Hey Community,

We're excited to invite you to the next InterSystems UKI Tech Talk webinar: 

👉AI Vector Search Technology in InterSystems IRIS

⏱ Date & Time: Thursday, September 25, 2025 10:30-11:30 UK

Speakers:
👨‍🏫 @Saurav Gupta, Data Platform Team Leader, InterSystems
👨‍🏫 @Ruby Howard, Sales Engineer, InterSystems

In the previous article, we saw how to build a customer service AI agent with smolagents and InterSystems IRIS, combining SQL, RAG with vector search, and interoperability.

In that case, we used cloud models (OpenAI) for the LLM and embeddings.

This time, we’ll take it one step further: running the same agent, but with local models thanks to Ollama.

Customer support questions span structured data (orders, products 🗃️), unstructured knowledge (docs/FAQs 📚), and live systems (shipping updates 🚚). In this post we’ll ship a compact AI agent that handles all three—using:

• 🧠 Python + smolagents to orchestrate the agent’s “brain”
• 🧰 InterSystems IRIS for SQL, Vector Search (RAG), and Interoperability (a mock shipping status API)

Test Objectives

InterSystems has been testing Vector Search since it was announced as an “experimental feature” in IRIS 2024.1. The first test cycle was aimed at identifying algorithmic inefficiencies and performance constraints during the Development/QD cycle. The next test cycle used simple vector searches for single threaded performance analysis to model reliable, scalable and performant behaviour at production database scale in IRIS, and performed a series of comparative tests of key IRIS vector search features against PostgreSQL/pgvector. The current test cycle models the expected behaviour of real-world customer deployments using complex queries that span multiple indices (vector and non-vector) and run in up to 1000 concurrent threads. These tests will be run against IRIS, PostgreSQL/pgvector, and ElasticSearch

Hey Community, 

Last week, the InterSystems team held our monthly Developer Meetup in a new venue for the first time ever! In the AWS Boston office location in the Seaport, over 71 attendees showed up to chat, network, and listen to talks from two amazing speakers. The event was a huge success; we had a packed house, tons of engagement and questions, and attendees lining up to chat with our speakers afterwards! 

Jayesh presents on Testing Frameworks for Agentic Systems to a full house

#InterSystems Demo Games entry

⏯️ Care Compass – InterSystems IRIS powered RAG AI assistant for Care Managers

Care Compass is a prototype AI assistant that helps caseworkers prioritize clients by analyzing clinical and social data. Using Retrieval Augmented Generation (RAG) and large language models, it generates narrative risk summaries, calculates dynamic risk scores, and recommends next steps. The goal is to reduce preventable ER visits and support early, informed interventions.

Presenters:
🗣 @Brad Nissenbaum, Sales Engineer, InterSystems
🗣 @Andrew Wardly, Sales Engineer, InterSystems
🗣 @Fan Ji, Solution Developer, InterSystems
🗣 @Lynn Wu, Sales Engineer, InterSystems

☤ 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.

InterSystems IRIS 2024 recently introduced the vector types. This addition empowers developers to work with vector search, enabling efficient similarity searches, clustering, and a range of other applications. In this article, we will delve into the intricacies of vector types, explore their applications, and provide practical examples to guide your implementation.

At its essence, a vector type is a structured collection of numerical values arranged in a predefined order. These values serve to represent different attributes, features, or characteristics of an object.

Hi Community,

Enjoy the new video on InterSystems Developers YouTube from our Tech Video Challenge:

⏯  Genes in DNA Sequences as vector representation using IRIS vector database

Learn how to design scalable, autonomous AI agents that combine reasoning, vector search, and tool integration using LangGraph.

Too Long; Didn't Read

• AI Agents are proactive systems that combine memory, context, and initiative to automate tasks beyond simple chatbots.
• LangGraph is a framework that enables us to build complex AI workflows, utilizing nodes (tasks) and edges (connections) with built-in state management.

Hi Community,

Enjoy the new video in a series of videos created by our Project Managers to highlight some of the interesting features of the new 2025.1 release:

⏯ RAG with built-in Vector Search in InterSystems IRIS 2025.1

You know that feeling when you get your blood test results and it all looks like Greek? That's the problem FHIRInsight is here to solve. It started with the idea that medical data shouldn't be scary or confusing – it should be something we can all use. Blood tests are incredibly common for checking our health, but let's be honest, understanding them is tough for most folks, and sometimes even for medical staff who don't specialize in lab work. FHIRInsight wants to make that whole process easier and the information more actionable.

Hi all!

I want to create an %Embedding.Config to use with an %Embedding property. I followed the documentation for %Embedding.OpenAI, and it works fine after setting sslConfig, modelName, and apiKey.

However, I need to use AzureOpenAI. While the embedding process is similar to OpenAI's, Azure requires additional connection parameters, like an endpoint. My question is: is it possible to configure these extra parameters with %Embedding.Config, and if so, how?

documentation reference

I am testing vectorsearch, while doing so I am trying to paginate my resultset for a "next page" function to give me the first, second, third 15 entries within a table. 

For this I have two embedding classes. One with a HNSW Index (vectornomicembedtextlatest), and one without (vectornomicembedtexttest).

Calling SELECT ID,PRIMKEY FROM SQLUser.vectornomicembedtexttest LIMIT 5 OFFSET 1 works fine with the first entry having the rowID of 486448. (I deleted old entries in the beginning and reused the table)

SELECT ID,PRIMKEY FROM SQLUser.

This article presents a potential solution for semantic code search in TrakCare using IRIS Vector Search.

Here's a brief overview of results from the TrakCare Semantic code search for the query: "Validation before database object save".

• 
  

  Code Embedding model 

There are numerous embedding models designed for sentences and paragraphs, but they are not ideal for code specific embeddings.

Three code-specific embedding models were evaluated: voyage-code-2, CodeBERT, GraphCodeBERT.

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.

I recently had to refresh my knowledge of the HealthShare EMPI module and since I've been tinkering with IRIS's vector storage and search functionalities for a while I just had to add 1 + 1.

For those of you who are not familiar with EMPI functionality here's a little introduction:

Enterprise Master Patient Index

In general, all EMPIs work in a very similar way, ingesting information, normalizing it and comparing it with the data already present in their system.

An experiment on how to use the LangChain framework, IRIS Vector Search, and LLMs to generate IRIS-compatible SQL from user prompts.

This article was based in this notebook. You can run it with a ready to use environment with this application in OpenExchange.

Setup

First, we need to install the necessary libraries:

!

Background

Embeddings is a new IRIS feature empowering the latest capability in AI semantic search.
This presents as a new kind of column on a table that holds vector data.
The embedding column supports search for another existing column of the same table.
As records are added or updated to the table, the supported column is passed through an AI model and the semantic signature is returned.
This signature information is stored as the vector for future search comparison.
Subsequently when search runs, a comparison of the stored signatures occurs without any further AI model processing overhead.

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 

See the Langchain IRIS Tool in action on YouTube. You can see IRIS metrics, discover classes, generate fake data, and so on. Project using Ollama, IRIS VectorDB, Streamlit and Langchain.

I just realized I never finished this serie of articles!

In today's article, we'll take a look at the production process that extracts the ICD-10 diagnoses most similar to our text, so we can select the most appropriate option from our frontend.

Looking for diagnostic similarities:

From the screen that shows the diagnostic requests received in HL7 in our application, we can search for the ICD-10 diagnoses closest to the text entered by the professional.

To speed up the search process, we stored the vectorized text of the diagnosis received at the time of capturing the HL7 message in our database.

This article shares analysis in solution cycle for the Open Exchange application TOOT ( Open Exchange application )

The hypothesis

A button on a web page can capture the users voice. IRIS integration could manipulate the recordings to extract semantic meaning that IRIS vector search can then offer for new types of AI solution opportunity.

The fun semantic meaning chosen was for musical vector search, to build new skills and knowledge along the way.

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!

With the introduction of vector data types and the Vector Search functionality in IRIS, a whole world of possibilities opens up for the development of applications and an example of these applications is the one that I recently saw published in a public contest by the Ministry of Health from Valencia in which they requested a tool to assist in ICD-10 coding using AI models.

How could we implement an application similar to the one requested? Let's see what we would need:

1. List of ICD-10 codes, which we will use as context for our RAG application to search for diagnoses within the plain texts.

Hey Community,

Enjoy the new video on InterSystems Developers YouTube:

⏯ Quick wins with InterSystems IRIS Vector DB

InterSystems Announces General Availability of InterSystems IRIS, InterSystems IRIS for Health, and HealthShare Health Connect 2025.1

The 2025.1 release of InterSystems IRIS® data platform, InterSystems IRIS^® for Health^TM, and HealthShare^® Health Connect is now Generally Available (GA). This is an Extended Maintenance (EM) release.

Hi all.

I'm trying to create an indexed table with an vector field so I can search by the vector value.
I've been investigating and found that to get the vector value based on the text (token), use a Python method like the following:

ClassMethod TokenizeData(desc As %String) As %String [ Language = python ]
{
    import iris
    # Step 2: Generate Document Embeddings
    from sentence_transformers import SentenceTransformer

    model = SentenceTransformer('/opt/irisbuild/all-MiniLM-L6-v2')

    # Generate embeddings for each document
    document_embeddings = model.

Using SQL Gateway with Python, Vector Search, and Interoperability in InterSystems Iris

Part 3 – REST and Interoperability

Now that we have finished the configuration of the SQL Gateway and we have been able to access the data from the external database via python, and we have set up our vectorized base, we can perform some queries. For this in this part of the article we will use an application developed with CSP, HTML and Javascript that will access an integration in Iris, which then performs the search for data similarity, sends it to LLM and finally returns the generated SQL. The CSP page calls an API in Iris that receives the data to be used in the query, calling the integration. For more information about REST in the Iris see the documentation available at https://docs.intersystems.com/irislatest/csp/docbook/DocBook.UI.Page.cl…

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.