updates

Author: alexwolfmsft

articles/ai-services/openai/includes/chatgpt-dotnet.md

@@ -78,7 +78,7 @@ dotnet run program.cs
 ## Output
 
 ```output
-Yes, many of the Azure AI services support customer managed keys. Some examples include Text Analytics, Speech Services, and Translator. However, it's important to note that not all services support customer managed keys, so it's best to check the documentation for each individual service to see if it is supported.
+Assistant : Yes, many other Azure AI services also support customer managed keys, including Azure Cognitive Services, Azure Machine Learning, and Azure Databricks. By using customer managed keys, you can retain complete control over your encryption keys and provide an additional layer of security for your AI assets.
 ```
 
 This will wait until the model has generated its entire response before printing the results. Alternatively, if you want to asynchronously stream the response and print the results, you can replace the contents of *program.cs* with the code in the next example.

articles/ai-services/openai/includes/dall-e-dotnet.md

@@ -108,7 +108,7 @@ dotnet run
 The URL of the generated image is printed to the console.
 
 ```console
-https://dalleproduse.blob.core.windows.net/private/images/552c5522-af4a-4877-a19c-400fac04a422/generated_00.png?se=2023-08-17T16%3A54%3A40Z&sig=XGCIx9r0WvWTJ0LL%2FJGymo2WYp4FDbSQNNrGRUnnUzI%3D&ske=2023-08-19T01%3A10%3A14Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2023-08-12T01%3A10%3A14Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02
+https://dalleproduse.blob.core.windows.net/private/images/b7ac5e55-f1f8-497a-8d0e-8f51446bf538/generated_00.png?se=2024-07-12T13%3A47%3A56Z&sig=Zri37iYVTVtc52qzTFBOqPgSHvXwEhcO86Smv2ojB%2FE%3D&ske=2024-07-17T12%3A15%3A44Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2024-07-10T12%3A15%3A44Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02
 ```
 
 > [!NOTE]

articles/ai-services/openai/includes/dotnet.md

@@ -26,20 +26,53 @@ ms.date: 07/26/2023
 
 ## Set up
 
-[!INCLUDE [Create a new .NET application](./dotnet-new-application.md)]
+### Create a new .NET Core application
+
+In a console window (such as cmd, PowerShell, or Bash), use the `dotnet new` command to create a new console app with the name `azure-openai-quickstart`. This command creates a simple "Hello World" project with a single C# source file: *Program.cs*.
+
+```dotnetcli
+dotnet new console -n azure-openai-quickstart
+```
+
+Change your directory to the newly created app folder. You can build the application with:
+
+```dotnetcli
+dotnet build
+```
+
+The build output should contain no warnings or errors.
+
+```output
+...
+Build succeeded.
+ 0 Warning(s)
+ 0 Error(s)
+...
+```
+
+Install the OpenAI .NET client library with:
+
+```console
+dotnet add package Azure.AI.OpenAI --version 1.0.0-beta.17
+```
+
+> [!NOTE]
+> The completions API is only available in version `1.0.0-beta.17` and earlier of the `Azure.AI.OpenAI` client library. For the latest `2.0.0` and higher version of `Azure.AI.OpenAI`, the recommended approach to generate completions is to use the [chat completions API](chatgpt-dotnet). 
 
 [!INCLUDE [get-key-endpoint](get-key-endpoint.md)]
 
 [!INCLUDE [environment-variables](environment-variables.md)]
 
-
 > [!div class="nextstepaction"]
 > [I ran into an issue with the setup.](https://microsoft.qualtrics.com/jfe/form/SV_0Cl5zkG3CnDjq6O?PLanguage=DOTNET&Pillar=AOAI&Product=gpt&Page=quickstart&Section=Set-up)
 
 ## Create a sample application
 
 From the project directory, open the *program.cs* file and replace with the following code:
 
+> [!NOTE]
+> The completions API is only available 
+
 ```csharp
 using Azure;
 using Azure.AI.OpenAI;
@@ -48,20 +81,19 @@ using static System.Environment;
 string endpoint = GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");
 string key = GetEnvironmentVariable("AZURE_OPENAI_API_KEY");
 
-AzureOpenAIClient azureClient = new(
+var client = new OpenAIClient(
     new Uri(endpoint),
     new AzureKeyCredential(key));
-ChatClient chatClient = azureClient.GetChatClient("gpt-35-turbo");
 
-ChatCompletion completion = chatClient.CompleteChat(
-    [
-        // System messages represent instructions or other guidance about how the assistant should behave
-        new SystemChatMessage("You are a helpful assistant that talks like a pirate."),
-        // User messages represent user input, whether historical or the most recen tinput
-        new UserChatMessage("When was Microsoft founded?")
-    ]);
+CompletionsOptions completionsOptions = new()
+{
+    DeploymentName = "gpt-35-turbo-instruct",
+    Prompts = { "When was Microsoft founded?" },
+};
 
-Console.WriteLine($"{completion.Role}: {completion.Content[0].Text}");
+Response<Completions> completionsResponse = client.GetCompletions(completionsOptions);
+string completion = completionsResponse.Value.Choices[0].Text;
+Console.WriteLine($"Chatbot: {completion}");
 ```
 
 > [!IMPORTANT]

articles/ai-services/openai/includes/use-your-data-dotnet.md

@@ -29,57 +29,37 @@ string searchEndpoint = GetEnvironmentVariable("AZURE_AI_SEARCH_ENDPOINT");
 string searchKey = GetEnvironmentVariable("AZURE_AI_SEARCH_API_KEY");
 string searchIndex = GetEnvironmentVariable("AZURE_AI_SEARCH_INDEX");
 
+#pragma warning disable AOAI001
+AzureOpenAIClient azureClient = new(
+    new Uri(azureOpenAIEndpoint),
+    new AzureKeyCredential(azureOpenAIKey));
+ChatClient chatClient = azureClient.GetChatClient(deploymentName);
+
+ChatCompletionOptions options = new();
+options.AddDataSource(new AzureSearchChatDataSource()
+{
+    Endpoint = new Uri(searchEndpoint),
+    IndexName = searchIndex,
+    Authentication = DataSourceAuthentication.FromApiKey(searchKey),
+});
 
-var client = new OpenAIClient(new Uri(azureOpenAIEndpoint), new AzureKeyCredential(azureOpenAIKey));
+ChatCompletion completion = chatClient.CompleteChat(
+    [
+        new UserChatMessage("What are my available health plans?"),
+    ], options);
+
+Console.WriteLine(completion.Content[0].Text);
+
+AzureChatMessageContext onYourDataContext = completion.GetAzureMessageContext();
 
-var chatCompletionsOptions = new ChatCompletionsOptions()
+if (onYourDataContext?.Intent is not null)
 {
-    Messages =
-    {
-        new ChatRequestUserMessage("What are my available health plans?"),
-    },
-    AzureExtensionsOptions = new AzureChatExtensionsOptions()
-    {
-        Extensions =
-        {
-            new AzureCognitiveSearchChatExtensionConfiguration()
-            {
-                SearchEndpoint = new Uri(searchEndpoint),
-                Key = searchKey,
-                IndexName = searchIndex,
-            },
-        }
-    },
-    DeploymentName = deploymentName
-};
-
-Response<ChatCompletions> response = client.GetChatCompletions(chatCompletionsOptions);
-
-ChatResponseMessage responseMessage = response.Value.Choices[0].Message;
-
-Console.WriteLine($"Message from {responseMessage.Role}:");
-Console.WriteLine("===");
-Console.WriteLine(responseMessage.Content);
-Console.WriteLine("===");
-
-Console.WriteLine($"Context information (e.g. citations) from chat extensions:");
-Console.WriteLine("===");
-foreach (ChatResponseMessage contextMessage in responseMessage.AzureExtensionsContext.Messages)
+    Console.WriteLine($"Intent: {onYourDataContext.Intent}");
+}
+foreach (AzureChatCitation citation in onYourDataContext?.Citations ?? [])
 {
-    string contextContent = contextMessage.Content;
-    try
-    {
-        var contextMessageJson = JsonDocument.Parse(contextMessage.Content);
-        contextContent = JsonSerializer.Serialize(contextMessageJson, new JsonSerializerOptions()
-        {
-            WriteIndented = true,
-        });
-    }
-    catch (JsonException)
-    {}
-    Console.WriteLine($"{contextMessage.Role}: {contextContent}");
+    Console.WriteLine($"Citation: {citation.Content}");
 }
-Console.WriteLine("===");
 ```
 
 > [!IMPORTANT]
@@ -92,30 +72,16 @@ dotnet run program.cs
 ## Output
 
 ```output
-Answer from assistant:
-===
-The available health plans in the Contoso Electronics plan and benefit packages are the Northwind Health Plus and Northwind Standard plans [^1^].
-===
-Context information (e.g. citations) from chat extensions:
-===
-tool: {
-  "citations": [
-    {
-      "content": "...",
-      "id": null,
-      "title": "...",
-      "filepath": "...",
-      "url": "...",
-      "metadata": {
-        "chunking": "orignal document size=1011. Scores=3.6390076 and None.Org Highlight count=38."
-      },
-      "chunk_id": "2"
-    },
-    ...
-  ],
-  "intent": "[\u0022What are my available health plans?\u0022]"
-}
-===
+Contoso Electronics offers two health plans: Northwind Health Plus and Northwind Standard [doc1]. Northwind Health Plus is a comprehensive plan that provides coverage for medical, vision, and dental services, prescription drug coverage, mental health and substance abuse coverage, and coverage for preventive care services. It also offers coverage for emergency services, both in-network and out-of-network. On the other hand, Northwind Standard is a basic plan that provides coverage for medical, vision, and dental services, prescription drug coverage, and coverage for preventive care services. However, it does not offer coverage for emergency services, mental health and substance abuse coverage, or out-of-network services [doc1].
+
+Intent: ["What are the available health plans?", "List of health plans available", "Health insurance options", "Types of health plans offered"]
+
+Citation:
+Contoso Electronics plan and benefit packages
+
+Thank you for your interest in the Contoso electronics plan and benefit packages. Use this document to
+
+learn more about the various options available to you...// Omitted for brevity
 ```
 
 This will wait until the model has generated its entire response before printing the results. Alternatively, if you want to asynchronously stream the response and print the results, you can replace the contents of *Program.cs* with the code in the next example.
@@ -136,6 +102,8 @@ string searchEndpoint = GetEnvironmentVariable("AZURE_AI_SEARCH_ENDPOINT");
 string searchKey = GetEnvironmentVariable("AZURE_AI_SEARCH_API_KEY");
 string searchIndex = GetEnvironmentVariable("AZURE_AI_SEARCH_INDEX");
 
+#pragma warning disable AOAI001
+
 AzureOpenAIClient azureClient = new(
     new Uri(azureOpenAIEndpoint),
     new AzureKeyCredential(azureOpenAIKey));
@@ -149,12 +117,39 @@ options.AddDataSource(new AzureSearchChatDataSource()
     Authentication = DataSourceAuthentication.FromApiKey(searchKey),
 });
 
-ChatCompletion completion = chatClient.CompleteChat(
+var chatUpdates = chatClient.CompleteChatStreamingAsync(
     [
-        new UserChatMessage("What are the best-selling Contoso products this month?"),
+        new UserChatMessage("What are my available health plans?"),
     ], options);
 
-Console.WriteLine(completion.Content[0].Text);
+AzureChatMessageContext onYourDataContext = null;
+await foreach (var chatUpdate in chatUpdates)
+{
+    if (chatUpdate.Role.HasValue)
+    {
+        Console.WriteLine($"{chatUpdate.Role}: ");
+    }
+
+    foreach (var contentPart in chatUpdate.ContentUpdate)
+    {
+        Console.Write(contentPart.Text);
+    }
+
+    if (onYourDataContext == null)
+    {
+        onYourDataContext = chatUpdate.GetAzureMessageContext();
+    }
+}
+
+Console.WriteLine();
+if (onYourDataContext?.Intent is not null)
+{
+    Console.WriteLine($"Intent: {onYourDataContext.Intent}");
+}
+foreach (AzureChatCitation citation in onYourDataContext?.Citations ?? [])
+{
+    Console.Write($"Citation: {citation.Content}");
+}
 ```
 
 > [!div class="nextstepaction"]