Hi folks, 

I made a solution (https://openexchange.intersystems.com/package/iris-pretty-gpt-1) and want to use it like 

CREATE FUNCTION ChatGpt(IN prompt VARCHAR)
RETURNS VARCHAR
PROCEDURE
LANGUAGE OBJECTSCRIPT
{
    return ##class(dc.irisprettygpt.main).prompt(prompt)
}


CREATE TABLE people (
name VARCHAR(255),
city VARCHAR(255),
age INT(11)
)


INSERT INTO people ChatGpt("Make a json file with 100 lines of structure [{'name':'%name%', 'age':'%age%', 'city':'%city%'}]")

I know that a FUNCTION can only return one result.

A few months ago, I faced a significant challenge: streamlining the handling of business logic in our application. My goal was to extract the business logic from the code and hand it over to analysts. Dealing with a multitude of rules could easily result in a code littered with countless "if" statements, especially if the coder lacked an understanding of cyclomatic complexity. Such code becomes a source of pain for those working with it—difficult to write, test, and develop.

Hi folks

I want to tell you how you can make your own assistant based on IRIS and OpenAI (perhaps you can then move to your own AI models)

iris-recorder-helper

This is the first time I have fully tried developing an application for IRIS and I want to point out steps that may also be useful to you

1. Deploy to google cloud via github workflows (One container with an IRIS database and a web server in Python (flask)) and placing secrets inside the application not through an environment variable
2. Record audio from the browser and send to the server
3. Launching cron jobs via the ZPM module
4. Integration