VIS x ipt: RAG & LLM
Event start time 25.4.2024 17:00
Event end time 25.4.2024 18:30
What?
In this workshop you implement your own Retrieval Augmented Generation (RAG) solution, a pattern in which Large Language Models (LLM) are fed with custom data at inference to generate a contextually accurate output.
Where and when?
Join us for this workshop on Thursday, April 25, 2024 at 5 p.m. at the ipt Office, Löwenstrasse 28, 8001 Zürich. The official part lasts until 18:30. You are invited for Pizza, Beer and networking afterwards!
What is it about?
In this workshop you will learn
What are Large Language Models (LLMs) and how can we use the Retrieval Augmented Generation (RAG) pattern to extend the LLMs with custom knowledge?
What techniques are there for tuning an LLM (prompt engineering)?
What can be optimized in a RAG pattern (data ingestion, document chunking)?
With whom?
Philipp completed his computer science studies at ETH five years ago. After working as a research assistant he joined ipt as an IT consultant. During his work, he has successfully realized projects in the private and public cloud with a focus on machine learning applications and recently generative AI.
Diem completed her Physics Studies at ETH and did a PhD in medical physics where she gained hands-on experience with AI. Now she is an IT consultant at ipt where she helps clients in promoting the topic GenAI into their projects.
Please bring your own laptop!
Event organisers
Main event organiser Dina Weiersmüller