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
Notes:
Thanks for reporting this; the issue is now resolved. Please update the connected system to V1.0.4.
Tried with both OpenAI and Azure Connected System, both results in successful connection, but integration throws error as mentioned above.
I am getting following error while upload a document using the connected system. Can anybody help me on this?
Simply search for the name you gave the database in the connected system by using the Appian objects search. This will allow you to find the embedded database document and the constant pointing to that document. If you want to create a new database with new documents, simply make a new connected system and name the database something different.
Can we see where are they stored physically or the only way is to query them?
All data is being stored in a native H2 database represented as an Appian Document. Embeddings are created using OpenAI/Azure, but all embeddings/text chunks are stored within the Appian environment.
Can I know where the embedded database is there is it like appian cloud db instance or just representing a vector DB like pinecone ,can we physically see that? As it is the main concern to build private Ai. Thank you.
The data is being stored in an embedded database represented as an Appian Document which is created when your click "Test Connection" in the connected system. This database will store chunks of document text along with their embeddings. The user's query will bring up the top most relevant chunks from the database.
This is set by the developer. The username refers to the Admin developer's Appian username and the database username/password are set so that only that user has access to the database.