Retrieval-Augmented Generation
Free, in-person workshops at our Old Street campus. Work through a piece of our ML curriculum with our founders. No application required.
Overview
This workshop will give you a flavour of our new programme and covers Retrieval-Augmented Generation.
Background
RAG (Retrieval-Augmented Generation) solves a fundamental limitation of large language models: they only know what they were trained on. Fine-tuning is expensive and slow; context windows are limited. RAG offers a different approach: retrieve relevant information at query time and feed it to the model alongside the user's question.
The basic pattern is deceptively simple: chunk your documents, embed them into vectors, store them in a database, then retrieve the most relevant chunks when a user asks something. In practice, getting this to work well requires careful decisions at every step: how you chunk, what you embed, how you retrieve, and how you present context to the model.
RAG powers internal knowledge bases, customer support systems, legal research tools, and any application where an AI needs to reason over a specific corpus. It's become the default architecture for connecting language models to organisational knowledge.
During this workshop, we'll walk through the core components, build a working system, and explore the trade-offs.
What we will cover
Opening talk: RAG architecture
Build a starter RAG pipeline
Extend it with your own documents or use case
Share & discuss
Programme Q&A from 5pm
What to bring
Your laptop
Optional: a set of documents you'd like to work with
Hot-desking
You're welcome to hot desk from 9am on the day.
Access information:
Please ring the Founders and Coders bell. The space is wheelchair accessible and has a lift. Our toilets are fully accessible.
If you have any specific access needs, please let us know when you sign up and we'll do our best to help.