PyData Trójmiasto #31

We are welcoming you to join 31st edition of PyData Trójmiasto meetup!

• When: 18th of June, at 18:00

• Where: Room 002, Building B, Gdańsk Science-Technology Park.

• Registration: event is free to join, just let us know you're coming by RSVP on meetup to estimate pizzas.

Agenda:
18:00 - 18:05 - Meeting boarding
18:05 - 18:10 - A few words about PyData
18:10 - 18:50 - Divide and Conquer in the LLM world - LLM agents by Sebastian Chwilczyński
18:50 - 19:35 - Bridging LLM and Databases: Lessons learned in production by Mateusz Hordyński
19:35 - Pizza & Networking

About Divide and Conquer in the LLM world
Andrew Ng said that AI agent workflows will drive massive AI progress this year, and all AI practitioners should pay attention to this trend. I'm the last one to undermine his words, so let's dive deep into agentic systems. In this presentation, we are going to explore the four most fundamental design patterns for Agent Systems: Reflection, Tools Use, Planning, and Collaboration. Along the way, we'll learn some best practices and examine recent use cases to see these principles in action.

About Sebastian
Sebastian Chwilczynski is a Machine Learning Engineer at deepsense.ai. He graduated in Artificial Intelligence from Poznań University of Technology. Recently, in his professional work, he's been mostly focused on making LLM systems more robust. Good research before the implementation is even more important than a morning coffee.

About Bridging LLM and Databases: Lessons learned in production
Prepare to dive into the exciting world of Large Language Models (LLMs) and structured data sources. In this session, we'll shed light on how to link LLMs to relational databases. We'll explore case studies and share different tried-and-tested approaches to achieve this. You'll understand the benefits, the obstacles, and what's on the horizon for integrating LLMs and structured data. Whether you're a seasoned professional in data science or just starting out, this talk has something to help you improve your skills in working with LLMs and external structured data sources.

About Mateusz
I'm a software engineer who specializes in creating big data architectures for both cloud and on-premises setups. Currently, I'm a Technical Leader at deepsense.ai, where I design generative AI applications and build data pipelines to support them. I'm also the lead maintainer of the open-source project db-ally. Outside of work, I try to live the digital nomad lifestyle, which has taught me how to work remotely from some pretty weird office setups.

We are deeply thankful to Gdańsk Science-Technology Park for hosting us. Vemco Sp. z o.o. for sponsoring tasty pizzas! And to JetBrains for the possibility to give away a few licenses for their tools - in exchange of interesting questions!;)

See you at PyData!