The introduction of InterSystems' "Vector Search" marks a paradigm shift in data processing. This cutting-edge technology employs an embedding model to transform unstructured data, such as text, into structured vectors, resulting in significantly enhanced search capabilities. Inspired by this breakthrough, we've developed a specialized search engine tailored to companies.

2 1
1 28
Announcement
· May 15
Documentation New Look

The InterSystems documentation new look is pretty awesome. The integrated pervious release documentation are single page is really useful.

Dark mode and collapse the side bar option is cool!

5 0
0 39

I have an angular UI communicating with a iris rest api. Now I need to authenticate (to federated) before accessing the UI, and for a better solution as the users are using the healthshare clinical viewer 2023, find a way to use the clinical viewer authentication / user to go to the UI.

The angular way would be to do an angular guard and have a function 'am I authenticate to federated', but I never found a function like this and how to get my username.

0 0
0 39

Hey Community,

Play the new video on InterSystems Developers YouTube:

Container Lifecycle - When is Your App Ready to Accept Work @ Global Summit 2023

https://www.youtube.com/embed/hALbMzols9o
[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]

0 0
0 39

Hi Community,

In this article, I will introduce my application iris-VectorLab along with step by step guide to performing vector operations.

IRIS-VectorLab is a web application that demonstrates the functionality of Vector Search with the help of embedded python. It leverages the functionality of the Python framework SentenceTransformers for state-of-the-art sentence embeddings.

Application Features

  • Text to Embeddings Translation.
  • VECTOR-typed Data Insertion.
  • View Vector Data
  • Perform Vector Search by using VECTOR_DOT_PRODUCT and VECTOR_COSINE functions.
  • Demonstrate the difference between normal and vector search
  • HuggingFace Text generation with the help of GPT2 LLM (Large Language Model) model and Hugging Face pipeline

0 0
0 36

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.

https://www.youtube.com/embed/bcu1gt0BDhY
[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]

0 1
0 13

I am trying to create my first call to our Epic FHIR Repository from Health Connect using Samples-FHIRStarter now that I have OAuth2.0 connection tested/working with our Epic Interconnect URL.

When I take a patient example from our Epic environment and test it through Data.BPL.PatientRecordCollector within the Namespace, I keep getting a 404 - File or directory not found

0 0
0 33

Hi Community,

In this article, I will introduce my application iris-image-vector-search.
The image vector retrieval demo uses IRIS Embedded Python and OpenAI CLIP model to convert images into 512 dimensional vector data. Through the new feature of Vector Search, VECTOR-COSINE is used to calculate similarity and display high similarity images.

2 0
1 29

Hi Community,

Here is a brief walkthrough on the capabilities of IRIS AI Studio platform. It covers one complete flow from loading data into IRIS DB as vector embeddings and retrieving information through 4 different channels (search, chat, recommender and similarity). In the latest release, added docker support for local installation and live version to explore.

https://www.youtube.com/embed/X1gzz3Qs2dw
[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]

2 0
0 18

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.

0 0
0 17

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.

1 0
0 16

Hi,

I have a spring-boot Java application which has Quartz Scheduler (spring-boot-quartz-starter) dependency, and uses IRIS DB.
There is a problem with making Quartz Scheduler work with IRIS since there is a blob field expected in two tables, but IRIS is using longvarbinary type.
Can you provide me with clues on how to resolve this?

I am using org.quartz.impl.jdbcjobstore.StdJDBCDelegate driverDelegateClass.

This is the error:
MisfireHandler: Error handling misfires: Couldn't retrieve trigger: invalid stream header: 41434544

0 0
0 13

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.

1 0
0 11

I would dearly love to avoid manually creating a SEF or XSD file to get the X12 832 (4010) schema into IRIS, but I have been hard pressed to find either downloadable resources or commercial options. The typical recommendation, edi-dev, seems to just do tooling that will help create SEF files, but no longer sells actual SEF files.

Anybody got any good resources that might have these schema files?

Thanks for any help!

Cordially,

Jonathan

0 0
0 11