Addons

ServerAssistantAI supports a variety of addons that can be installed to enhance the plugin's functionality and improve the overall user experience.

Available Addons

Advanced Question Detection

• Description: This addon provides an advanced custom-trained question detection model to accurately identify and classify player questions. It improves the AI's ability to understand and respond to a wider range of inquiries, including more complex or ambiguous questions. The model can be tested on our online interface here. The Advanced Question Detection model will periodically keep getting improved to enhance its accuracy and performance.

• Language Support: The advanced question detection model was trained exclusively on English data, so currently it can only accurately detect and classify questions asked in English, but multilingual support is planned. If players ask questions in other languages, the addon may not be able to identify them correctly.

• Features:

  • Improved accuracy in detecting and categorizing player questions

  • Support for a broader range of question types and formats

  • Reduced false positives and false negatives in question identification

  • Customizable sensitivity to fine-tune question detection

• Installation: Download the SAAI-AdvancedQuestionDetection-1.2.jar file from the #saai-addons forum channel on our Discord and place it in the plugins/ directory. Restart your server for the changes to take effect.

• Configuration: To enable the advanced question detection, change the question_detection field in the config.yml file to advanced. When the advanced mode is enabled, the interpersonal_regex field will be ignored, but the regex field will still work in conjunction with the advanced question detection model. For full configuration details and more information, please refer to the dedicated forum post on our Discord server.

Please make sure that your server is stable and running smoothly without any performance issues before using the Advanced Question Detection addon. If your server is already experiencing performance problems due to any reason, running an AI model concurrently may further impact the server's stability and performance.

Anthropic Addon (LLM)

• Description: Claude is a family of foundational AI models that can be used in a variety of applications. This addon allows ServerAssistantAI to utilize Anthropic's Claude models for LLM functionality.

• Installation: Download the SAAI-Anthropic-1.2.1.jar file from the #saai-addons forum channel on our Discord and place it in the plugins/ directory. Restart your server for the changes to take effect. Our forum post also includes configuration template files specifically for Anthropic models.

Azure OpenAI Addon (LLM & Embedding)

• Description: Azure OpenAI Service is a fully managed service that allows developers to easily integrate OpenAI models into their applications. This addon enables ServerAssistantAI to utilize Azure OpenAI for both LLM and embedding functionality.

• Installation: Download the SAAI-AzureOpenAI-1.2.1.jar file from the #saai-addons forum channel on our Discord and place it in the plugins/ directory. Restart your server for the changes to take effect. Our forum post also includes configuration template files specifically for OpenAI models.

HuggingFace Addon (LLM & Embedding)

• Description: HuggingFace provides access to thousands of open-source models for free through the HuggingFace Inference API. This addon integrates HuggingFace models into ServerAssistantAI for both LLM and embedding functionality.

• Installation: Download the SAAI-HuggingFace-1.2.1.jar file from the #saai-addons forum channel on our Discord and place it in the plugins/ directory. Restart your server for the changes to take effect. Our forum post also includes configuration template files specifically for Cohere models.

Google AI Studio Addon (LLM & Embedding)

• Description: Google AI Studio is the fastest way to start using Google's most advanced Gemini generative AI models. This addon integrates Google AI Studio models into ServerAssistantAI for both LLM and embedding functionality.

• Installation: Download the SAAI-GoogleAIStudio-1.2.1.jar file from the #saai-addons forum channel on our Discord and place it in the plugins/ directory. Restart your server for the changes to take effect. Our forum post also includes configuration template files specifically for Google Gemini models.

Mistral AI Addon (LLM & Embedding)

• Description: Mistral AI currently provides three types of access to Large Language Models. An API providing pay-as-you-go access to our latest models, Cloud-based deployments, Open source models available under the Apache 2.0 License, available on Hugging Face or directly from the documentation. This addon integrates Mistral AI models into ServerAssistantAI for both LLM and embedding functionality.

• Installation: Download the SAAI-MistralAI-1.2.1.jar file from the #saai-addons forum channel on our Discord and place it in the plugins/ directory. Restart your server for the changes to take effect. Our forum post also includes configuration template files specifically for Mixtral models.

Installing Addons

To install an addon for ServerAssistantAI, follow these steps:

1. Download the desired addon file (.jar) from the #saai-addons forum channel on our Discord.

2. Place the addon file in the plugins/ directory on your server.

3. Restart your server to load the addon and apply its features.

4. (Optional) Configure the addon's settings by editing its respective configuration file.

5. Verify that the addon is functioning correctly by testing its features in-game or checking the server console for any related messages or errors.

The improved question detection and expanded LLM options offered by these addons can significantly improve the AI's ability to understand and assist players effectively.

Creating Addons

To create an addon for ServerAssistantAI, you can use our API. Examples of addons that were created for ServerAssistantAI can be found on the SAAI-Addons open-source GitHub repository. These examples showcase how to integrate various AI providers and models into ServerAssistantAI using our API, along with how to structure your own addons, handle credentials, and implement chat and embedding models. Feel free to use these examples as a starting point for creating your own custom addons for ServerAssistantAI!