google-cloud-aiplatform/schema/dataset/metadata/image_1.0.0.yaml",
    "saved_queries": [{"display_name": "saved_query_name", "problem_type": "IMAGE_CLASSIFICATION_MULTI_LABEL"}]
}'​

After the command completes, wait five minutes and try model tuning again.

---

If the issue persists, I recommend contacting Google Cloud Support. They 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.

Also, I suggest filing a defect report. This way you could have visibility on the progress of your request as it is publicly available. Please note that I can't provide any details or timelines at this moment. For future updates, I suggest keeping an eye out on the issue tracker.

Was this helpful? If so, please accept this answer as “Solution”. If you need additional assistance, reply here within 2 business days and I’ll be happy to help.