Date: 27 January 2025, 15:00 – 18:00 CET
Location: Bistro Campus Kitchen One (HPI), Berlin
Format: In-person event (Hands-on Workshop)
What’s it about?
A practical introduction to Retrieval-Augmented-Generation (RAG) – systems that intelligently extract information from your own documents without sharing data with third parties. In the workshop, you will set up a local RAG system on your laptop and understand the fundamental components: large language models (LLM), embeddings and vector databases.
You will work with real components: local LLM (vLLM), vector database (Qdrant), various embedding models and semantic search techniques. Objective: practical knowledge for building secure knowledge systems for internal databases, policies or documentation.
Practical Content
Installation of a complete minimal RAG implementation with local LLM, vector database and sample documents. You will learn about semantic vectors (Cosine Similarity), open-source models and the core logic of RAG systems.
Requirements
Python, GitHub and Docker proficiency, or attendance at the Getting-Started Guide or “Getting Started with Your Own AI Application” workshop.
Registration
The event is free of charge. Registration via Eventbrite is required – places are limited.
