Information
  • Author: Appian Corporation
  • Type: Plug-in (Connected System)
  • Support: This plug-in or utility is not supported by the author. The content is free to use with a licensed product, but it is made available as-is and Community supported.
  • Compatible Version(s): 24.2
  • First Released:
  • Last Updated:
  • Cost: Free
Resources
Share
Home » AppMarket » Document Vector Database

Document Vector Database

Overview

The Document Vector Database Connected System enables Large Language Models (LLMs) to answer user submitted questions based on Appian Knowledge Center Documents. By uploading documents to this connected system, users can perform semantic searches to pinpoint the most pertinent content related to their questions. The Connected System also boasts Client APIs tailored for the AI Knowledge Assistant Component. This allows the AI Knowledge Assistant Component to deliver AI generated answers to user inquiries sourced from documents stored in the database, as well as general questions.

Key Features & Functionality

  1. Upload Document - Uploads and stores the documents and its vector in the database.
  2. List Documents - Provides us the list of documents uploaded in the database.
  3. Database Operations
    1. Delete Documents - Enables us to delete the documents that are uploaded in the database.
    2. Sync Documents - Updates the existing documents in the database with the latest version of the document available in the Appian Knowledge Center.
    3. Change Database Password - Changes Database password.
  4. Query Documents - Get relevant pieces of content from documents for the given prompt.
  5. Generate Response - Perform search in the given documents and generate ChatGPT response for the given prompt.
  6. Client APIs for AI Knowledge Assistant component for fetching document details, chat completions, document querying, and uploading new documents to the database.

Notes:

  • Download the AI Knowledge Assistant, a sophisticated chatbot designed to perform semantic searches across your documents and provide precise answers to your queries.
  • This plugin is not supported for HA environments.
Anonymous
  • v3.0.0 Release Notes
    • Scalability Enhancements
    • We have significantly enhanced the vector database’s scalability to allow multiple users to interact with the chatbot concurrently. Please note that query speeds may vary depending on the length of the documents, the amount of documents queried, the number of concurrent users, and hardware configurations.
    • Query Performance
    • There has been a substantial increase in query performance. Documents that are queried are now temporarily cached in-memory, resulting in a slight latency during the initial query but followed by nearly instantaneous responses for subsequent questions. This update markedly improves the speed and efficiency of our query processing.
    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.

  • v2.0.1 Release Notes
    • Query Performance Optimization.
    • Bug Fixes and improvements.
  • in reply to zhanl0002

    1. There is no size limit to the embedded database. 

    2. The embedded vector db is stored as a Appian document in the Appian Knowledge Center.

  • in reply to Appian AppMarket

    If you are already using an older version of the Document Vector Database Connected System, complete the following steps to migrate to the newer version. This will be a one-time setup.

    • 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.
    • If you are using the “AI Knowledge Assistant Component”, update the component to the latest version. This is required for it to work with the new version of the connected system. To make the yellow error under “securityKey” disappear, append the latest version to the component name (ex. “AIKnowledgeAssistantField_v2”). After updating the component to the latest version, follow the Migration Guide provided in the component documentation.
  • v2.0.0 Release Notes
    1. Connected System Configuration Changes
      1. New Parameters: Added for Model/Deployment ID and Max Tokens (specific to Azure OpenAI Service) to enable the new Generate Response Integration.
      2. Database Username Removal: Now, only the Appian Username is required.
    2. Integration and Functionality Enhancements
      1. New Integration - Generate Response: This integration mimics AI Knowledge Assistant’s functionality by allowing documents to be queried based on a user’s question and sent to OpenAI to generate a response. A developer can now asynchronously call the ‘Generate Response’ integration, save this output, and pass this into the conversation parameter of the AI Assistant. This allows the AI Assistant to be automatically loaded with questions and answers when a user loads the interface.
      2. New Integration - Sync Documents: Updates the existing documents in the database with the latest version of the document available in the Appian Knowledge Center.
      3. Reduced Complexity: Chunk size and topK are now handled for the developer.
      4. New Parameter: Logged In User - loggedInUser() now required for all integrations to handle document security. Users will only be able to upload, delete, and view documents they have access to.
  • in reply to Julian Grunauer

    Hi  

    The generated doc has create user  username DDL command , where does it creates the user with the given username and password? Where can we check ?

  • in reply to Julian Grunauer

    Hi  ,

    Kindly answer the below questions:

    • Is there any external vector DB involved here where we can see our document embeddings?
    • In Appian as soon as we test connection this generated a database file, inside that DB we have lots of DDL, statements, and doc metadata, some chunks - who is responsible for triggers of that SQL?
    • Once embedded doc is generated , whatever documents we upload to vector DB via integration, those embedding gets stored in that same document only right , there is no other table/document involved in which we do indexing against our prompts? 

    Kindly let me know if we have correct understanding.

    Thanks

  • Is there any size limitation to the the embedded database that stored the vectors? Does the embedded db stored in APPIAN Cloud?

© 2024 Appian. All rights reserved.
We want to hear from you! Submit a review on Gartner or G2.