Search

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

All we need is a Vector DB. Lucky for you, this is one of IRIS's newest features.

Hi Community, Let's meet at the online meetup with the winners of the Vector Search, GenAI and ML Contest.

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.

Vector databases are kind of a part of it, and already many different realizations for the support in the world outside of IRIS. Why Vector?

Vector Search - 4 points Starting from 2024.1 release InterSystems IRIS contains a new technology vector search that allows to build vectors over InterSystems IRIS data and perform

But this example of performing vector operations through a lighter model seems exciting.

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).

🚀 Vote for this application in Vector Search, GenAI and ML contest, if you find it promising!

🚀 Vote for this application in Vector Search, GenAI and ML contest, if you find it promising! Feel free to share any feedback or inputs you may have. Thank you.

In this video, @Patrick.Sulin7198, Lead Solutions Developer, gives an approachable introduction to: The origins and nature of vector embeddings How vector embeddings are created

As you can see, we're using the sentence_transformer library to generate the vector with the downloaded model.

.) = value The reason to raise that subject is that with IRIS 2024.1 there is after may years a "new kid on this block" $VECTOR() Assigns, returns, and deletes vector data at

The server converts the question “Who is the villain in this play” into a numeric vector using the same text-to-vector model that generated the vector embeddings for King Lear, and

We have great examples of this in this community, such as IRIS Vector Search (https://openexchange.intersystems.com/package/iris-vector-search) and IRIS AI Studio (https://openexchange.intersystems.com