Error: Invalid request: The request is not valid, HTTP status: 404. Details: The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again.

[microsoft]

Error: Invalid request: The request is not valid, HTTP status: 404. Details: The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again.

[alliscode]

Hi @ekdnam, thank you for creating this issue. Would you please double check if you have the two required models deployed to your AzureOpenAI instance:

• gpt-35-turbo
• text-embedding-ada-002

When setting things up by running the install script, it's important that the Deployment names of the models are used if they are different from the model names:

• IMPORTANT: For AzureOpenAI, if you deployed models gpt-35-turbo and text-embedding-ada-002 with custom names (instead of each own's given name), also use the parameters:

    ```powershell
    -CompletionModel {DEPLOYMENT_NAME} -EmbeddingModel {DEPLOYMENT_NAME} -PlannerModel {DEPLOYMENT_NAME}
    ```
  

[ekdnam]

@alliscode I had forgotten to deploy embeddings to AzureOpenAI. I was able to solve that error. Thanks!
However, I got a new error - please find the trace below

fail: Microsoft.SemanticKernel.IKernel[0]
      Something went wrong while executing the native function. Function: <GetDelegateInfo>b__0. Error: Service error: The service failed to process the request, HTTP status:500
      Microsoft.SemanticKernel.AI.AIException: Service error: The service failed to process the request, HTTP status:500
       ---> Azure.RequestFailedException: Service request failed.
      Status: 500 (Internal Server Error)
      
      Content:
      { "statusCode": 500, "message": "Internal server error", "activityId": "04ac5880-7bfb-4987-96e8-4b18d67a8f36" }
      
      Headers:
      x-ms-client-request-id: 22cdc27b-42dc-434d-b261-d4b990a1c56e
      apim-request-id: REDACTED
      Strict-Transport-Security: REDACTED
      X-Content-Type-Options: REDACTED
      x-ms-region: REDACTED
      Date: Tue, 08 Aug 2023 05:27:42 GMT
      Content-Length: 111
      Content-Type: application/json
      
         at Azure.Core.HttpPipelineExtensions.ProcessMessageAsync(HttpPipeline pipeline, HttpMessage message, RequestContext requestContext, CancellationToken cancellationToken)
         at Azure.AI.OpenAI.OpenAIClient.GetEmbeddingsAsync(String deploymentOrModelName, EmbeddingsOptions embeddingsOptions, CancellationToken cancellationToken)
         at Microsoft.SemanticKernel.Connectors.AI.OpenAI.AzureSdk.ClientBase.RunRequestAsync[T](Func`1 request)
         --- End of inner exception stack trace ---
         at Microsoft.SemanticKernel.Connectors.AI.OpenAI.AzureSdk.ClientBase.RunRequestAsync[T](Func`1 request)
         at Microsoft.SemanticKernel.Connectors.AI.OpenAI.AzureSdk.ClientBase.InternalGetEmbeddingsAsync(IList`1 data, CancellationToken cancellationToken)
         at Microsoft.SemanticKernel.AI.Embeddings.EmbeddingGenerationExtensions.GenerateEmbeddingAsync[TValue,TEmbedding](IEmbeddingGeneration`2 generator, TValue value, CancellationToken cancellationToken)
         at Microsoft.SemanticKernel.Memory.SemanticTextMemory.SearchAsync(String collection, String query, Int32 limit, Double minRelevanceScore, Boolean withEmbeddings, CancellationToken cancellationToken)+MoveNext()
         at Microsoft.SemanticKernel.Memory.SemanticTextMemory.SearchAsync(String collection, String query, Int32 limit, Double minRelevanceScore, Boolean withEmbeddings, CancellationToken cancellationToken)+System.Threading.Tasks.Sources.IValueTaskSource<System.Boolean>.GetResult()
         at SemanticKernel.Service.CopilotChat.Skills.ChatSkills.SemanticChatMemorySkill.QueryMemoriesAsync(String query, String chatId, Int32 tokenLimit, ISemanticTextMemory textMemory) in /Users/ekdnam/Projects/copilot-chat-app/webapi/CopilotChat/Skills/ChatSkills/SemanticChatMemorySkill.cs:line 57
         at SemanticKernel.Service.CopilotChat.Skills.ChatSkills.SemanticChatMemorySkill.QueryMemoriesAsync(String query, String chatId, Int32 tokenLimit, ISemanticTextMemory textMemory) in /Users/ekdnam/Projects/copilot-chat-app/webapi/CopilotChat/Skills/ChatSkills/SemanticChatMemorySkill.cs:line 57
         at SemanticKernel.Service.CopilotChat.Skills.ChatSkills.ChatSkill.GetChatResponseAsync(String chatId, SKContext chatContext) in /Users/ekdnam/Projects/copilot-chat-app/webapi/CopilotChat/Skills/ChatSkills/ChatSkill.cs:line 341
         at SemanticKernel.Service.CopilotChat.Skills.ChatSkills.ChatSkill.ChatAsync(String message, String userId, String userName, String chatId, String messageType, String planJson, String messageId, SKContext context) in /Users/ekdnam/Projects/copilot-chat-app/webapi/CopilotChat/Skills/ChatSkills/ChatSkill.cs:line 267
         at Microsoft.SemanticKernel.SkillDefinition.SKFunction.InvokeAsync(SKContext context, CompleteRequestSettings settings)
fail: Microsoft.SemanticKernel.IKernel[0]
      Function call fail during pipeline step 0: ChatSkill.Chat. Error: Service error: The service failed to process the request, HTTP status:500
Hello, world!

Does this mean I have to use a query vector store? Nothing in-memory?
Or is it something different all together?

[alliscode]

@ekdnam is this error persistent? Generally, 500 level errors are indicating a transient error within the service itself and are considered retriable. If the issue is persistent you might want to configure logging in your Azure OpenAI instance to get more information about what is going wrong.

As for the vector store, the default setup is to use volatile (in memory), but this can be configured in the MemoryStore section of the appsettings.json file within the webapi.

[alliscode]

@ekdnam We've verified that Azure OpenAI experienced intermittent outage yesterday. Can you confirm if you are still experiencing this 500 error?

[ekdnam]

@alliscode thanks for letting me know.

The app is working now.

[ekdnam]

Thanks for your help! I am closing the issue now.