GetTogether on How to host a LLM in C#

GetTogether on How to host a LLM in C#

During this session our keynote speaker Xavier Spileers will demonstrate how to download and host an LLM locally using C# and the LLamaSharp library. 

This opens up exciting possibilities, from creating your own personalized chatbot to automating the processing of natural language texts. We'll explore the practical steps involved in setting up the LLM, including model selection, resource considerations, and basic interaction. A crucial aspect of working with LLMs is crafting effective prompts. Therefore, Xavier will also touch upon strategies for efficient prompting, showing how to structure your input to get the best results from the model. 

Moreover, he will explain and demonstrate how to build a Retrieval Augmented Generation (RAG) system. This involves integrating the LLM with a vector database to ground its responses in specific knowledge or documents, leading to more accurate and contextually relevant outputs. We'll cover the fundamentals of vector databases, how to create embeddings, and how to query them efficiently to enhance the LLM's capabilities.

Our Speaker

Xavier Spileers started as a software engineer in 1999 and uses .NET as from 2003. Ever since he evolved from project manager to software architect and started his own software development company in 2007. Xavier is also a teacher of software development courses.

Location

Queaso Services ( Business District, Dendermondesteenweg 530/A te 9070 Destelbergen )

When?

Monday, 24^th of March 2025

Agenda

18u30: arrival with food and beverage 
 
19u30: presentation by Xavier Spileers on how to host a LLM in C#.
 
20u30: questions & answers 
 
21u00: peer talks at the bar while enjoying a drink

Join us for this GetTogether by registering on this page. See you soon!