Hi Community,

In this article, I will introduce my application iris-AgenticAI .

The rise of agentic AI marks a transformative leap in how artificial intelligence interacts with the world—moving beyond static responses to dynamic, goal-driven problem-solving. Powered by OpenAI’s Agentic SDK , The OpenAI Agents SDK enables you to build agentic AI apps in a lightweight, easy-to-use package with very few abstractions. It's a production-ready upgrade of our previous experimentation for agents, Swarm.
This application showcases the next generation of autonomous AI systems capable of reasoning, collaborating, and executing complex tasks with human-like adaptability.

Application Features

• Agent Loop 🔄 A built-in loop that autonomously manages tool execution, sends results back to the LLM, and iterates until task completion.
• Python-First 🐍 Leverage native Python syntax (decorators, generators, etc.) to orchestrate and chain agents without external DSLs.
• Handoffs 🤝 Seamlessly coordinate multi-agent workflows by delegating tasks between specialized agents.
• Function Tools ⚒️ Decorate any Python function with @tool to instantly integrate it into the agent’s toolkit.
• Vector Search (RAG) 🧠 Native integration of vector store (IRIS) for RAG retrieval.
• Tracing 🔍 Built-in tracing to visualize, debug, and monitor agent workflows in real time (think LangSmith alternatives).
• MCP Servers 🌐 Support for Model Context Protocol (MCP) via stdio and HTTP, enabling cross-process agent communication.
• Chainlit UI 🖥️ Integrated Chainlit framework for building interactive chat interfaces with minimal code.
• Stateful Memory 🧠 Preserve chat history, context, and agent state across sessions for continuity and long-running tasks.

I was thinking about how to create a new parameter in a method, similar to Output or ByRef...

What documentation can I read to learn more about this?

I want to create a parameter customized.

When developing a new Interoperability Production, it is quite natural that settings are initially added in the Production.

However, as soon as you want to move the Production from development to a test or staging environment, it becomes clear that some settings like HTTP Servers, IP addresses and/or ports need to be changed. In order to avoid these settings being overwritten during a redeployment later on, it is essential that you move these settings from the Production to the System Default settings.

Monitor incremental changes in the database through scheduled tasks, display change trends through charts, set alarm thresholds, and write information to messages.log

How to use it

You can install it through Docker or ZPM

Deploying with Docker Prerequisites

Make sure you have git and Docker desktop installed.

Hi Community,

OpenAPI-Client Gen has just released, this is an application to create an IRIS Interoperability Production client from Swagger 2.0 specification.

Instead of the existing tool ^%REST that creates a server-side REST application, OpenAPI-Client Gen creates a complete REST Interoperability Production client template.

Install by ZPM:

There are many applications for working with HL7 V2 messages, but the tools for working with XML in IRIS Management Portal and Cache Studio are limited.

Hi everyone,

In this article, I’m excited to introduce CodeInspector, a tool designed to simplify code validation by applying custom rules tailored to your development requirements. Whether you're managing a large codebase or working in an agile environment, CodeInspector helps ensure code quality by offering flexibility and adaptability to specific project needs.

See the new team members in action:

https://www.youtube.com/embed/PdndX1p7pjc
[This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]

Try them online for yourself:

https://gitpod.io#snapshot/b31bdf9c-4657-402a-a2d

Get it from the Extensions view inside VS Code, or here in Marketplace.

Hi, I am considering making my own swagger json generation based on my rest api implementing the %CSP.REST class.

Before I begin, I was wondering if there is already some kind of support, perhaps in IRIS already, or some tools that might help me.

I have been using embedded python for more than 2 years now on a daily basis.
May be it's time to share some feedback about this journey.

Why write this feedback? Because, I guess, I'm like most of the people here, an ObjectScript developer, and I think that the community would benefit from this feedback and could better understand the pros & cons of chosing embedded python for developing stuff in IRIS. And also avoid some pitfalls.

• Feedback : Using embedded python daily for 2 years
• Introduction
• Starting with Python
  • Python is not ObjectScript
    • Pep8
    • Modules
    • Dunders
  • Conclusion
• Embedded Python
  • What is Embedded Python ?
  • How to use Embedded Python ?
  • How I use Embedded Python
    • Use Python libraries and code as they were ObjectScript classes
      • With the language tag
      • Without the language tag
      • Conclusion
    • Use a python first approach
      • Example : iris-fhir-python-strategy
      • Remarks
      • Where to find the code
      • How to implement a Strategy
      • Implementation of InteractionsStrategy
      • Implementation of Interactions
      • Interactions in Python
      • Implementation of the abstract python class
      • Too long, do a summary

TL;DR

This article introduces using the langchain framework supported by IRIS for implementing a Q&A chatbot, focusing on Retrieval Augmented Generation (RAG). It explores how IRIS Vector Search within langchain-iris facilitates storage, retrieval, and semantic search of data, enabling precise and up-to-date responses to user queries. Through seamless integration and processes like indexing and retrieval/generation, RAG applications powered by IRIS enable the capabilities of GenAI systems for InterSystems developers.

Introduction

In the next few weeks, my coworkers are planning to start using VSCode to code with InterSystems' products. Among the many advantages of that, I would emphasize being able to connect with other technologies, such as GitHub, with ease. Besides, VSCode also offers an extensive extensions store, where you can find many free add-ons that make coding faster and more efficient. Last but not least, to conquer the heart of every developer, it is open source.

Do you ever spend an age entering criteria in the message viewer page, trying to find a message just to realise you're in the wrong instance of IRIS?

Or get lost in a sea of message tabs struggling to spot that Visual Trace page your were JUST looking at?

Well, have you tried the IRIS WHIZ browser extension and its suite of tools designed to help you avoid such unpleasantness?

Is it planned that LOAD DATA takes into account several DATE/DATETIME formats with, for example, a parameter indicating the format used in the source data?

example :

LOAD DATA .../...
USING
{
  "from": {
    "file": {
       "dateformat": "DD/MM/YYYY"
    }
  }
}