Hey, community! 👋

We are a team of Stanford students applying technology to make sense of climate action. AI excites us because we know we can quickly analyze huge amounts of text.

As we require more reports on sustainability, such as responsibility reports and financial statements, it can be challenging to cut through the noise of aspirations and get to the real action: what are companies doing

That’s why we built a tool to match companies with climate actions scraped from company sustainability reports.

Hi Community,

We're pleased to invite you to the upcoming webinar in Hebrew:

👉 Hebrew Webinar: GenAI + RAG - Leveraging Intersystems IRIS as your Vector DB👈

📅 Date & time: February 26th, 3:00 PM IDT

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

Part 2 – Python and Vector Search

Since we have access to the data from our external table, we can use everything that Iris has to offer with this data. Let's, for example, read the data from our external table and generate a polynomial regression with it.

For more information on using python with Iris, see the documentation available at https://docs.intersystems.com/irislatest/csp/docbook/DocBook.UI.Page.cls?KEY=AFL_epython

Let's now consume the data from the external database to calculate a polynomial regression. To do this, we will use a python code to run a SQL that will read our MySQL table and turn it into a pandas dataframe:

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

Part 1 - SQL Gateway

Hello

In this article we will look at the use of SQL Gateway in Iris. SQL Gateway allows Iris to have access to tables from other (external) database via ODBC or JDBC. We can access Tables or Views from various databases, such as Oracle, PostgreSQL, SQL Server, MySQL and others.

You need to install the application first. If not installed, please refer to the previous article

Application demonstration

After successfully running the iris image vector search application, some data needs to be stored to support image retrieval as it is not initialized in the library.

Image storage

Firstly, drag and drop the image or click the upload icon, select the image, and click the upload button to upload and vectorize it. This process may be a bit slow.

This process involves using embedded Python to call the CLIP model and vectorize the image into 512 dimensional vector data.

Hey Community,

Enjoy the new video on InterSystems Developers YouTube:

⏯ First Vector Search on IRIS

InterSystems announces General Availability of InterSystems IRIS, InterSystems IRIS for Health, and HealthShare Health Connect 2024.3

The 2024.3 release of InterSystems IRIS^® data platform, InterSystems IRIS^® for Health, and HealthShare^® Health Connect is now Generally Available (GA).

Release Highlights

In this release, you can expect a host of exciting updates, including:

1. Much faster extension of database and WIJ files
2. Ability to resend messages from Visual Trace
3. Enhanced Rule Editor capabilities
4. Vector search enhancements
5. and more.

🌍 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.

Welcome to the third and final publication of our articles dedicated to the development of RAG applications based on LLM models. In this final article, we will see, based on our small example project, how we can find the most appropriate context for the question we want to send to our LLM model and for this we will make use of the vector search functionality included in IRIS.

Vector searches

A key element of any RAG application is the vector search mechanism, which allows you to search within a table with records of this type for those most similar to the reference vector.

In ObjectScript you have a wide collection of functions that return some value
typically:

set variable = $somefunction(param1,param2, ...)

There is nothing special about that.
But there is a set of functions that I classify as LEFT SIDED 
The specialty of them is that you can use them also on the left of the equal operator 
as a target in the SET command:

set $somefunction(param1,param2, ...) = value

The reason to raise that subject is that with IRIS

We continue with this series of articles on LLM and RAG applications and in this article we will discuss the red boxed part of the following diagram:

In the process of creating a RAG application, choosing an LLM model that is appropriate to your needs (trained in the corresponding subject, costs, speed, etc.) is as important as having a clear understanding of the context you want to provide. Let's start by defining the term to be clear about what we mean by context.

What is context?

In the business world, every second counts, and having high-performing applications is essential for streamlining our business processes. We understand the significance of crafting efficient algorithms, measurable through the big O notation.

Nevertheless, there are numerous strategies to boost the performance of systems built on the IRIS Data Platform. These strategies are equally crucial for optimizing overall efficiency.

Let's join the journey for a sneak peek into the tips for making IRIS Data Platform work better, where every little trick will help your applications shine.

1.

Motivated by personal feedback by @Edilson Eberle Carvalho  and 
an excellent presentation of @Michael Braam  related to Vector Search I'd like to share
my personal approach to Vectors.
When I started and met vectors with 256, 384, and over 1200 dimensions - I felt lost.
However my example Vector-inside-IRIS - a simplification of iris-vector-search - worked fine.
 
In order to understand the mechanics behind it, I decided to start in small steps.
Our common 3 dimensions describe our physical world quite fine.
Even the half 4th dimension (no negatives) added by Einstein is not to hard to follow.

We've recently made available a new version of InterSystems IRIS in the Vector Search Early Access Program, featuring a new Approximate Nearest Neighbor index based upon the Hierarchical Navigable Small World (HNSW) indexing algorithm. This addition allows for highly efficient, approximate nearest-neighbor searches over large vector datasets, dramatically improving query performance and scalability.

Hi, Community!

Want to dive deeper into the concepts of vector searches and embeddings? Learn from an InterSystems expert:

What Are Embeddings?

Hey Developers,

Play the new video on InterSystems Developers YouTube:

⏯ Chatbots are all the RAGe: Generative AI with InterSystems IRIS @ Global Summit 2024

Hi Community,

Play the new video on InterSystems Developers YouTube:

⏯ InterSystems IRIS Vector Search and the Python Ecosystem @ Global Summit 2024

Hi, Community!

Curious how a retrieval-augmented generation (RAG) application works? Take a look at this demonstration:

Exploring a Basic RAG Application

Hi, Community!

Are you building generative AI applications? See how a retrieval-augmented generation (RAG) architecture can help:

Exploring the Benefits of RAG

Artificial intelligence (AI) has transformative potential for driving value and insights from data. As we progress toward a world where nearly every application will be AI-driven, developers building those applications will need the right tools to create experiences from these applications. Tools like vector search are essential for enabling efficient and accurate retrieval of relevant information from massive datasets when working with large language models.

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

I received some really excellent feedback from a community member on my submission to the Python 2024 contest. I hope its okay if I repost it here:

you build a container more than 5 times the size of pure IRIS

and this takes time

container start is also slow but completes

backend is accessible as described

a production is hanging around

frontend reacts

I fail to understand what is intended to show

the explanation is meant for experts other than me

The submission is here: https://openexchange.intersystems.

In the previous article we presented the d[IA]gnosis application developed to support the coding of diagnoses in ICD-10. In this article we will see how InterSystems IRIS for Health provides us with the necessary tools for the generation of vectors from the ICD-10 code list using a pre-trained language model, its storage and the subsequent search for similarities on all these generated vectors.

This is an attempt to run a vector search demo completely in IRIS
There are no external tools and all you need is a Terminal / Console and the management portal.
Special thanks to Alvin Ryanputra as his package iris-vector-search that was the base
of inspiration and the source for test data.
My package is based on IRIS 2024.1 release and requires attention to your processor capabilities.

I attempted to write the demo in pure ObjectScript.
Only the calculation of the description_vectoris done in embedded Python
Calculation of a vector with 384 dimensions over 2247 records takes time.

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:

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

Translated from the Spanish Community Article Contest.

Following the latest programming contest on OEX I had some surprising observation.
There were almost exclusive applications based on AI in combination with pre-cooked Py modules.
But digging deeper, all examples used the same technical pieces of IRIS.

Seen from point of view of IRIS it was pretty much the same whether searching for text
or searching for images or other pattern.  It ended in almost exchangeable methods.

This reminds me my private situation at home.

Current triage systems often rely on the experience of admitting physicians. This can lead to delays in care for some patients, especially when faced with inexperienced residents or non-critical symptoms. Additionally, it can result in unnecessary hospital admissions, straining resources and increasing healthcare costs.

We focused our project on pregnant women and conducted a survey with friends of ours who work at a large hospital in São Paulo, Brazil, specifically in the area of monitoring and caring for pregnant women.

ChatIRIS Health Coach, a GPT-4 based agent that leverages the Health Belief Model as a psychological framework to craft empathetic replies. This article elaborates on the backend architecture and its components, focusing on how InterSystems IRIS supports the system's functionality.

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.