[228][ENG] Wrocław Jug x Javeloper - Tomasz Rumak && Marcin Łapaj
Details
Po wakacyjnej przerwie zapraszamy na współorganizowane wydarzenie Wrocław JUG + Javeloper Meetup Wrocław, które odbędzie się już 29 października 2025 roku, w Sztuka na Miejscu przy ul. Łaciarska 4 we Wrocławiu.
BARDZO WAŻNE --- \/
Aby uczestniczyć w wydarzeniu trzeba wykonać pare dodatkowych kliknięć i zarejestrować się również na Evenea.
O tu: https://app.evenea.pl/event/wjugjaveloper/
Potrzebuje tego od nas nasz sponsor.
Agenda:
17:30 - 18:00 Rejestracja uczestników, sprawdzenie biletów
18:00 - 18:15 Otwarcie wydarzenia i przywitanie uczestników
18:15 - 19:00 State of AI - Tomasz Rumak [ENG]
19:00 - 19:10 Przerwa
19:10 - 19:55 From words to wisdom: How LLMs and vector databases revolutionize data understanding - Marcin Łapaj [ENG]
20:00 Networking przy napojach i cateringu
1. Temat: State of AI
Abstract:
AI is shaping workflows today not tomorrow. In this session, Tomasz Rumak will explore the current state of AI, common patterns, and practical tools that make AI useful in real projects and everyday tasks.
Język: ENG
Prelegent: Tomasz Rumak
Country Leaf of Agency Trading IT at UBS Poland, previously Engineering Manager at Amina Bank AG. Experienced in building high-performance trading platforms for UBS, Credit Suisse, and Amina AG. AI tinkerer exploring practical applications in engineering, personal projects, and everyday life.
2. Temat: From words to wisdom: How LLMs and vector databases revolutionize data understanding
Abstract:
In this session, we will delve into the dynamic relationship between large language models (LLMs) and vector databases. LLMs, like ChatGPT, have the ability to generate human-like text and respond intelligently to questions. But how do these models understand and maintain context?
The key lies in vectorization. Text is transformed into high-dimensional mathematical representations vectors that capture semantic meaning beyond individual words. These vectors allow LLMs to efficiently store, compare, and retrieve information. By utilizing vector databases,
we can perform fast similarity searches, enabling AI systems to find the most relevant information, even when it isn't an exact match to the input. This capability is crucial for tasks such as contextual search, recommendation systems, and natural language understanding. During the session using Kotlin and LangChain4j, I will demonstrate how to convert text into vectors, store them in a database, and retrieve relevant information in real-time.
Język: ENG
Prelegent: Marcin Łapaj
An adult programmer and enthusiast of the craft approach to coding. For 18 years, he's been writing code of varying quality. He has journeyed from developer to manager and back again. Personally, he's passionate about cycling and travel.