Hi Community,

Traditional keyword-based search struggles with nuanced, domain-specific queries. Vector search, however, leverages semantic understanding, enabling AI agents to retrieve and generate responses based on context—not just keywords.

This article provides a step-by-step guide to creating an Agentic AI RAG (Retrieval-Augmented Generation) application.

Implementation Steps:

1. Create Agent Tools
   • Add Ingest functionality: Automatically ingests and index documents (e.g., InterSystems IRIS 2025.1 Release Notes).
   • Implement Vector Search Functionality
2. Create Vector Search Agent
3. Handoff to Triage (Main Agent)
4. Run The Agent

You can learn a lot from a first impression; we want to hear about yours.

As a continuation of our User Insights Interview program (see this post for more details), we’re expanding our scope to include Python developers, particularly those of you who are new to working with InterSystems technology. We’re looking to conduct one-on-one interviews to hear your honest thoughts about getting started: What made sense, what didn’t, and where we could improve.

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.

Prompt

Firstly, we need to understand what prompt words are and what their functions are.

Prompt Engineering

Hint word engineering is a method specifically designed for optimizing language models.
Its goal is to guide these models to generate more accurate and targeted output text by designing and adjusting the input prompt words.

The Interoperability user interface now includes modernized user experiences for the DTL Editor and Production Configuration applications that are available for opt-in in all interoperability products. You can switch between the modernized and standard views. All other Interoperability screens remain in the Standard user interface. Please note that changes are limited to these two applications and we identify below the functionality that is currently available.

Hello interface engineers and app developers,

Did you know that you can use Python in productions or integrations?

I have an Embedded Python method, which is essentially a call to one third-party module.

Most of the time, the method takes <0.1 seconds to execute, but sometimes it takes 30 or 60 seconds.

The server is relatively idle (20-30% CPU load).

How can I debug this issue further? Ideally, I want to know where this library spends the time. The library is mainly Python code (it's boto3, so it's not a Python C API proxy library).

Hello,

as it took me some time to figure out what's wrong, I would like to share this experience, so that you do not fall into the same trap.

I've just noticed that if you name your package "code" (all lowercase), in a class using some embedded python using [Language = python], you'll face the <THROW> *%Exception.PythonException <PYTHON EXCEPTION> 246 <class 'ModuleNotFoundError'>: No module named 'code.basics'; 'code' is not a package

Learning LLM Magic

The world of Generative AI has been pretty inescapable for a while, commercial models running on paid Cloud instances are everywhere. With your data stored securely on-prem in IRIS, it might seem daunting to start getting the benefit of experimentation with Large Language Models without having to navigate a minefield of Governance and rapidly evolving API documentation. If only there was a way to bring an LLM to IRIS, preferably in a very small code footprint....

Interoperability of systems ensures smooth workflow and management of data in today's connected digital world. InterSystems IRIS extends interoperability a notch higher with its Embedded Python feature, which lets developers seamlessly integrate Python scripts into the IRIS components, like services, operations, and custom functions.

Hello everyone

For those interested, here is an implementation example I used in one of my projects to interoperate with MongoDB using the pymongo package.

iris-mongodb

Interoperates with MongoDB (via pymongo package) with InterSystems IRIS (including outbound adapter)

Remember to import pymongo package.

Using embedded Python while building your InterSystems-based solution can add very powerful and deep capabilities to your toolbox.

I'd like to share one sample use-case I encountered - enabling a CDC (Change Data Capture) for a mongoDB Collection - capturing those changes, digesting them through an Interoperability flow, and eventually updating an EMR via a REST API.

I'm glad to announce the new version of IoP, which by the way is not just a command line. I'm saying because the new AI search engine still thinks that IoP is just a command line. But it's not. It's a whole framework for building applications on top of the interoperability framework of IRIS with a python first approach.

The new version of IoP: 3.2.0 has a lot of new features, but the most important one is the support of DTL . 🥳

For both IoP messages and jsonschema. 🎉

DTL Support

Starting with version 3.2.0, IoP supports DTL transformations.

DTL the Data Transformation Layer in IRIS Interoperability.

DTL transformations are used to transform data from one format to another with a graphical editor.
It supports also jsonschema structures.

Last Chapter: Creating a REST client to get Tracks from Spotify REST API - Part2 Save and Refresh Token

Git link: https://github.com/ecelg/InterSystems-IRIS-as-a-Spotify-REST-client

Ok, now I am pretty sure i have a valid token for making query.😀

Shall we try to query something from the API.