You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The server had an error processing your request. Sorry about that! You can retry your request, or contact us through an Azure support request at: https://go.microsoft.com/fwlink/?linkid=2213926 if you keep seeing this error. (Please include the request ID 0e2f2ad5-23ca-4fc8-8001-f5aadfe940a8 in your email.). Azure.AI.OpenAI: HTTP 500 (server_error: )
Project:
C# Assistant using Microsoft.SemanticKernel Version="1.31.0" with a few plugins where I'm attempting to return a plain text string response along with a JSON payload. The plugin is reached, processes, and responds, then semantic kernel crashes after the plugin is completed. The prompt output from the plugin is:
Generate a single variation of the given utterance. Do not include any explanations or newline (\\n) characters.
+++++++++
Got it. Updating bedrooms to 3. Is there anything else to update?
+++++++++
If you see a response that contains JSON don't modify it. Example JSON: {"customerProfile": {"key": "value"}}.
Also give the following suggestions as is, do not modify anything: {"CustomerProfile":{"RealEstate":{"PlanPreference":{"Bedrooms":3}}}}
The text was updated successfully, but these errors were encountered:
Thank you. I am here because I asked this question in the Azure Community and was redirected here. I asked the question in the Azure Community because I don't have access to support cases. I'm merely trying to help you improve your software, so if this isn't helpful feel free to close the issue.
From https://learn.microsoft.com/en-us/answers/questions/2127585/microsoft-semantickernel-connectors-openai-http-50:
I read https://devblogs.microsoft.com/semantic-kernel/using-json-schema-for-structured-output-in-net-for-openai-models/, tried using OpenAIPromptExecutionSettings.ResponseFormat, including the #pragma warning disable SKEXP0010 overrides, and can consistently cause an HTTP 500 calling OpenAI. The following request IDs can be used to trace, and I can send the complete offending code including all prompts and plugins if anyone is interested.
request ID b5924025-f244-4769-902e-0ffb50510db4
request ID e2ba223e-a7c6-4178-a297-7a51af71305e
request ID 0e2f2ad5-23ca-4fc8-8001-f5aadfe940a8
Error:
Microsoft.SemanticKernel.Connectors.OpenAI: HTTP 500 (server_error: )
The server had an error processing your request. Sorry about that! You can retry your request, or contact us through an Azure support request at: https://go.microsoft.com/fwlink/?linkid=2213926 if you keep seeing this error. (Please include the request ID 0e2f2ad5-23ca-4fc8-8001-f5aadfe940a8 in your email.). Azure.AI.OpenAI: HTTP 500 (server_error: )
Project:
C# Assistant using Microsoft.SemanticKernel Version="1.31.0" with a few plugins where I'm attempting to return a plain text string response along with a JSON payload. The plugin is reached, processes, and responds, then semantic kernel crashes after the plugin is completed. The prompt output from the plugin is:
The text was updated successfully, but these errors were encountered: