📅 Week 4: Connect AI to your data with RAG
This event is part of our seven-week AI Engineering program, where we build an end-to-end AI application step by step and present our finished projects during Demo Day in Week 7.
This week, we’ll work through the key layers of a modern AI application
Learn how to chunk documents and create embeddings.
Use a vector database such as pgvector.
Build an ingestion pipeline to embed and store documents.
Implement similarity search and hybrid search.
Learn to evaluate retrieval quality and identify failure cases.
By the end of the 7 week cycle, you should have a working AI application in your own GitHub repository and practical experience with AI pipelines, APIs, databases, retrieval, evaluation and deployment.
You are welcome to follow the shared project or apply the weekly concepts to your own project.
✨ Who is this for?
This cycle is designed for data scientists, analysts, software developers and Python users interested in moving toward AI engineering.
No previous LLM or AI engineering experience is required. However, you should already understand basic Python or be willing to complete some preparation independently.
✨ Who’s hosting?
I’m Lindsey, a senior data scientist working on AI systems, causal inference and data products.
I’ve worked on machine learning, uplift modelling, fraud detection and production LLM systems. I care about learning through building—and moving beyond AI hype toward applications that actually work.
💻 Bring: Your laptop, your project and your curiosity.
☕ Please grab a coffee or drink from the Octopus Bar to support the business and thank them for providing the space.