Unleashing the Power of GenAI with Edge Ecosystem Analytics and Kubernetes Orchestration
Rudraksh Karpe
Rudraksh Karpe is an LLM Engineer at ZS Associates and a Google Summer of Code contributor for the openSUSE Project. Previously, he has worked with the KDE community to enhance the environmental sustainability of KDE applications. He is also a recipient of the Shubhra Kar Linux Foundation Training (LiFT) Scholarship Program.
No video of the event yet, sorry!
The exponentially growing AI/ML and LLMs advancements bring concerns about privacy, as there is a risk of data exposure to online LLMs service providers. Setting up LLMs in-house requires a high computational cost which is a major obstacle for businesses across various sectors such as Retail, Healthcare, Finance, etc. These industries seek to leverage the power of LLMs to drive profitability in their overall business while maintaining control over their data.
In this session, we will explore the Edge Ecosystem Analytics and its transformative potential in GenAI Applications. Through seamless orchestration via Rancher managed Kubernetes which can help individuals overcome challenges in adopting and deploying cutting edge Gen-AI applications at the edge.
Key Topics:
- Overview of Large Language Models (LLMs)
- Scope for Edge Computing in AI revolution
- Benefits over privacy concerns by localization of LLMs
- Real-world Application Showcase by leveraging GenAI for Edge Ecosystem Analytics
- Integration of Retrieval Augmentation Generation (RAG) Pipeline into Rancher & K3s
- Challenges while deploying GenAI applications at the Edge
This short talk will showcase a real-world GenAI-based application, highlighting the utilization of the RAG pipeline as well as a data modeling pipeline to continually improve analytic outputs and its seamless integration with Rancher and K3s. Attendees would learn about Rancher, K3s in managing Kubernetes deployments for GenAI applications, LLMs optimizations techniques such as RAG, overview of Fine Tuning and AI Agents.
- Date:
- 2024 June 28 - 16:15
- Duration:
- 30 min
- Room:
- Saal
- Conference:
- openSUSE Conference 2024
- Language:
- Track:
- New Technologies
- Difficulty:
- Medium
- Branding Meetup: Next steps
- Start Time:
- 2024 June 28 15:30
- Room:
- Seminar Room 2
- Uyuni Community Hours
- Start Time:
- 2024 June 28 16:00
- Room:
- Seminar Room 1
- Pluggable CPU schedulers in openSUSE
- Start Time:
- 2024 June 28 16:00
- Room:
- Gallerie
- warewulf - making cluster installations fast and reliable
- Start Time:
- 2024 June 28 16:30
- Room:
- Gallerie