Microsoft Azure Zürich User Group

IN-PERSON meetup at Digicomp

Note: This meetup takes place on the 4th floor!

Please note:

• Please do only reserve a seat, if you really plan to attend.
• Seats are not limited. No need to "block" a seat.
• If you will attend, please register quickly
• Please unregister if you cannot make it.

***

AGENDA

• 18:00 Welcome
• 18:05 Session 1: "ChatGPT Over Your Own Data" by Marco Gerber
• 19:10 Drinks, Food and Networking
• 19:40 Mini-Session: "Honey, I Shrunk the Language Model: The Case for Going Small" by Filip W.
• 19:50 Session 2: "Bringing your first LLM into Production or Beware of your Boss’s Nephew" by Christian Hidber
• 21:00 end

Session 1: ChatGPT OverYour Own Data by Marco Gerber
As the demand for intelligent chatbots grows, organizations seek ways to tailor these conversational agents to their specific needs. In this session, we explore how to create a private ChatGPT instance that leverages your own data. Whether you’re building a customer support bot, an internal knowledge base, or a specialized domain-specific assistant, understanding the architecture and data requirements is crucial.

About Marco:
Curious potato, keen on Azure and cloud technologies. Mountain climber and photography lover. Proud beer practitioner.

Blog: https://marcogerber.ch/
LinkedIn: https://www.linkedin.com/in/marcogerber/

Mini Session: "Honey, I Shrunk the Language Model: The Case for Going Small" by Filip W.

Ever wondered if size really matters when it comes to AI? In this small teaser, we’ll peek into the world of Small Language Models (SLMs), which are all about efficiency and privacy. Get a taste of how Microsoft's Phi models deliver powerful language capabilities - without the footprint of the traditional LLMs. Perfect for those ready to embrace the benefits of AI without the computational hunger of LLMs, and ideal for embedded scenarios like mobile or self-hosted applications.

About Filip: Filip is a Microsoft MVP for AI Services

Session 2: Bringing your first LLM into Production or Beware of your Boss’s Nephew by Christian Hidber
Blog posts and notebooks on «build you chatbot in 5 minutes» or «chat with your data now» are abundant. Deploying a Large Language Model (LLM) application in a production environment—and keeping it running smoothly—is a significantly more complex endeavor.
Through LLM application demos from an industrial planning software, we'll explore how to select promising applications and understand the differences between ad-hoc and production prompts. We dive hands-on into llm-as-a-judge evaluations and online-monitoring of retrieval-based solutions. The talk concludes with some of the issues you might encounter, as well as some – opinionated – recommendations.

About Christian:
Christian lives in Zurich, Switzerland and works as a consultant focusing on real-world machine learning applications. . He earned his PhD in mathematics from ETH Zurich and completed a postdoctoral fellowship at the International Computer Science Institute in Berkeley. Christian has been developing and architecting IT solutions for the last 2 decades. Currently he’s applying artificial intelligence to Geberit’s planning software ProPlanner.

https://www.linkedin.com/in/christian-hidber/

The event is, as always, free of charge and held in English.

Please reserve a seat and cancel if you cannot make it. Thank you!

This event is sponsored by Digicomp
Thanks a lot for supporting the Swiss Azure Community!