Hi developers!

I'm testing vibecoding with ObjectScript and my silicon friend created a code-block that got me thinking "what's wrong"?

Here is the piece of code:

for i=0:1:(json.%Size()-1) {

set p = json.%Get(i)

if (p="value1")!(p="value2") {

quit 1
}

AI wanted to quit from a method with a return value. Good intention, but bad use of the command.

And ObjectScript compiler compiles this code with no error(?) (syntax linter in VSCode says it's a syntax, kudos @Brett Saviano ).

But in action, it produces <COMMAND>, of course.

Thirteen years ago, I attained dual undergraduate degrees in electrical engineering and math, then promptly started full-time at InterSystems using neither. One of my most memorable and stomach-churning academic experiences was in Stats II. On an exam, I was solving a moderately difficult confidence interval problem. I was running out of time, so (being an engineer) I wrote out the definite integral on the exam paper, punched it into my graphing calculator, wrote an arrow with “calculator” over it, then wrote the result.

This project is an experiment to use OpenAI API to answer to user prompts in the healthcare domain using FHIR resources and Python code.

Project idea

Generative AIs, like the LLM models available on OpenAI, has been demonstrated remarkable power to understand and answer high level questions. They use huge amounts of data to train their models, so they can answer complex questions.

They can even use programming languages to create code based on prompts - and I have to confess that the idea of getting my work automated causes me some anxiety.

After seeing several article raving about how ground-breaking the recent release of ChatGPT is, I thought I would try asking it to help with a Caché newbie question:  How do you find the version of InterSystems Caché?

To be honest, I was quite surprised at what the chat bot told me:

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.
This project explores how ChatGPT and Anthropic Claude, two of the most advanced AI models, can interact with IRIS using Custom GPTs and the Model Context Protocol (MCP).

Hey Community,

It's time for the first programming contest of the year, and there's a surprise so read on! Please welcome:

🏆 InterSystems AI Programming Contest: Vector Search, GenAI, and AI Agents 🏆

Duration: March 17 - April 6, 2025

Prize pool: $12,000 + a chance to be invited to the Global Summit 2025!

Hey Community,

We have more exciting news! The new InterSystems online programming contest dedicated to Generative AI, Vector Search and Machine Learning is starting very soon! 

🏆 InterSystems Vector Search, GenAI and ML Contest 🏆

Duration: April 22 - May 19, 2024

Prize pool: $14,000

Hi Community!

Just want to share with you an exercise I made to create "my own" chat with GPT in Telegram.

It became possible because of two components on Open Exchange: Telegram Adapter by @Nikolay Solovyev and IRIS Open-AI by  @Kurro Lopez

So with this example you can setup your own chat with ChatGPT in Telegram. 

Let's see how to make it work!

A "big" or "small" ask for ChatGPT?

I tried OpenAI GPT's coding model a couple of weeks ago, to see whether it can do e.g. some message transformations between healthcare protocols. It surely "can", to a seemingly fair degree. 
It has been nearly 3 weeks, and it's a long, long time for ChatGPT, so I am wondering how quickly it grows up by now, and whether it could do some of integration engineer jobs for us, e.g. can it create an InterSystems COS DTL tool to turn the HL7 into FHIR message? 

Immediately I got some quick answers, in less than one minute or two.

Hi Developers!

We are happy to present the bonuses page for the applications submitted to the InterSystems AI Programming Contest!

See the results below.

Hi Community,

We’re excited to share a brand-new Instruqt tutorial: 

🧑‍🏫 RAG using InterSystems IRIS Vector Search

This hands-on lab walks you through building a Retrieval Augmented Generation (RAG) AI chatbot powered by InterSystems IRIS Vector Search. You’ll see how vector search can be leveraged to deliver up-to-date and accurate responses, combining the strengths of IRIS with generative AI.

✨ Why try it?

Artificial Intelligence (AI) is getting a lot of attention lately because it can change many areas of our lives. Better computer power and more data have helped AI do amazing things, like improving medical tests and making self-driving cars. AI can also help businesses make better decisions and work more efficiently, which is why it's becoming more popular and widely used. How can one integrate the OpenAI API calls into an existing IRIS Interoperability application?

Problem

Do you resonate with this - A capability and impact of a technology being truly discovered when it's packaged in a right way to it's audience. Finest example would be, how the Generative AI took off when ChatGPT was put in the public for easy access and not when Transformers/RAG's capabilities were identified. At least a much higher usage came in, when the audience were empowered to explore the possibilities.

As you all know, the world of artificial intelligence is already here, and everyone wants to use it to their benefit.

There are many platforms that offer artificial intelligence services for free, by subscription or private ones. However, the one that stands out because of the amount of "noise" it made in the world of computing is Open AI, mainy thanks to its most renowned services: ChatGPT and DALL-E.

What is Open AI?

Hi Community!
As an AI language model, ChatGPT is capable of performing a variety of tasks like language translation, writing songs, answering research questions, and even generating computer code. With its impressive abilities, ChatGPT has quickly become a popular tool for various applications, from chatbots to content creation.
But despite its advanced capabilities, ChatGPT is not able to access your personal data. So we need to build a custom ChatGPT AI by using LangChain Framework:
Below are the steps to build a custom ChatGPT:

• Step 1: Load the document 

• Step 2: Splitting the document into chunks

• Step 3: Use Embedding against Chunks Data and convert to vectors

• Step 4: Save data to the Vector database

• Step 5: Take data (question) from the user and get the embedding

• Step 6: Connect to VectorDB and do a semantic search

• Step 7: Retrieve relevant responses based on user queries and send them to LLM(ChatGPT)

• Step 8: Get an answer from LLM and send it back to the user

  For more details, please Read this article

Currently, many digital artists use generative AI technology as a support to accelerate the delivery of their work. Nowadays it is possible to generate a corresponding image from a text sentence. There are several market solutions for this, including some available to be used through APIs. See some at this link: https://www.analyticsvidhya.com/blog/2023/08/ai-image-generators/.

I created a new application to use in IRIS taking advantage of one of these APIs. I chose the Imagine API.

Hi Community,

Round 2 of the GenAI Crowdsourcing Mini-Contest is here! Everyone can join, even if you missed Round 1. You have $5 million in fantasy funds to invest in up to 5 promising submissions.

🎁 Rewards

• The top-funded submission of Round 1 will emerge victorious.
• The mastermind of the winning concept earns 5,000 points, while 3 astute "investor(s)" backing the winning idea get a chance to receive 200 bonus points each.

Dive into the game, strategically allocate your virtual investments, and aim for maximum returns! Deadline: Dec 31st, 2023

FHIR has revolutionized the healthcare industry by providing a standardized data model for building healthcare applications and promoting data exchange between different healthcare systems. As the FHIR standard is based on modern API-driven approaches, making it more accessible to mobile and web developers. However, interacting with FHIR APIs can still be challenging especially when it comes to querying data using natural language.

Introducing the FHIR - AI and OpenAPI Chain application, a solution that allows users to interact with FHIR APIs using natural language queries.

Hi, colleagues!

As you can see the new topic of the programming contest - AI Agents. 

The topic was over-hyped recently on the Internet and has different meanings. You might get curious about what we mean by AI agents in regard to the InterSystems programming contest.

Yet another example of applying LangChain to give some inspiration for new community Grand Prix contest.

I was initially looking to build a chain to achieve dynamic search of html of documentation site, but in the end it was simpler to borg the static PDFs instead.

Create new virtual environment

mkdir chainpdf

cd chainpdf

python -m venv .

I try to get a vector from calling GetEmbedding, but i failed to convert it into a vector 

Here is a simplyfied sample class: 

Class User.myclass Extends %Persistent
{ Property myVECTOR As %Vector(CAPTION = "Vector");

Property myProperty As %String(MAXLEN = 40) [ Required ];

}

here the GetEmbedding part from User.mymethods:

...
ClassMethod GetEmbedding(sentences As %String) As %String [ Language = python ]
{
  import sentence_transformers   model = 

What is Unstructured Data?
Unstructured data refers to information lacking a predefined data model or organization. In contrast to structured data found in databases with clear structures (e.g., tables and fields), unstructured data lacks a fixed schema. This type of data includes text, images, videos, audio files, social media posts, emails, and more.

Why Are Insights from Unstructured Data Important?
According to an IDC (International Data Corporation) report, 80% of worldwide data is projected to be unstructured by 2025, posing a significant concern for 95% of businesses.

Hi Everyone,

Join us at the online Developer Roundtable to discuss Generative AI Use Cases in Healthcare on August 31, 10 am ET. 
Learn Use Cases + Reference Architecture in Healthcare, and witness the demo of LLMs. We will have time for Q&A and open discussion as usual.

Speaker: @Nicholai Mitchko , Manager, Solution Partner Sales Engineer, InterSystems

Background: Nicholai runs a team of 10 solution engineers at InterSystems that help healthcare companies design, develop, and deliver solutions at enormous scale. In his free time, Nicholai works on large language models, including developing his own models which appear on the Huggingface OpenLLM leaderboard.

See the recording on our YouTube channel:

We all know that having a set of proper test data before deploying an application to production is crucial for ensuring its reliability and performance. It allows to simulate real-world scenarios and identify potential issues or bugs before they impact end-users. Moreover, testing with representative data sets allows to optimize performance, identify bottlenecks, and fine-tune algorithms or processes as needed. Ultimately, having a comprehensive set of test data helps to deliver a higher quality product, reducing the likelihood of post-production issues and enhancing the overall user experience. 

In this article, let's look at how one can use generative AI, namely Gemini by Google, to generate (hopefully) meaningful data for the properties of multiple objects. To do this, I will use the RESTful service to generate data in a JSON format and then use the received data to create objects.

Introduction

This article aims to explore how the FHIR-PEX system operates and was developed, leveraging the capabilities of InterSystems IRIS.

Streamlining the identification and processing of medical examinations in clinical diagnostic centers, our system aims to enhance the efficiency and accuracy of healthcare workflows. By integrating FHIR standards with InterSystems IRIS database Java-PEX, the system help healthcare professionals with validation and routing capabilities, ultimately contributing to improved decision-making and patient care.

Fun or No Fun - how serious is it?

Large language models are stirring up some phenomena in recent months. So inevitably I was playing ChatGPT too over last weekend, to probe whether it would be a complimentary to some BERT based "traditional" AI chatbots I was knocking up, or rather would it simply sweep them away. 
A thought comes to mind while playing. By going slightly theoretical or philosophical, eventually interoperability standards such as HL7 and FHIR etc are kind of "languages", right? HL7 has its own grammar, rules, vocabulary and even dialects - every system speaks its own tone.

☤ Care 🩺 Compass 🧭 - Proof-of-Concept - Demo Games Contest Entry

Introducing Care Compass: AI-Powered Case Prioritization for Human Services

In today’s healthcare and social services landscape, caseworkers face overwhelming challenges. High caseloads, fragmented systems, and disconnected data often lead to missed opportunities to intervene early and effectively. This results in worker burnout and preventable emergency room visits, which are both costly and avoidable.

Care Compass was created to change that.

Considering new business interest in applying Generative-AI to local commercially sensitive private data and information, without exposure to public clouds. Like a match needs the energy of striking to ignite, the Tech lead new "activation energy" challenge is to reveal how investing in GPU hardware could support novel competitive capabilities. The capability can reveal the use-cases that provide new value and savings.

Sharpening this axe begins with a functional protocol for running LLMs on a local laptop.

My local Mac has an M1 processor.

I combined @Rodolfo Pscheidt https://github.com/RodolfoPscheidtJr/ollama-ai-iris with some files from @Guillaume Rongier https://openexchange.intersystems.com/package/iris-rag-demo.

My own project is https://github.com/oliverwilms/ollama-ai-iris

I can run load_data.py and it connects to IRIS (same container).

When I try to run query_data.py https://github.com/oliverwilms/ollama-ai-iris/blob/main/query_data.py , it cannot connect to ollama:

ConnectionError: Failed to connect to Ollama. Please check that Ollama is downloaded, running and accessible.

I wonder if I need to add in query_data.