Real time Data Apps and LLMs

We are looking forward to welcoming everyone to the next Big Data Applications meetup on Thursday, Sep 28th, in Santa Clara!

We are grateful for DataStax for hosting this gathering.

Venue

DataStax Office

2625 Augustine Drive, Suite 125

Santa Clara, CA 95054, USA

Agenda

06:00 - 06:30 pm- Registration and networking

06:30 - 06:55 pm- Talk 1: Build Generative AI applications with Real-time events

07:00 - 07:25 pm- Talk 2: Modernize Oracle with Cassandra using Change Data Capture

07:30 - 07:55 pm- Talk 3: Building LLM Apps with Streamlit

08:00 - 08:30 pm- Socializing and networking

Talk 1

Speaker: Ryan Michael, VP of Engineering at Kaskada

Beyond Q&A: Using LLM’s for real-time, personalized notifications

Are you tired of seeing Gen AI demos of yet another chat bot? Are you looking for the interesting applications of this technology that’s supposed to change everything?
Generative AI can do more than answer questions - it can understand what’s happening in the world in real-time, and use that understanding to creatively make our lives better.
But to do so, Generative AI apps need access to real-time information, which has traditionally been difficult to deal with. Connecting AI to real-time data is the problem that the OSS Kakada project (which, in full disclosure, I co-created) aims to solve.
To demonstrate how the right tools make this type of application easy, we built BeepGPT - an AI bot that reads your Slack so you don’t have to. In this presentation we’ll walk you through our process and share some of the lessons we learned along the way.

Talk 2

Speaker: Rajkumar Sen (CTO, Arcion Labs)

Modernize Oracle with Cassandra using Change Data Capture

For generations, enterprises have entrusted Oracle database products, including the renowned Exadata, to store and manage critical transactional and analytical data. Now, it's time to modernize your data infrastructure and unlock the full potential of real-time applications for data and machine learning use cases. Discover Arcion, a cutting-edge, real-time, in-memory CDC platform designed for unrivaled scalability, low latency, and guaranteed consistency. In this talk, Raj will walk through the challenges of setting up real-time change data capture, the key elements to be considered when selecting a CDC solution, and a live demo of using Arcion to replicate data from Oracle to Cassandra.

Talk 3

Speaker: Atif Tahir (MLOps community member)

Building LLM Apps with Streamlit

Streamlit turns data scripts into shareable web apps in minutes. All in pure Python. No front‑end experience required. MLOps community organized a LLM stack hackathon and Atif's team was in the top three for the Q&A bots category. In this talk, it will be shared how can one build an LLM app in a day using community slack and MLOps data. ​MLOps.community is a 17K+ member community, primarily online in a thriving slack channel and through virtual and in-person events. There is a lot of tribal knowledge in the community where experts answer questions from other MLOps practitioners both in Slack as well as via in-person meetups and online videos. The LLM powered app answers MLOps and other ML/DS/AI questions that community members may have using the historical knowledge in Slack, videos, etc.