VIScon Workshop: Build Your Own RAG Pipeline: From Data to AI-Powered Answers in One Afternoon

This event is only available for VIScon Symposium or Hackathon participants, as well as Helpers! Please sign up for one of these events first!

Build a complete Retrieval-Augmented Generation (RAG) pipeline from scratch! Starting with raw documents and ending with an AI system that can answer natural language questions with cited sources, you will learn how the technology behind tools like ChatGPT, Perplexity, and enterprise AI search systems actually works under the hood, and build your own working version in a single workshop session.

Abstract:

Large Language Models can write poetry and answer simple questions, but ask them about something outside of their training data and they hallucinate confidently. RAG solves this by grounding LLMs in real data, and it's the core architecture behind virtually every production AI system that works with private or up-to-date information. In this hands-on workshop, you'll build a RAG pipeline step by step and understand the engineering decisions that make or break these systems.

The Complete Pipeline You'll Build:

Document ingestion and text extraction from PDFs and other file formats Text chunking with different strategies A retrieval pipeline that finds relevant document chunks for a given query An LLM-powered answer generation step that synthesizes retrieved context into cited responses

What You'll Learn:

How RAG works and why it's the dominant architecture for AI applications today Chunking strategies and why they matter more than most people think Prompt engineering for grounded, citation-backed answers How to evaluate retrieval quality and detect hallucinations Workshop Structure: We'll start with the theory: what is RAG, why does it exist, and how does it compare to fine-tuning or pure prompting? Then we'll get hands-on, building each pipeline component step by step in Python. Along the way, we'll experiment with different approaches and discuss the trade-offs.

Who Should Attend: Perfect for students and developers who are curious about how AI-powered question-answering systems actually work behind the hype. Some familiarity with Python is helpful, but we'll provide starter code and work through everything together. Whether you're exploring AI/ML, building side projects, or just want to understand the technology reshaping every industry, this workshop gives you the foundations.

Takeaways: You'll leave with a working RAG pipeline you can extend for your own projects, all code and notebooks, and a solid understanding of the architecture that powers modern AI applications.

About Me (Lukas Reichart - DeepJudge): My journey with VIS and VSETH (2017-2022) took me from student projects to co-leading the migration of VSETH's infrastructure to a cloud-native Kubernetes setup through the SIP project. Now, as a Solution Architect at DeepJudge, I work on exactly the kind of system we'll be building in this workshop, just at enterprise scale. DeepJudge is a precision AI search platform built by ex-Google search engineers that helps law firms search across millions of documents using RAG, and semantic search. I get to see every day what makes these systems work in production, and I'm excited to break it all down with you in a hands-on setting.

Additional slots might become available later on. Please use the waiting list!

The VSETH General Privacy Policy applies to this event.

Details and Prerequisites

Workshops may require items VIScon cannot provide (e.g., a Laptop) which you have to bring with you or to set up something (e.g., install software) that would otherwise take up a significant chunk of the workshop. You may also need knowledge in certain fields (e.g., how to program in a specific language). All of this information can be found in the following paragraphs, so you can decide whether you want/can participate in this workshop, or not. #####What you have to bring to the workshop:

• A Laptop

What you have to do before the workshop:

Nothing.

Knowledge requirements(/recommendations) for this workshop:

Nothing.

FAQ

Why can't I sign up for this workshop?

If you signed up for the main event after the early access deadline (8:00pm, 17th of September), you can sign up from the 20st of September. But don't worry, we will send you a reminder when the sign up opens. Early access is our way to thank early supporters!