AI customer support design: leave document search to AI and contract decisions to DB rules(qiita.com)
Writing language: KoreanRead in the original language
Plain summary
- This is a manga-style introductory resource written by Yuji Arakawa of Oracle Japan. A new engineer designs a support system that finds the manual matching an inquiry and checks contract information to see whether an on-site visit is possible.
- Document search finds items similar in meaning to the question, but first narrows candidates by customer, model, and publication status. Contract decisions are not left to the AI; they are placed as a decision column in a DB view (a virtual table that applies conditions in advance).
- In tests where the AI chooses and uses document search and contract lookup tools, problems occur such as tools not being called, execution errors, and wrong target device errors. The failure cases in the story are fictional examples to explain the design, and they are prevented by checking the call records in code.
- If the work of turning documents into numeric arrays for meaning comparison is done inside the DB, the full set of documents is not sent outside. The AI that generates answers uses an external cloud service.
Editorial opinion
O: If you are a backend developer who needs to add per-customer access restrictions to an internal document search chatbot, the customer-restricted view and the contract-decision view in the original demo repository are worth following as a design reference.
X: Converting documents into vectors inside the DB uses the DB's CPU and memory, so you should check throughput and the number of concurrent runs yourself in your own environment.
Writing language: Korean
Found on
Qiita ↗ / Published by source
Have you run into something like this? Tell us in a line or two what you did. You do not need to know the product.