BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CFP.DEV//CFP.DEV shortcodes//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Voxxed Days Zurich
X-WR-RELCALID:c426493a-54d4-472b-b975-6f3aaa7163fa
X-WR-TIMEZONE:Europe/Zurich
BEGIN:VEVENT
UID:cfp-1151-14320@cfp.dev
DTSTAMP:20260920T140342Z
SEQUENCE:0
STATUS:CONFIRMED
DTSTART:20250325T140000Z
DTEND:20250325T144500Z
SUMMARY:Agentic AI with Quarkus\, LangChain4j and vLLM
DESCRIPTION:Although there is no universally agreed definition of what an A
 I agent is\, in practice several patterns are emerging that demonstrate ho
 w to coordinate and combine the capabilities of multiple AI services\, in 
 order to create AI-based systems that can accomplish more complex tasks.Th
 ese Agentic Systems architectures can be grouped in 2 main categories: wor
 kflows\, where LLMs and tools are orchestrated through predefined code pat
 hs\, and agents\, where LLMs dynamically direct their own processes and to
 ol usage\, maintaining control over how they execute tasks.Moreover the se
 curity and safety of Agentic Systems architectures is one of the biggest c
 hallenges for the adoption in mission critical scenarios. The possibility 
 to serve the model on premise and the introduction of guardrailing techniq
 ues are key enablers.The goal of this talk is giving a theoretical overvie
 w of Agentic AI in general and these patterns in particular\, discussing t
 heir range of applicability and showing with practical examples how they c
 an be easily implemented with Quarkus and its LangChain4j extension on pre
 mise using vLLM and Kubernetes.\nSpeakers: Mario Fusco\, Daniele Zonca\nTr
 ack: Data & AI
URL:https://vdz25.voxxeddays.ch/talk/agentic-ai-with-quarkus-langchain4j-an
 d-vllm/
LOCATION:Room 3\nARENA Cinemas\, Sihlcity\nZürich\, Switzerland
CATEGORIES:Data & AI
END:VEVENT
END:VCALENDAR