Syncro Soft is proud to announce the release of Oxygen AI Positron Assistant 4.0, a powerful tool that helps users increase their productivity by providing support for using AI-generated content within Oxygen tools - Oxygen XML Editor/Author/Developer, Oxygen JSON Editor, Oxygen XML Web Author, and Oxygen Content Fusion. Version 4.0 enhances the existing AI features and introduces new actions and functionalities, making the assistant even more capable.

With version 4.0, the recently implemented Retrieval-Augmented Generation (RAG) optimization process was broadened. In addition to retrieving context information from a project, it can now also retrieve content using the Oxygen Feedback search functionality. The AI Positron Fix action now also leverages the Retrieval-Augmented Generation (RAG) process, leading to more relevant error fixes.

Intelligent Agents is a newly added category of AI-powered actions that introduces a set of powerful tools designed to streamline DITA XML topic management. These intelligent agents go beyond simple content manipulation, offering advanced capabilities to save files, add references to the DITA map, and access a wide range of functions for contextual understanding and project structure modification. The new actions available in this category include:

Expand Draft - Enhances a draft of a DITA XML topic by refining the content, adding markup that is consistent with similar topics, and generating documentation based on the referenced images using Vision support.

Split Topic - Splits large topics with numerous subjects into multiple topic files. The newly created topics are also conveniently referenced in the DITA map that is currently open in the DITA Maps Manager.

Create Topics - Generates DITA XML topics based upon user input, incorporating relevant project content. It creates a topic hierarchy, assigns DITA document types, and proposes a DITA map location. Topics are then saved and added upon user approval.

The Reuse category is another addition to the Oxygen AI Positron Assistant, focusing on optimizing content management and consistency within DITA XML workflows. It introduces the following AI-powered actions:

Component - Asks the AI to identify the most similar existing reusable component that matches the current selected paragraph.

Product Name - Searches for product names in the selected content and replaces them with key references if keys are defined for the particular product names.

Developers will benefit from the new Suggest Refactoring AI action, which generates suggestions to refactor selected XSLT or XSD code, thus making it easier to understand and maintain. Additionally, the existing Generate Code action now produces code that is more relevant to the current editor type (XSL, XQuery, CSS, JSON, XML Schema, or Schematron) by reusing components from the current document.

Moreover, information about the document type is now automatically passed to the AI for context in chat sessions, and various new function calls were added that can be referenced within custom actions to offer context information in order to retrieve more relevant answers from the AI.

Other improvements include the proper detection of Markdown content containing XML code in the AI's response, allowing for the XML code block to be inserted or previewed. Additionally, document type information is now automatically passed as context for conversations when initiated directly from a new chat with the AI. Various security enhancements have also been implemented.

For more information, see: https://www.oxygenxml.com/ai_positron_assistant.html