Hello, did you review the CORS settings in your storage account? Maybe the data is not public and should be.
Another possible Issue is a temporary service problem.
Regards,
Miguel.
This browser is no longer supported.
Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.
Hi MSFT team,
I was using chat playground in azure openai studio. I add the data source using files (only 2 small HTML files with less than 100kb) saved in a blob storage container. I have all the open ai and ai search resources set up correctly. But i saw the error message saying "We couldn't connect your data. An unexpected error occurred while processing your data. Please try again." Previously, i could be able to set up the data source using the same approach without any issue. Now i cannot do it using the same approach and i was wondering if there is anything wrong in the indexing process?
PS. I saw someone reports similar issue in ticket: https://video2.skills-academy.com/en-gb/answers/questions/1690860/we-couldnt-connect-your-data-error-in-azure-openai . Did you change some of your data indexing process so it impact a wide range of users?
Thanks.
Hello, did you review the CORS settings in your storage account? Maybe the data is not public and should be.
Another possible Issue is a temporary service problem.
Regards,
Miguel.
Thanks for reaching out to us and reporting this issue, I see several threads reporting this issue, to help you out of this issue soon -
I hope this helps!
Regards,
Yutong
Hi, the issue has been resolved, I believe it's the Microsoft backend issue.
Update:
The indexing process still has the error that the vector search fields cannot be automatically correctly created when using the azure openai chat playground portal (data source: azure blob storage). Saw the following error and multiple people reports the same issue:
An error occurred when calling Azure Cognitive Search: Azure Search: Please assign a proper column/field for vector search. It should be of type Collection(Edm.Single)
Update: issue solved.