docs: review the articles

petar-i-todorov · petar-i-todorov · commit 8246eb6ed4b4 · 2025-10-20T19:16:09.000+03:00
diff --git a/interactivity/ai-powered-insights-overview.md b/interactivity/ai-powered-insights-overview.md
@@ -1,5 +1,5 @@
 ---
-title: AI-Powered Insights
+title: AI-Powered Insights Overview
 page_title: AI-Powered Insights in Report Preview
 description: "Learn about the AI insights feature of Reporting, which allow users to execute predefined or custom prompts on the core data of the previewed report, receiving responses from an AI model."
 slug: telerikreporting/designing-reports/adding-interactivity-to-reports/ai-powered-insights
diff --git a/interactivity/configuring-ai-powered-insights.md b/interactivity/configuring-ai-powered-insights.md
@@ -1,5 +1,5 @@
 ---
-title: Customizing the AI-Powered Insights
+title: Customizing AI-Powered Insights
 page_title: How to Customize the AI-Powered Insights
 description: "Learn how to configure the AI-powered insights functionality to handle common and not so much use cases."
 slug: telerikreporting/designing-reports/adding-interactivity-to-reports/configuring-ai-powered-insights
@@ -8,7 +8,9 @@ published: True
 position: 3
 ---
 
-This article outlines the different ways to customize the AI-powered insights functionality to handle different use cases. They are listed as follows:
+# Customizing AI-Powered Insights
+
+This article explains how to customize the AI-powered insights functionality for different use cases. There are two distinct ways to achieve this:
 - [Configuring the Report Engine](#configuring-the-report-engine) - Declarative configuration through application settings.
 - [Overriding ReportsControllerBase Methods](#overriding-reportscontrollerbase-methods) - Programmatic customization with custom logic.
 
@@ -45,7 +47,7 @@ This is a base configuration, but it can be further extended to handle specific
 
 By default, the **AI Prompt** dialog requests explicit consent from users before sending prompts to the AI model. This ensures transparency about data being sent to external AI services and gives users control over their data privacy
 
-	<img src="images/user-consent.png" style="border: 1px solid lightgray; width: 500px" alt="User Consent for AI Summaries" />
+<img src="images/user-consent.png" style="border: 1px solid lightgray; width: 500px" alt="User Consent for AI Summaries" />
 
 In enterprise environments where AI usage policies are already established or when working with trusted internal models, you may want to streamline the user experience by disabling this consent requirement. In these cases, you can set the `requireConsent` option to `false`:
 
@@ -70,9 +72,9 @@ In enterprise environments where AI usage policies are already established or wh
 
 ### Prompts Configuration
 
-By default, users can create their own custom prompts to ask any questions about their reports. While this provides maximum flexibility, it can lead to unpredictable token usage costs and potentially inconsistent results. In these cases, you might want to provide the users with predefined prompts that are designed to handle specific tasks.
+By default, users can create their own custom prompts to ask any questions about their reports. While this provides maximum flexibility, it can lead to unpredictable token usage costs and potentially inconsistent results. In these cases, you can provide the users with predefined prompts that are designed to handle specific tasks.
 
-To restrict users to predefined prompts only, you can set `allowCustomPrompts` to `false` and add the predefined prompts through the `predefinedPrompts` option:
+To restrict users to predefined prompts only, you set `allowCustomPrompts` to `false` and add the predefined prompts through the `predefinedPrompts` option:
 
 ````JSON
 {
@@ -396,47 +398,6 @@ public override async Task<HttpResponseMessage> GetAIResponse(string clientID, s
     return await base.GetAIResponse(clientID, instanceID, documentID, threadID, args);
 }
 ````
-````Token·Usage·Validation
-/// <summary>
-/// Examines the approximate tokens count and determines whether the prompt should be sent to the LLM.
-/// </summary>
-/// <returns></returns>
-public override async Task<HttpResponseMessage> GetAIResponse(string clientID, string instanceID, string documentID, string threadID, AIQueryArgs args)
-{
-    const int MAX_TOKEN_COUNT = 500;
-    args.ConfirmationCallBack = (AIRequestInfo info) =>
-    {
-        if (info.EstimatedTokensCount > MAX_TOKEN_COUNT)
-        {
-            return ConfirmationResult.CancelResult($"The estimated token count exceeds the allowed limit of {MAX_TOKEN_COUNT} tokens.");
-        }
-
-        return ConfirmationResult.ContinueResult();
-    };
-
-    return await base.GetAIResponse(clientID, instanceID, documentID, threadID, args);
-}
-````
-````RAG·Optimization·Monitoring
-/// <summary>
-/// Examines whether the RAG optimization is applied for the current prompt.
-/// </summary>
-/// <returns></returns>
-public override async Task<HttpResponseMessage> GetAIResponse(string clientID, string instanceID, string documentID, string threadID, AIQueryArgs args)
-{
-    args.ConfirmationCallBack = (AIRequestInfo info) =>
-    {
-        if (info.Origin == AIRequestInfo.AIRequestOrigin.Client)
-        {
-            System.Diagnostics.Trace.TraceInformation($"RAG optimization is {info.RAGOptimization} for this prompt.");
-        }
-
-        return ConfirmationResult.ContinueResult();
-    };
-
-    return await base.GetAIResponse(clientID, instanceID, documentID, threadID, args);
-}
-````
 
 ## See Also
 
diff --git a/interactivity/custom-iclient.md b/interactivity/custom-iclient.md
@@ -18,123 +18,123 @@ To enable a custom AI client implementation, follow these steps:
 
 1. Create a class that implements the `Telerik.Reporting.AI.IClient` interface. The following example demonstrates an Azure OpenAI integration for illustration purposes, though you can use any LLM provider:
 
-````C#
-using Azure.AI.OpenAI;
-using Microsoft.Extensions.AI;
-using System.ClientModel;
-using Telerik.Reporting.AI;
-
-namespace WebApplication1.AI;
-
-public class CustomAIClient : IClient
-{
-    public string Model { get; } = "gpt-4o-mini";
-
-    public bool SupportsSystemPrompts => false;
+    ````C#
+    using Azure.AI.OpenAI;
+    using Microsoft.Extensions.AI;
+    using System.ClientModel;
+    using Telerik.Reporting.AI;
 
-    private readonly IChatClient chatClient;
+    namespace WebApplication1.AI;
 
-    public CustomAIClient()
+    public class CustomAIClient : IClient
     {
-        string endpoint = "https://ai-explorations.openai.azure.com/";
-        string credential = "YOUR_API_KEY";
-        string model = "gpt-4o-mini";
+        public string Model { get; } = "gpt-4o-mini";
 
-        chatClient = new AzureOpenAIClient(new Uri(endpoint), new ApiKeyCredential(credential))
-            .GetChatClient(model)
-            .AsIChatClient();
-    }
+        public bool SupportsSystemPrompts => false;
 
-    public async Task<IReadOnlyCollection<IMessage>> GetResponseAsync(IReadOnlyCollection<IMessage> query, CancellationToken cancellationToken)
-    {
-        // Convert Telerik.Reporting.AI IMessage to Microsoft.Extensions.AI ChatMessage
-        var chatMessages = new List<ChatMessage>();
-        foreach (var message in query)
-        {
-            ChatRole chatRole = message.Role switch
-            {
-                MessageRole.System => ChatRole.System,
-                MessageRole.Assistant => ChatRole.Assistant,
-                MessageRole.User => ChatRole.User,
-                _ => throw new ArgumentException($"Invalid MessageRole: {message.Role}")
-            };
+        private readonly IChatClient chatClient;
 
-            // Convert text contents from Telerik.Reporting.AI TO Microsoft.Extensions.AI
-            var textContents = message.Contents
-                .OfType<Telerik.Reporting.AI.TextContent>()
-                .Select(textContent => new Microsoft.Extensions.AI.TextContent(textContent.Text))
-                .Cast<AIContent>()
-                .ToList();
+        public CustomAIClient()
+        {
+            string endpoint = "https://ai-explorations.openai.azure.com/";
+            string credential = "YOUR_API_KEY";
+            string model = "gpt-4o-mini";
 
-            chatMessages.Add(new ChatMessage(chatRole, textContents));
+            chatClient = new AzureOpenAIClient(new Uri(endpoint), new ApiKeyCredential(credential))
+                .GetChatClient(model)
+                .AsIChatClient();
         }
 
-        // Call Azure OpenAI
-        var response = await chatClient.GetResponseAsync(chatMessages, new ChatOptions(), cancellationToken);
-
-        // Convert response back to Telerik.Reporting.AI IMessage
-        var resultMessages = new List<IMessage>();
-        foreach (var responseMessage in response.Messages)
+        public async Task<IReadOnlyCollection<IMessage>> GetResponseAsync(IReadOnlyCollection<IMessage> query, CancellationToken cancellationToken)
         {
-            MessageRole messageRole = responseMessage.Role.Value switch
+            // Convert Telerik.Reporting.AI IMessage to Microsoft.Extensions.AI ChatMessage
+            var chatMessages = new List<ChatMessage>();
+            foreach (var message in query)
             {
-                "system" => MessageRole.System,
-                "assistant" => MessageRole.Assistant,
-                "user" => MessageRole.User,
-                _ => throw new ArgumentException($"Invalid ChatRole: {responseMessage.Role}")
-            };
-
-            // Convert back to Telerik.Reporting.AI content
-            var contents = responseMessage.Contents
-                .OfType<Microsoft.Extensions.AI.TextContent>()
-                .Select(tc => new Telerik.Reporting.AI.TextContent(tc.Text))
-                .Cast<IContent>()
-                .ToList();
-
-            resultMessages.Add(new Message(messageRole, contents));
+                ChatRole chatRole = message.Role switch
+                {
+                    MessageRole.System => ChatRole.System,
+                    MessageRole.Assistant => ChatRole.Assistant,
+                    MessageRole.User => ChatRole.User,
+                    _ => throw new ArgumentException($"Invalid MessageRole: {message.Role}")
+                };
+
+                // Convert text contents from Telerik.Reporting.AI TO Microsoft.Extensions.AI
+                var textContents = message.Contents
+                    .OfType<Telerik.Reporting.AI.TextContent>()
+                    .Select(textContent => new Microsoft.Extensions.AI.TextContent(textContent.Text))
+                    .Cast<AIContent>()
+                    .ToList();
+
+                chatMessages.Add(new ChatMessage(chatRole, textContents));
+            }
+
+            // Call Azure OpenAI
+            var response = await chatClient.GetResponseAsync(chatMessages, new ChatOptions(), cancellationToken);
+
+            // Convert response back to Telerik.Reporting.AI IMessage
+            var resultMessages = new List<IMessage>();
+            foreach (var responseMessage in response.Messages)
+            {
+                MessageRole messageRole = responseMessage.Role.Value switch
+                {
+                    "system" => MessageRole.System,
+                    "assistant" => MessageRole.Assistant,
+                    "user" => MessageRole.User,
+                    _ => throw new ArgumentException($"Invalid ChatRole: {responseMessage.Role}")
+                };
+
+                // Convert back to Telerik.Reporting.AI content
+                var contents = responseMessage.Contents
+                    .OfType<Microsoft.Extensions.AI.TextContent>()
+                    .Select(tc => new Telerik.Reporting.AI.TextContent(tc.Text))
+                    .Cast<IContent>()
+                    .ToList();
+
+                resultMessages.Add(new Message(messageRole, contents));
+            }
+
+            return resultMessages;
         }
 
-        return resultMessages;
-    }
-
-    public static IClient GetCustomAIClient()
-    {
-        return new CustomAIClient();
+        public static IClient GetCustomAIClient()
+        {
+            return new CustomAIClient();
+        }
     }
-}
-````
+    ````
 
 1. Register the custom client in your `ReportServiceConfiguration`:
 
     * .NET
 
     ````C#
-builder.Services.TryAddSingleton<IReportServiceConfiguration>(sp => new ReportServiceConfiguration
-{
-    HostAppId = "MyApp",
-    AIClientFactory = WebApplication1.AI.CustomAIClient.GetCustomAIClient,
-    // ...
-});
-````
+    builder.Services.TryAddSingleton<IReportServiceConfiguration>(sp => new ReportServiceConfiguration
+    {
+        HostAppId = "MyApp",
+        AIClientFactory = WebApplication1.AI.CustomAIClient.GetCustomAIClient,
+        // ...
+    });
+    ````
 
     * .NET Framework
 
     ````C#
-public class CustomResolverReportsController : ReportsControllerBase
-{
-    static ReportServiceConfiguration configurationInstance;
-
-    static CustomResolverReportsController()
+    public class CustomResolverReportsController : ReportsControllerBase
     {
-        configurationInstance = new ReportServiceConfiguration
+        static ReportServiceConfiguration configurationInstance;
+
+        static CustomResolverReportsController()
         {
-            HostAppId = "MyApp",
-            AIClientFactory = WebApplication1.AI.CustomAIClient.GetCustomAIClient,
-            // ...
-        };
+            configurationInstance = new ReportServiceConfiguration
+            {
+                HostAppId = "MyApp",
+                AIClientFactory = WebApplication1.AI.CustomAIClient.GetCustomAIClient,
+                // ...
+            };
+        }
     }
-}
-````
+    ````
 
 You can further customize the AI client to enable additional features like RAG optimization, predefined prompts, and user consent settings. For more details, refer to [Configuring the AI-Powered Insights]({%slug telerikreporting/designing-reports/adding-interactivity-to-reports/configuring-ai-powered-insights%}).
 
@@ -170,6 +170,8 @@ This dual-call approach optimizes token usage by first determining RAG suitabili
 
 When RAG is disabled, the method is called only once without the report metadata being pre-filtered.
 
+> RAG is available only in .NET and .NET Standard.
+
 ## See Also
 
 * [AI-Powered Insights Overview]({%slug telerikreporting/designing-reports/adding-interactivity-to-reports/ai-powered-insights%})
diff --git a/interactivity/using-ai-powered-insights-rest-service.md b/interactivity/using-ai-powered-insights-rest-service.md
