#Large Language Model (LLM)

I created this application considering how to convert images such as prescription forms into FHIR messages

It recognizes the text in the image through OCR technology and extracts it, which is then transformed into fhir messages through AI (LLA language model).

Finally, sending the message to the fhir server of IntereSystems can verify whether the message meets the fhir requirements. If approved, it can be viewed on the select page.

I implemented a Python Flask application for the 2024 Python Contest with a page that provides common form fields for an outgoing email such as the To and CC fields. And it lets you input a message as well as uploading text based attachments.

Then using LlamaIndex in Python, the app analyzes the content you put in and returns to you in a result box if there is anything that should stop you from sending that email.

Take a look at the Github repo here.

Hi Members,

Watch this video to learn a new innovative way to use a large language model, such as ChatGPT, to automatically categorize Patient Portal messages to serve patients better:

⏯ Triage Patient Portal Messages Using ChatGPT @ Global Summit 2023

https://www.youtube.com/embed/D0V09aGZK1E
[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]

Hi Community,

Play the new video on InterSystems Developers YouTube:

⏯ Using LLMs with InterSystems IRIS Interoperability Productions @ Global Summit 2024

https://www.youtube.com/embed/IQ9r0OWYSZ8
[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]

Hey Community,

Watch the new video on InterSystems Developers YouTube:

⏯ Securing AI Implementations - Moving from Experimentation to Production @ Global Summit 2024

https://www.youtube.com/embed/HZn4jazdowY
[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]

🌍 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.

💡 What It Does
This educational app transforms lesson presentations into interactive study sessions:

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.

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.

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.

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.

Prompt

Firstly, we need to understand what prompt words are and what their functions are.

Prompt Engineering

Hint word engineering is a method specifically designed for optimizing language models.
Its goal is to guide these models to generate more accurate and targeted output text by designing and adjusting the input prompt words.

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.