Nyala Labs Bonfire - RAG: Powering LLMs with Private Data

​This 2-hour, heads-down coding session covers the full Retrieval-Augmented Generation (RAG) pipeline. You will write Python code to bridge the gap between static vector databases and live LLM reasoning. We will build a system that retrieves relevant context, injects it into prompt templates, and generates grounded, factual answers. Participants will walk away with a functional “Chat with your docs” engine - the core architecture for any production-level AI knowledge base or B2B research tool.

​

​About the speaker:

​Abel Chin is a current ASEAN Undergraduate Scholar at Singapore Management University majoring in Computer Science. He is also the Founder and current President of Nyala Labs. In his spare time, he is doing a VC-backed startup in accounting compliance.