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
  8. Embedded PDF Viewer: This empowers users to seamlessly view referenced sources directly within the component
  9. Markdown Response: Provides styled responses rendered in markdown format with clear structure and visual appeal, featuring titles, bulleted lists, code blocks, and more.

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

Anonymous
  • v3.1.1 Release Notes
    • Minor 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.

  • v3.1.0 Release Notes
    1. Mobile Responsiveness: We have implemented mobile responsiveness to ensure an seamless user experience across all devices, enhancing accessibility and usability on mobile devices as well.
    2. Markdown Support: We have included styled responses rendered in markdown format. Now the content is presented with clear structure and visual appeal, featuring titles, bulleted lists, code blocks, and more.
    3. Embedded PDF Viewer: Introducing the Embedded PDF Viewer feature which empowers users to seamlessly view referenced sources directly within the component.
    4. Streaming Response Flexibility: Now we have the flexibility to enable/disable streaming functionality based on the configuration in the Document Vector Database Connected System configuration.
    5. Parameter Changes: Introduced a new parameter ‘enableEmbeddedPDFViewer’ to enable/disable the embedded PDF viewer. This defaults to true.

    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.

  • Hi  ,

    Due to the need to authenticate documents with user/group permissions, we are unable to make this plugin compatible with portals.

  • We are trying to use this component in Portal but seems to be not supported. Is there a way to use this in portal?

  • Hi,
    I think you would need to implement a chatbot with another technology (chat bot focused) where you can design a workflow according to your needs, and embed it in your Appian application and establish communication between them via integrations and web API. 

  • v3.0.4 Release Notes
    • Minor 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.

  • Hi  ,

    This chatbot is only for answering user questions based on document information and unfortunately will not be able to support this use case. 

  • Hello All,

    My use case is using ai-knowledge-assistant(community.appian.com/.../ai-knowledge-assistant), chatbot will ask question sequentially like

    ai-knowledge-assistant: Hello! I am your assistance. How can I help you?

    Human :I want to register one student in the school.

    ai-knowledge-assistant:sure! what is the name of the student?

    Human : Arka

    ai-knowledge-assistant:what is his previous school name?

    Human: Abc

    ai-knowledge-assistant: Please upload the school results <Upload button>

    Human:<human uploads the document>

    ai-knowledge-assistant: Please review the below information

    Student Name : Arka

    Previous school: Abc

    School result

    Please confirm

    Human: I confirmed

    <system creates an entry in the student record >

    Now my question are

    1. Is it possible to show the question sequentially ?

    2. Is it possible to have a button to upload a document and save it document folder?

    3. Is it possible to trigger the process model after user says like confirm?

    Appreciate your help in advance.

    Regards

    Arka

  • Hi  

    Currently, we do not have any plans to integrate this plugin with Amazon AI services. 

  • Hi , Is it possible to have this application work with Amazon AI services instead of Azure?