Hi Community!

Need an introduction to Generative AI? Learning Services is excited to announce the first video in a new series about GenAI basics:

🧐 What Is Generative AI?

https://www.youtube.com/embed/zMfiV0RhrCA?utm_source=youtube&utm_medium=social&utm_campaign=zMfiV0RhrCA
[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]

I try to get a vector from calling GetEmbedding, but i failed to convert it into a vector

Here is a simplyfied sample class:

Hi All,
We invite you to join our next Meetup in Boston on June 25 5:30-7:30 pm.
>> RSVP here <<

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.

Considering new business interest in applying Generative-AI to local commercially sensitive private data and information, without exposure to public clouds. Like a match needs the energy of striking to ignite, the Tech lead new "activation energy" challenge is to reveal how investing in GPU hardware could support novel competitive capabilities. The capability can reveal the use-cases that provide new value and savings.

Sharpening this axe begins with a functional protocol for running LLMs on a local laptop.

TL;DR

This article introduces using the langchain framework supported by IRIS for implementing a Q&A chatbot, focusing on Retrieval Augmented Generation (RAG). It explores how IRIS Vector Search within langchain-iris facilitates storage, retrieval, and semantic search of data, enabling precise and up-to-date responses to user queries. Through seamless integration and processes like indexing and retrieval/generation, RAG applications powered by IRIS enable the capabilities of GenAI systems for InterSystems developers.

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]

In the previous article, we saw different modules in IRIS AI Studio and how it could help explore GenAI capabilities out of IRIS DB seamlessly, even for a non-technical stakeholder. In this article, we will deep dive into "Connectors" module, the one that enables users to seamlessly load data from local or cloud sources (AWS S3, Airtable, Azure Blob) into IRIS DB as vector embeddings, by also configuring embedding settings like model and dimensions.

Hey Community,

We have more exciting news! The new InterSystems online programming contest dedicated to Generative AI, Vector Search and Machine Learning is starting very soon!

🏆 InterSystems Vector Search, GenAI and ML Contest 🏆

Duration: April 22 - May 19, 2024

Prize pool: $14,000

Hi all,

As part of the InterSystems Solutionathon we would like to distribute a very quick survey on your thoughts on using AI-driven code documentation for ObjectScript.

https://forms.office.com/r/nSGevGpbTy

Please let us know if you have any further questions!

Hey Community,

Watch the latest video on InterSystems Developers YouTube:

⏯ Using Vector Search for Generative AI

https://www.youtube.com/embed/IapbO3j1Qmw
[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!

As an AI language model, ChatGPT is capable of performing a variety of tasks like language translation, writing songs, answering research questions, and even generating computer code. With its impressive abilities, ChatGPT has quickly become a popular tool for various applications, from chatbots to content creation.
But despite its advanced capabilities, ChatGPT is not able to access your personal data. So we need to build a custom ChatGPT AI by using LangChain Framework:

Below are the steps to build a custom ChatGPT:

• Step 1: Load the document

• Step 2: Splitting the document into chunks

• Step 3: Use Embedding against Chunks Data and convert to vectors

• Step 4: Save data to the Vector database

• Step 5: Take data (question) from the user and get the embedding

• Step 6: Connect to VectorDB and do a semantic search

• Step 7: Retrieve relevant responses based on user queries and send them to LLM(ChatGPT)

• Step 8: Get an answer from LLM and send it back to the user

For more details, please Read this article

Hi Community,

Thank you for participating in our recent mini-contest! We received many great ideas, and we hope you enjoyed the process.

The mastermind of the winning concept will receive 5,000 points, while the astute "investors" in said concept will receive 200 points each.

The Winning Concept: Senior people loneliness

Hi Community,

Round 2 of the GenAI Crowdsourcing Mini-Contest is here! Everyone can join, even if you missed Round 1. You have $5 million in fantasy funds to invest in up to 5 promising submissions.