AI Knowledge Assistant

Overview

The AI Knowledge Assistant is an innovative UI component tailored to revolutionize user interactions within the Appian platform. By harnessing the power of large language models, this tool offers an immersive chatbot experience, allowing users not just to converse with state-of-the-art Generative AI models, but also source answers from their Appian Knowledge Center documents. This means, beyond traditional data retrieval, users can now semantically search and engage with their private data. Designed with adaptability in mind, the AI Knowledge Assistant seamlessly integrates with various organizational themes, ensuring a cohesive brand experience.

Key Features & Functionality

  1. Intuitive Chat Experience: With the integration of large language models, users can have natural, flowing conversations with the system, making data retrieval feel less like querying and more like conversing.
  2. Semantic Document Search: Go beyond keyword searches. With the Appian AI Chatbot, users can chat with documents, extracting nuanced insights from the Appian Knowledge Center. This semantic search capability ensures that the information retrieved is contextually relevant and precise.
  3. Privacy-Centric Interactions: Recognizing the importance of data privacy, the Chatbot is designed to allow users to interact with their private data in a secure environment. This ensures that sensitive information remains protected while still being accessible.
  4. Customizable Themes: Every organization is unique, and the Chatbot celebrates this individuality. It comes with a range of customizable themes that can be tailored to resonate with your company's brand aesthetics.
  5. Vector Database Integration: At the core of its functionality, the Chatbot utilizes a vector database. This advanced technology allows for efficient and accurate document interactions, transforming the way users engage with written content.
  6. Document Security: The AI Knowledge Assistant manages the security of Appian Documents to prevent unauthorized access to documents that users do not have the necessary permissions to view or edit.
  7. Response Streaming: The AI Knowledge Assistant delivers responses seamlessly by streaming information, providing users with a chatbot-like experience. This intuitive interface incorporates a convenient stop button, allowing users to halt the response stream at any point during the interaction. This feature enhances user control, enabling them to manage the flow of information according to their preferences and needs

Note: You must download the Document Vector Database Connected System to use the AI Knowledge Assistant component plugin.

Anonymous
  • v3.0.3 Release Notes
    1. Bug Fixes
    2. Updated the default value to false for the ‘chatWithoutDocuments’ property in the queryEmbeddedDocuments parameter.

    IMPORTANT NOTE: If you are using this plugin in production, open a support case and ask to increase Heap Max for app server by 1GB. This will increase query performance and allow the plugin to handle a larger number of concurrent users.

  • It is a native Appian vector database hosted on the Appian server.

  • Hello   , I'm sorry you're experiencing setup issues. Have your tried uploading documents into the vector database prior to referencing those documents in the Assistant? Make sure to set up the securityKey and documentList parameters in the Assistant according to the documentation.

  • I encountered an issue while trying to utilize the AI Knowledge Assistant component plugin. After successfully downloading and configuring the Document Vector Database Connected System as per the plugin requirements, I encountered an unexpected behavior when attempting to use the AI Knowledge Assistant component.

    Specifically, upon accessing the component, instead of encountering the expected submit button to ask questions, I am met with a round loading icon, indicating that the component is not loading properly. Despite waiting for a considerable amount of time, the submit button fails to appear, rendering the component unusable.

    I have ensured that all necessary configurations have been correctly implemented, including the setup of the Document Vector Database Connected System. However, despite these efforts, the issue persists.

  • v3.0.1 Release Notes
    • Bug Fixes
    IMPORTANT NOTE: If you are using this plugin in production, open a support case and ask to increase Heap Max for app server by 1GB. This will increase query performance and allow the plugin to handle a larger number of concurrent users.

  • If you are already using an older version of the AI Knowledge Assistant Component, complete the following steps to migrate to the newer version. This will be a one-time setup.

    • Install the latest version of the Document Vector Database Connected System.
    • Once the latest version of the connected system is installed, create a new Vector Database Connected System object. The previous connected system object and integrations based on it will continue to work.
      • Important Note: While creating the connected system object, do not use the same Database Name, provide a different value.
    • Use the List Documents Integration (based on the older version of the connected system) to get the list of all documents uploaded to the previous vector database.
    • Create an integration based on the new connected system object using the Upload Document Integration template and upload all the documents that were in the previous database.
    • Create new integration objects for the new connected system. Older integration objects will continue to function off the previous connected system version.
    • After the completion of the migration, set up the Third Party Credentials in the Admin Console as shown in the documentation and configure the “securityKey” parameter.

    There are also other parameter configuration changes to the component, please refer to the "Component Parameter Configuration" section of the documentation for more details.

  • v2.1.0 Release Notes

    1. Security Enhancements
    • Document Security Integration: The AI Knowledge Assistant now incorporates document security, ensuring users can only query documents they have permission to access in Appian.
    • New Parameter - securityKey: Manage document access permissions.
    • New Parameter - inaccessibleDocumentsVisibility: Allows control over the visibility of documents that users lack permission to access.

    1. Reduced Complexity and Increased Performance
    • Removed Parameters: The embeddingConfiguration, timeout, and topK parameters have been deprecated to reduce setup complexity and improve performance via internal optimizations.
    • Updated Style Parameter:
      • New Parameter - collapseChatOnLoad: Manages the initial collapsed state of the assistant.
      • New Parameter -  chatHeight: Now nested within the style parameter.

    1. User Interface Enhancements
    • Automatic User Icon: The userIcon will default to the user’s Appian profile picture.
    • UI/UX Improvements
      • Sticky scroll navbar/search bar
      • Initial assistant message can be removed
      • Sources UI changed to the document name and page number
      • Clicking on a Source now saves the source’s document ID into onDocumentSelect
      • Document source chunks can now span multiple pages
      • Theme UI enhancements
      • Modern scroll bar and enlarged text
      • New “Show More” Sources interaction to handle large number of sources
      • Control over document inaccessible visibility 

    1. Performance and Reliability
    • Query Latency Reduction: Increased query speed through internal optimizations.
    • Dynamic Load Handling: Enhanced capability to manage higher load during simultaneous user queries.
    • Follow-up Question Answering: Enhanced to address ambiguous queries related to previous questions more accurately.
    • Error Handling and Bug Fixes: Improved system stability and reliability.
  • How to count the tokens that being sent? Would it be possible to show if the selected documents have passed the token limit? Thanks.

  • What is the vector db used for the AI knowledge Assistant component?