Update AI-powered-insights.md (#1796)

* Update AI-powered-insights.md

* Update aiclient-element.md

Author: todorarabadzhiev

doc-output/configure-the-report-engine/aiclient-element.md

@@ -31,18 +31,6 @@ __`<AIClient>` element__
 |Child Elements|<ul><li>__predefinedPrompts__ - Optional element. Defines a list of predefined prompts that the AI client can use.</li><li>__ragSettings__ - Optional element. Configures the Retrieval-Augmented Generation (RAG) options.</li></ul>|
 |Parent Element|__Telerik.Reporting__ - Configures all settings that the Telerik Reporting Engine uses.|
 
-__`<ragSettings>` element__
-
->important The `ragSettings` element is valid only in .NET and .NET Standard. It is not supported in the .NET Framework.
-
-
-> The _ragSettings_ will be respected only when _allowRAG_ is _true_
-
-|   |   |
-| ------ | ------ |
-|Attributes|<ul><li>__tokenizationEncoding__ - Optional string attribute. If set, specifies the tokenization encoding used for Retrieval-Augmented Generation (RAG). By default, the encoding is determined automatically.</li><li>__modelMaxInputTokenLimit__ - Optional integer attribute. If set, specifies the maximum number of input tokens allowed by the RAG model. The default value is 15000.</li><li>__maxNumberOfEmbeddingsSent__ - Optional integer attribute. If set, specifies the maximum number of embeddings that can be sent in a single RAG request. The default value is 15.</li><li>__maxTokenSizeOfSingleEmbedding__ - Optional integer attribute. If set, specifies the maximum token size allowed for a single embedding in RAG. A value of 0 means there is no limit. The default value is 0.</li><li>__splitTables__ - Optional boolean attribute _(true by default)_. Indicates whether tables should be split during Retrieval-Augmented Generation (RAG) processing. When the splitting is allowed, only the relevant table cells will be taken into account, significantly reducing the number of tokens</li></ul>|
-|Parent Element|__AIClient__|
-
 __`<predefinedPrompts>` element__
 
 |   |   |
@@ -59,6 +47,17 @@ __`<add>` element__
 |Child Elements|None|
 |Parent Element|__predefinedPrompts__|
 
+__`<ragSettings>` element__
+
+|   |   |
+| ------ | ------ |
+|Attributes|<ul><li>__tokenizationEncoding__ - Optional string attribute. If set, specifies the tokenization encoding used for Retrieval-Augmented Generation (RAG). By default, the encoding is determined automatically.</li><li>__modelMaxInputTokenLimit__ - Optional integer attribute. If set, specifies the maximum number of input tokens allowed by the RAG model. The default value is 15000.</li><li>__maxNumberOfEmbeddingsSent__ - Optional integer attribute. If set, specifies the maximum number of embeddings that can be sent in a single RAG request. The default value is 15.</li><li>__maxTokenSizeOfSingleEmbedding__ - Optional integer attribute. If set, specifies the maximum token size allowed for a single embedding in RAG. A value of 0 means there is no limit. The default value is 0.</li><li>__splitTables__ - Optional boolean attribute _(true by default)_. Indicates whether tables should be split during Retrieval-Augmented Generation (RAG) processing. When the splitting is allowed, only the relevant table cells will be taken into account, significantly reducing the number of tokens</li></ul>|
+|Parent Element|__AIClient__|
+
+>important The `ragSettings` element is valid only in .NET and .NET Standard. It is not supported in the .NET Framework.
+
+> The _ragSettings_ will be respected only when _allowRAG_ is _true_
+
 ## Example
 
 The following code example demonstrates how to configure the Reporting engine with an Azure OpenAI client that uses the GPT-4o mini model variant. In addition, the AI functionality is limited to a few predefined prompts that enable it to summarize and translate the report.

interactivity/AI-powered-insights.md

@@ -22,6 +22,13 @@ To bring the power of Generative AI (GenAI) into reporting workflows, we are int
 
 ### Key Features:
 
+- **Retrieval-Augmented Generation (RAG)**  
+  When enabled, the option helps produce more accurate, up-to-date, and relevant responses by referencing authoritative knowledge bases outside of the training data sources. By default, the feature is enabled.
+
+  When enabled, you may configure the RAG through the [AIClient ragSettings element]({%slug telerikreporting/aiclient-element%}##attributes-and-elements).
+
+  Alternatively, you may disable the feature by setting the _AIClient allowRAG_ attribute to _false_.
+  
 - **Predefined Summary Prompts**  
   Users can choose from a set of **predefined prompts** tailored for common tasks like summarization, explanation, and data insights—boosting efficiency with minimal effort.