Hi Community,

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

Iris-RAG-Gen is a generative AI Retrieval-Augmented Generation (RAG) application that leverages the functionality of IRIS Vector Search to personalize ChatGPT with the help of the Streamlit web framework, LangChain, and OpenAI. The application uses IRIS as a vector store.

Application Features

• Ingest Documents (PDF or TXT) into IRIS
• Chat with the selected Ingested document
• Delete Ingested Documents
• OpenAI ChatGPT

Introduction

As AI-driven automation becomes an essential part of modern information systems, integrating AI capabilities into existing platforms should be seamless and efficient. The IRIS Agent project showcases how generative AI can work effortlessly with InterSystems IRIS, leveraging its powerful interoperability framework—without the need to learn Python or build separate AI workflows from scratch.

There are a lot of great community articles regarding "vector search on IRIS", and samples in OpenExchange. Everytime I see these, I'm so excited to know that so many developers already try vectors on IRIS!

But if you've not tried "Vector Search on IRIS" yet, please give me one minute 😄 I create one IRIS class - and with only one IRIS class you can see how you put vector data in your IRIS database and how you compare these in your application.

An effective source control solution allows organizations to manage complex codebases, facilitate seamless collaboration within development teams, and streamline deployment processes.

Sonic Healthcare, a leading provider of pathology, radiology, general practice, and corporate medical services, has significantly enhanced visibility and control over its complex environment by implementing Deltanji source control. The tight integration Deltanji provides with InterSystems IRIS and IRIS for Health has been central in achieving these improvements.

Hi Community,

In this article, I will introduce my application iris-HL7v2Gen .

IRIS-HL7v2Gen is a CSP application that facilitates the dynamic generation of HL7 test messages. This process is essential for testing, debugging, and integrating healthcare data systems. The application allows users to generate a wide variety of HL7 message types, validate their structure against HL7 specifications, explore the message hierarchy, and transmit messages over TCP/IP to production systems. These features are particularly useful in settings where compliance with HL7 standards is mandatory for interoperability between different healthcare organizations or systems.

Application Features

• Dynamic HL7 Message Generation: Instantly create HL7 messages for a range of message types, facilitating comprehensive testing.
• Message Structure Exploration: Visualize the structure of generated messages based on HL7 specifications.
• Value Set Visualization View predefined sets of allowable coded values for specific fields.
• Message Validation: Validate messages against HL7 standards to ensure compliance.
• TCP/IP Communication: Easily transmit messages to production using TCP/IP settings.
• Broad Message Type Support: Supports 184 different HL7 message types, ensuring versatility for various healthcare integration needs.
• ClassMethod: Generate a Test Message by Invoking a Class Method
• Version Support: Currently Supports HL7 Version 2.5

If one of your packages on OEX receives a review you get notified by OEX only of YOUR own package.
The rating reflects the experience of the reviewer with the status found at the time of review.
It is kind of a snapshot and might have changed meanwhile.
Reviews by other members of the community are marked by * in the last column.

I also placed a bunch of Pull Requests on GitHub when I found a problem I could fix.
Some were accepted and merged, and some were just ignored.
So if you made a major change and expect a changed review just let me know.

The latest "Bringing Ideas to Reality" InterSystems competition saw me trawling through the ideas portal for UI problems to have a go at.

https://www.youtube.com/embed/zw51X1JQhQ0
[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]

If one of your packages on OEX receives a review you get notified by OEX only of YOUR own package.
The rating reflects the experience of the reviewer with the status found at the time of review.
It is kind of a snapshot and might have changed meanwhile.
Reviews by other members of the community are marked by * in the last column.

I also placed a bunch of Pull Requests on GitHub when I found a problem I could fix.
Some were accepted and merged, and some were just ignored.
So if you made a major change and expect a changed review just let me know.

In principle I'm looking in forward direction.
Though from time to time it makes sense to turn back and see the full path taken.

• I started reporting my reviews almost 4 years ago.
• I just reviewed packages that I could reproduce in my environment.
• Skipping items beyond my physical or mental capacities.
• So some great packages might not be present here
• But I added also 139 contributions of other reviewers
• It was anyhow a total of 769 reviews published
• Meeting over this time 191 different authors

One of the challenges of creating a DICOM message is how to implement putting data in the correct place. Part of it is by inserting the data in the specific DICOM tags, while the other is to insert binary data such as a picture - In this article I will explain both.

To create a DICOM message, you can either use the EnsLib.DICOM.File class (to create a DICOM file) or the EnsLib.DICOM.Document class (to create a message that can be sent to PACS directly). In either case, the SetValueAt method will allow you to add your data to the DICOM tags.

If one of your packages on OEX receives a review you get notified by OEX only of YOUR own package.
The rating reflects the experience of the reviewer with the status found at the time of review.
It is kind of a snapshot and might have changed meanwhile.
Reviews by other members of the community are marked by * in the last column.

I also placed a bunch of Pull Requests on GitHub when I found a problem I could fix.
Some were accepted and merged, and some were just ignored.
So if you made a major change and expect a changed review just let me know.

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.