Q2 2025 Release Changes

_config.yml

@@ -215,6 +215,9 @@ navigation:
     libraries/radpdfprocessing/features/embedded-file-streams:
         title: Embedded File Streams
         position: 5
+    libraries/radpdfprocessing/features/ai-document-analysis:
+        title: AI Document Analysis
+        position: 6
     libraries/radpdfprocessing/model/interactive-forms:
         title: Interactive Forms
     libraries/radpdfprocessing/model/interactive-forms/form-fields:

getting-started/download-product-files.md

@@ -0,0 +1,50 @@
+---
+title: Download Product Files
+description: Learn how to download the source code, pdf documentation, different versions from your Telerik account.
+page_title: Download Product Files
+slug: download-product-files
+tags: download, dpl, product, file, assets, distribution
+published: True
+position: 4
+---
+
+# Download Product Files
+
+As of **Q2 2025** the [Telerik Document Processing]({%slug introduction%}) libraries are available as a separate distribution in the **Downloads** section of your [Telerik account](https://www.telerik.com/account/). 
+
+Since the **Telerik Document Processing** is a part of several [Telerik bundles](https://www.telerik.com/purchase.aspx) and it is installed following the steps for installing the suite with which you've obtained the product, when you purchase a Telerik license, you can download the following files:
+
+* Latest Public version
+
+* Latest [Preview version]({%slug obtain-use-latest-internal-build-version%})
+
+* Assemblies available as NuGet packages
+
+* Previous versions
+
+* Source code
+
+* Documentation files
+
+Тo download these files, follow the steps below:
+
+1\. Log into [your Telerik account](https://www.telerik.com/account/) and click the **Downloads** option: 
+
+![Downloads in Your Account](images/downloads-account.png)  
+
+2\. Select **Telerik Document Processing**:
+
+![DPL Downloads in Your Account](images/dpl-downloads-account.png)  
+
+3\. Select an asset you want to download: DLLs, PDB files, NuGet Packages, documentation files, or Source code:
+
+![DPL Product Files](images/dpl-product-files.png)   
+
+4\. You can choose between official Public versions or Preview versions (if such exist) according to the activation date of your license. From the **Version** drop down list, you can also select which specific version to download.
+
+>important If you are looking for a specific version, but it isn't listed in the Version list, please contact our sales team: **[email protected]**. They will make the required version available for download.
+
+## See Also
+
+* [What Versions of Document Processing Libraries are Distributed with the Telerik Products]({%slug distribute-telerik-document-processing-libraries-net-versions%})
+* [Latest Internal Build (Preview Version)]({%slug obtain-use-latest-internal-build-version%})

knowledge-base/before-q2-2025.md

@@ -0,0 +1,61 @@
+---
+title: Licensing before 2025
+page_title: "Licensing mechanism before Q2 2025 explained."
+description: "Learn more about Licensing in Telerik Document Processing before Q2 2025 and how you may upgrade your Trial license to Purchase license"
+type: how-to
+slug: licensing-before-q2-2025
+tags: licensing, dpl, document, processing, before, 2025, trial, dev
+published: True
+position: 4
+---
+
+# Licensing before 2025
+
+[Telerik Document Processing]({%slug introduction%}) used to come in separate **Trial** and **Developer** (or commercial) assets distribution until Q2 2025.
+
+![License Mechanism](images/license-mechanism.png)    
+
+>caution After launching the [new licensing mechanism](https://www.telerik.com/blogs/license-key-files-telerik-kendo-ui-products-2025-update), the activation is performed through a [license key]({%slug setting-up-license-key%}) (trial or commercial). Upgrading from a Trial to Developer (or commercial) version requires only updating the license key without the necessity of reinstalling the respective Telerik product.
+
+## Trial Licenses
+
+Telerik Document Processing is available under a 30-day trial license with a full-featured version of the tool—no restrictions! What’s more, you are eligible for complete technical support during your trial period in case you have any questions. 
+
+The free trial licenses of all Telerik products are fully functional and will work for an unlimited time, but will randomly display a copyright message. These builds have the `Trial` abbreviation in their file names. To use the trial version of Telerik Document Processing, you need to agree to the [End User License Agreement (EULA)]({%slug license-agreement%}).
+
+* To sign up for a free 30-day trial, [Log in to your Telerik account or create one](https://www.telerik.com/account).
+* To download the trial version, refer to the [Telerik Document Processing's Product page](https://www.telerik.com/document-processing-libraries).
+* To download a developer build with a trial license, log into your [Telerik account](https://www.telerik.com/account/).
+
+## Developer Licenses
+
+Telerik Document Processing also offers a developer license. To use Telerik Document Processing commercially, you need to purchase a license and to agree to the terms of use, which are fully described in the [End User License Agreement (EULA)]({%slug license-agreement%}).
+
+Developer licenses come with modified DLLs, which work without displaying copyright messages. If you have a Developer license for one or more Telerik components, you need to ensure that you are using the developer build when downloading the libraries. These builds have the `Dev` abbreviation in their file names.
+
+If your application is displaying a copyright message intermittently, this means that you are using a trial version of the product. Log in to your [Telerik account and download](https://www.telerik.com/account/downloads) the developer build by choosing the product from the available Licenses.
+
+For more information on the commercial terms, refer to the pricing list of the [available developer licenses which include Telerik Document Processing](https://www.telerik.com/purchase.aspx) 
+
+## Upgrading from Trial to Developer
+
+To upgrade the trial version of your license to a developer license:
+
+1. Back up your Telerik Document Processing files and folders especially if your project uses the settings that are included in them.
+1. Uninstall the __Trial__ version of the Telerik product with which you have obtained the Document Processing libraries either by using the __Start Menu__ shortcut or the __Add/Remove Programs__ dialog.
+1. Obtain the new __Dev__ installer and [install Telerik Document Processing]({%slug installation-installing-on-your-computer%}).
+
+>note More information is available in the following KB article: [How to Upgrade Trial to Licensed Version]({%slug upgrade-trial-to-licensed-version%}).
+
+## Redistribution
+
+Telerik Document Processing is a part of several [Telerik bundles](https://www.telerik.com/purchase.aspx) and is licensed under the conditions with which you've obtained the product. Read more in the [Redistributing Telerik Document Processing]({%slug installation-deploying-telerik-document-processing%}) topic.
+
+For further discussing your planned use of Telerik Document Processing, send an email to [[email protected]](mailto:[email protected]).
+
+# See Also
+
+* [Trial vs Licensed version]({%slug trial-license-limitations%}) 
+* [Installing on Your Computer]({%slug installation-installing-on-your-computer%})
+* [Install using NuGet Packages]({%slug installation-nuget-packages%})
+* [Download Product Files]({%slug download-product-files%})

libraries/radpdfprocessing/features/ai-document-analysis/complete-context-question-processor.md

@@ -0,0 +1,168 @@
+---
+title: CompleteContextQuestionProcessor
+page_title: CompleteContextQuestionProcessor
+slug: radpdfprocessing-features-ai-document-analysis-complete-context-question-processor
+tags: ai, document, analysis, question, processor, complete, context
+published: True
+position: 4
+---
+
+# CompleteContextQuestionProcessor
+
+The `CompleteContextQuestionProcessor` class enables you to ask questions about a PDF document and receive answers based on the entire document content. Unlike [PartialContextQuestionProcessor]({%slug radpdfprocessing-features-ai-document-analysis-partial-context-question-processor%}), this processor sends the complete document text to the AI model, which is suitable for smaller documents or when you need to ensure that the AI model has access to all the information in the document. This class inherits from the abstract `AIProcessorBase` class, which provides common functionality for all AI processors.
+
+## When to Use CompleteContextQuestionProcessor
+
+The `CompleteContextQuestionProcessor` is ideal for the following scenarios:
+
+1. **Small Documents**: When the document is small enough to fit within the token limit of the AI model.
+2. **Holistic Understanding**: When the question requires understanding the entire document context.
+3. **Simplicity**: When you don't need the advanced embedding functionality of `PartialContextQuestionProcessor`.
+
+However, if you're working with larger documents or want to optimize token usage, you should use the [PartialContextQuestionProcessor]({%slug radpdfprocessing-features-ai-document-analysis-partial-context-question-processor%}#when-to-use-partialcontextquestionprocessor) instead.
+
+## Public API
+
+### Properties
+
+| Property | Description |
+|----------|-------------|
+| `Settings` | Gets the settings for the AI question-answering process. Returns `CompleteContextProcessorSettings`. |
+
+### Methods
+
+| Method | Description |
+|--------|-------------|
+| `public Task<string> AnswerQuestion(ISimpleTextDocument document, string question)` | Answers a question using the provided document. Parameters: `document` - The document containing the text to process, `question` - The question to answer. Returns a task that represents the asynchronous operation. The task result contains the answer to the question. |
+
+## CompleteContextProcessorSettings
+
+The `CompleteContextProcessorSettings` class provides configuration options for the question-answering process.
+
+### Settings Properties
+
+* **ModelMaxInputTokenLimit**: Gets or sets the maximum input token limit the model allows.
+* **TokenizationEncoding**: Gets or sets the tokenization encoding.
+* **ModelId**: Gets or sets the ID of the model.
+
+## Usage Example
+
+The following example demonstrates how to use the `CompleteContextQuestionProcessor` to ask questions about a PDF document, including working with specific document pages. For setting up the AI client as shown in this example, see the [AI Provider Setup]({%slug radpdfprocessing-features-ai-document-analysis-prerequisites%}#ai-provider-setup) section:
+
+#### __[C#] Example 1: Using CompleteContextQuestionProcessor__
+
+```csharp
+private async void AskQuestionUsingCompleteContext()
+{
+    // Load the PDF document
+    string filePath = @"path\to\your\document.pdf";
+    PdfFormatProvider formatProvider = new PdfFormatProvider();
+    RadFixedDocument fixedDocument;
+
+    using (FileStream fs = File.OpenRead(filePath))
+    {
+        fixedDocument = formatProvider.Import(fs);
+    }
+
+    // Set up the AI client (Azure OpenAI in this example)
+    string key = Environment.GetEnvironmentVariable("AZUREOPENAI_KEY");
+    string endpoint = Environment.GetEnvironmentVariable("AZUREOPENAI_ENDPOINT");
+    string model = "gpt-4o-mini";
+
+    AzureOpenAIClient azureClient = new(
+        new Uri(endpoint),
+        new Azure.AzureKeyCredential(key),
+        new AzureOpenAIClientOptions());
+    ChatClient chatClient = azureClient.GetChatClient(model);
+
+    IChatClient iChatClient = new OpenAIChatClient(chatClient);
+    int maxTokenCount = 128000;
+
+    // Create the processor
+    using (CompleteContextQuestionProcessor processor = 
+           new CompleteContextQuestionProcessor(iChatClient, maxTokenCount))
+    {
+        try
+        {
+            // Customize settings if needed
+            processor.Settings.TokenizationEncoding = "cl100k_base";
+            processor.Settings.ModelId = "gpt-4o-mini";
+
+            // Example 1: Process full document
+            // Convert the document to a simple text representation
+            ISimpleTextDocument plainDoc = fixedDocument.ToSimpleTextDocument();
+
+            // Ask a question about the full document
+            string question = "What is the main subject of this document?";
+            string answer = await processor.AnswerQuestion(plainDoc, question);
+
+            Console.WriteLine($"Question: {question}");
+            Console.WriteLine($"Answer: {answer}");
+
+            // Ask another question
+            string question2 = "What are the key conclusions drawn in this document?";
+            string answer2 = await processor.AnswerQuestion(plainDoc, question2);
+
+            Console.WriteLine($"Question: {question2}");
+            Console.WriteLine($"Answer: {answer2}");
+
+            // Example 2: Process specific pages
+            // Convert only pages 5-10 to a simple text document (0-based index)
+            ISimpleTextDocument partialDoc = fixedDocument.ToSimpleTextDocument(4, 9);
+
+            // Ask a question about the specific pages
+            string pageQuestion = "Summarize the content of pages 5-10 of the document.";
+            string pageAnswer = await processor.AnswerQuestion(partialDoc, pageQuestion);
+
+            Console.WriteLine($"Question: {pageQuestion}");
+            Console.WriteLine($"Answer: {pageAnswer}");
+        }
+        catch (ArgumentException ex) when (ex.Message.Contains("The text is too long"))
+        {
+            Console.WriteLine("The document is too large to process with CompleteContextQuestionProcessor.");
+            Console.WriteLine("Consider using PartialContextQuestionProcessor instead.");
+        }
+    }
+}
+```
+
+## Token Limit Considerations
+
+The `CompleteContextQuestionProcessor` sends the entire document to the AI model, which means the document must fit within the model's token limit. If the document exceeds this limit, the `AnswerQuestion` method will throw an `ArgumentException`. This is a key difference from the [SummarizationProcessor]({%slug radpdfprocessing-features-ai-document-analysis-summarization-processor%}#handling-large-documents), which can handle documents of any size.
+
+Here's how to check if a document is suitable for processing with `CompleteContextQuestionProcessor`:
+
+#### __[C#] Example 2: Checking Document Size__
+
+```csharp
+private bool IsDocumentSuitableForCompleteContext(RadFixedDocument document, int modelMaxInputTokenLimit)
+{
+    ISimpleTextDocument textDoc = document.ToSimpleTextDocument();
+
+    if (textDoc is ISimpleTextDocumentInternal internalDoc)
+    {
+        string text = internalDoc.Text;
+
+        // Create an encoding to count tokens
+        GptEncoding encoding = GptEncoding.GetEncoding("cl100k_base");
+
+        // Estimate the token count for the document text + prompt + typical question
+        const string prompt = "You are a helpful assistant. Use the following context to answer the question.";
+        const string typicalQuestion = "What is this document about?";
+
+        int estimatedTokens = encoding.Encode(prompt + text + typicalQuestion).Count;
+
+        // Allow for a safety margin
+        return estimatedTokens <= (int)(modelMaxInputTokenLimit * 0.9);
+    }
+
+    return false;
+}
+```
+
+## See Also
+
+* [AI Document Analysis Overview]({%slug radpdfprocessing-features-ai-document-analysis-overview%})
+* [Prerequisites]({%slug radpdfprocessing-features-ai-document-analysis-prerequisites%})
+* [SummarizationProcessor]({%slug radpdfprocessing-features-ai-document-analysis-summarization-processor%})
+* [PartialContextQuestionProcessor]({%slug radpdfprocessing-features-ai-document-analysis-partial-context-question-processor%})