Preferences

Oxygen AI Positron Assistant Preferences

Various settings can be configured in Options > Preferences > Plugins > Oxygen AI Positron Assistant:

Enable AI Positron Assistant: Deselect this setting to disable the AI assistant. Combined with the Project Options radio button, you can disable the AI assistant for certain projects.
Context prompt: The context provides useful information about the user to the AI and is used in each action and chat request to create more relevant and personalized responses.
Additional context file: The content of this referenced file is added to the Context value and used in all AI action prompts. The file path reference can contain editor variables.
Allow automatic validation and correction of AI-generated content: When enabled (default), AI-generated content is automatically validated when you insert it into a document or after the AI saves it to a file. If errors are detected, the AI automatically tries to provide a corrected version of the generated content.
Note:
The AI will not be able to find solutions for certain types of errors, so some manual corrections will still be required.

AI Service Configuration Preferences

Various service-related connection settings can be configured in Options > Preferences > Plugins > Oxygen AI Positron Assistant > AI Service Configuration:

AI Positron Service address: Currently, there is only one public platform that provides this service.
Default model: The default model is used for the chat pane and for actions that do not explicitly specify a fixed model. Each chosen model consumes a certain number of credits per token. The gpt-4o model is used by default if no other model is chosen.

Actions Preferences

Various settings related to AI actions can be configured in Options > Preferences > Plugins > Oxygen AI Positron Assistant > Actions:

Load default actions: Specifies if default actions are loaded.
Additional actions folder: You can use this option to specify a local folder where you have stored additional actions.
Actions to exclude: You can specify a comma-separated list of IDs for the actions that you do not want presented in the list of available actions. Use the menu to the right of the text field to choose the actions to exclude.
Embed AI Assistant in Author page: Controls whether or not the AI Positron Assistant drop-down widget is displayed when documents are open in the Author visual editing mode. This drop-down list contains some of the most useful AI actions for creating and improving the structure and content of the current document.

Saved Memories Preferences

Enable memory store: A setting used to disable the user-specific memory store that contains rules stored by the AI engine for the current user. It is enabled by default.
Memory store text area: A text area that contains the set of rules stored by the AI engine for the current user. The text area is fully editable. All the rules from this text area are gathered and used along with the Context when any AI action is invoked or when chatting with the AI engine.

Functions and RAG Preferences

Various settings related to the use of functions for retrieval augmented generation can be configured in the Retrieval-Augmented Generation (RAG) preferences page (click the

Settings button in the header and go to Retrieval-Augmented Generation (RAG)).

Enable functions

Enables the use of functions for retrieval-augmented generation and for writing content in the project.

Enable project-based RAG

Enables retrieval-augmented generation based on similar content obtained from the current open project. Actions and chat interactions generate content give more precise and meaningful responses when this setting is enabled. It is enabled by default. The available functions used for RAG are listed in the text box.

The AI actions that use RAG are:

Generate Documentation Draft
New DITA Topic
Expand Draft
Create Topics

Ask for confirmation: When selected (default), the end user is asked to confirm whenever each specific project-based RAG function is about to be processed.
Content retrieval token limit: Specifies a limitation for the upper amount of project content that may be sent to the AI engine to enhance responses and tune them based on the currently open project.

Enable external RAG sources

Enables the use of external retrieval augmented generation sources.

Oxygen Feedback site token: When the Oxygen Feedback product is used to provide search functionality for a web site generated from the DITA XML project, its search system can be used to retrieve related content. In the Oxygen Feedback administrative interface, find the installation instructions for the site version that you want to use (click the Installation button on your version's tile in the Site Version page). The installation information contains a unique deploymentToken value that can be copied and pasted into the Oxygen Feedback site token field.
Oxygen Feedback site description: A description for this external content retrieval site that is passed to the AI engine to help it decide whether or not the external source is used.

Enable writing content in project

Allows functions that can be used by the AI to write content in the current project. The available functions used for this purpose are listed in the text box.

Limit read/write access to

Allows you to restrict the locations where functions can read and write content. You can specify these locations as a comma-separated list of resource paths. By default, read and write access is restricted to the project directory and the directory of the current root map.

XPath Functions Preferences

Enable XPath Functions

Enables the use of AI-specific XPath functions in Oxygen when applying Schematron validation or XSLT transformations.

Cache responses and reuse them for identical prompts: If enabled (default), responses for identical requests are stored (cached), resulting in fewer requests being sent to the AI server and faster completion times. A Clear cache button located to the right of this option can be used to clear the cache.
Cache size: Specifies a maximum limit for the cache size.
Notify me when the number of requests exceeds: You can select this option and specify a number of AI requests that when exceeded, a confirmation dialog box is displayed asking if you want to continue using the XPath AI functions. If you select "No" for the answer, the XPath functions will be disabled.