Hi all! Here I would like to share how we use vector search and GenAI with InterSystems technology. As an example, I'll describe BG-AppealAI project, which our company submitted to the InterSystems Vector Search, GenAI and ML Contest. BG-AppealAI application can write an appeal if you upload an insurance contract and the insurance company’s letter with a refusal to pay medical expenses. Of course, we are aware that at the moment AI has not reached such a level as to create ready-made legal documents.

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.

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

Hi Community
In this article, I will introduce my application IRIS-GenLab.
IRIS-GenLab is a generative AI Application that leverages the functionality of Flask web framework, SQLALchemy ORM, and InterSystems IRIS to demonstrate Machine Learning, LLM, NLP, Generative AI API, Google AI LLM, Flan-T5-XXL model, Flask Login and OpenAI ChatGPT use cases.

Hi Community,

InterSystems Innovation Acceleration Team invites you to take part in the GenAI Crowdsourcing Mini-Contest.

GenAI is a powerful and complex technology. Today, we invite you to become an innovator and think big about the problems it might help solve in the future.

What do you believe is important to transform with GenAI?

Your concepts could be the next big thing, setting new benchmarks in technology!

Contest Structure

     1.

In the previous article, we saw in detail about Connectors, that let user upload their file and get it converted into embeddings and store it to IRIS DB. In this article, we'll explore different retrieval options that IRIS AI Studio offers - Semantic Search, Chat, Recommender and Similarity. 

New Updates  ⛴️ 

• Added installation through Docker. Run `./build.sh` after cloning to get the application & IRIS instance running in your local
• Connect via InterSystems Extension in vsCode - Thanks to @Evgeny.

ChatIRIS Health Coach, a GPT-4 based agent that leverages the Health Belief Model (Hochbaum, Rosenstock, & Kegels, 1952) as a psychological framework to craft empathetic replies.

In the previous article, we saw different modules in IRIS AI Studio and how it could help explore GenAI capabilities out of IRIS DB seamlessly, even for a non-technical stakeholder. In this article, we will deep dive into "Connectors" module, the one that enables users to seamlessly load data from local or cloud sources (AWS S3, Airtable, Azure Blob) into IRIS DB as vector embeddings, by also configuring embedding settings like model and dimensions. 

New Updates  ⛴️ 

• Online Demo of the application is now available at https://iris-ai-studio.vercel.

Our next Developer Meetup will take place on July 26, 17:30 pm at the CIC Venture Café in Cambridge.

Join us to learn Generative AI Use Cases + Reference Architecture in Healthcare, witness the demo of LLMs in Healthcare and share your thoughts on the topic.

RSVP here

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 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:

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

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.

Hi Developers!

Here're the technology bonuses for the InterSystems Vector Search, GenAI, and ML contest 2024 that will give you extra points in the voting:

• Vector Search usage - 5
• IntegratedML usage - 3
• Embedded Python - 3
• LLM AI or LangChain usage: Chat GPT, Bard, and others - 3
• Questionnaire - 2
• Docker container usage - 2 
• ZPM Package deployment - 2
• Online Demo - 2
• Implement InterSystems Community Idea - 4
• Find a bug in Vector Search, or Integrated ML, or Embedded Python - 2
• First Article on Developer Community - 2
• Second Article On DC - 1
• First Time Contribution - 3
• Video on YouTube - 3
• Suggest a new idea - 1

See the details below.

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

Vanna.AI - Personalized AI InterSystems OMOP Agent

Along this OMOP Journey, from the OHDSI book to Achilles, you can begin to understand the power of the OMOP Common Data Model when you see the mix of well written R and SQL deriving results for large scale analytics that are shareable across organizations. I however do not have a third normal form brain and about a month ago on the Journey we employed Databricks Genie to generate sql for us utilizing InterSystems OMOP and Python interoperability.

Let's say you have Python including variable-length arguments methods. How can you call it from ObjectScript? 

def test1(*args):
  return sum(args)
  
def test2(**kwargs):
  a1 = kwargs.get("a1",None)
  a2 = kwargs.get("a2",None)
  return a1+a2

You can call this "a.py" from ObjectScript as below.  For **kwargs argument, create Dynamic Object in ObjectScript and put it into methods with <variablename>... (3 dots) format. 

    set a=##class(%SYS.Python).Import("a")
    write a.test1(1,2,3)   ;; 6
    set req={}
    set req.a1=10
    set req.a2=20
    write a.

As said in the previous article about the iris-fhir-generative-ai experiment, the project logs all events for analysis. Here we are going to discuss two types of analysis covered by analytics embedded in the project:

• Users prompts
• Execution errors

In order to extract useful data to apply analytics, we used the iknowpy library - an opensource library for Natural Language Processing based in the iKnow for IRIS Data Platform. It makes possible identifies entities (phrases) and their semantic context in natural language text in several languages.

Hi Community,

This is a detailed, candid walkthrough of the IRIS AI Studio platform. I speak out loud on my thoughts while trying different examples, some of which fail to deliver expected results -  which I believe is a need for such a platform to explore different models, configurations and limitations. This will be helpful if you're interested in how to build 'Chat with PDF' or data recommendation systems using IRIS DB and LLM models.

Hey Community!

We're happy to share our newest learning path dedicated to the essentials of GenAI, accessible on the Learning Portal via your SSO:

🤖 Getting Started with Generative AI 🤖

Here is what you can expect:

Hi developers!

This will be a very short article as in April 2025 with Lovable and other Prompt-to-UI tools it becomes possible to build the frontend with prompting. Even to the folks like me who is not familiar with modern UI techics at all.

Well, I know at least the words javascript, typescript and ReactJS, so in this very short article we will be building the ReactJS UI to InterSystems FHIR server with Lovable.ai.

Let's go!

Introduction

With the rise of Gen AI, we believe that now users should be able to access unstructured data in a much simpler fashion. Most people have many emails that they cannot often keep track of. For example, in investment/trading strategies, professionals rely on quick decisions leveraging as much information as possible. Similarly, senior employees in a startup dealing with many teams and disciplines might find it difficult to organize all the emails that they receive. These common problems can be solved using GenAI and help make their lives easier and more organized.

🌍 Inclusion & Innovation in Education 🌍
Our project reimagines learning for all students, with a focus on accessibility and interactive experiences. Built with the goal of making education engaging and inclusive, the tool is designed to support students of all abilities in learning complex material in an intuitive way.

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 = sentence_transformer

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.

Hi Community!

We're happy to share the next video in the series dedicated to Gen AI on our InterSystems Developers YouTube:

⏯ Prompt before the prompt - third step of GenAI model training

What if you could speak in a chat to check what happens in Interoperability, is there any errors, and even solve some types of issues.

With MCP server, you can connect any of your MCP Client, for instance Claude, to IRIS, and ask to check on Interoperability

Now it is possible ask your IRIS server using an AI Chat or compose other agent applications to get:

1. List the server metrics
2. Return intersystems iris server information
3. Save the global value Hello to the global name Greetings
4. Get the global value Greetings
5. Kill the global Greetings
6. List the classes on IRIS Server
7. Where is intersystems iris installed?
8. Return namespace information from the USER
9. List the CSP Applications
10. List the server files on namespace USER
11. List the jobs on namespace %SYS

To do it, get and install the new package langchain-iris-tool (https://openexchange.

Introduction

To achieve optimized AI performance, robust explainability, adaptability, and efficiency in healthcare solutions, InterSystems IRIS serves as the core foundation for a project within the x-rAI multi-agentic framework. This article provides an in-depth look at how InterSystems IRIS empowers the development of a real-time health data analytics platform, enabling advanced analytics and actionable insights. The solution leverages the strengths of InterSystems IRIS, including dynamic SQL, native vector search capabilities, distributed caching (ECP), and FHIR interoperability. This innovative approach directly aligns with the contest themes of "Using Dynamic SQL & Embedded SQL," "GenAI, Vector Search," and "FHIR, EHR," showcasing a practical application of InterSystems IRIS in a critical healthcare context.

Hey Community!

We're happy to share the next video in the "Code to Care" series on our InterSystems Developers YouTube:

⏯  Agentic AI in Action: Building a Decision-Making Loop with LLMs