Day 3 — Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) is the process of optimising the output of a large language model, so it references a more grounded knowledge base before generating a response.

Offline, I also got to work on a RAG system using LangChain that allows me to upload a PDF and make searches and ask questions based on what is in that PDF. The LLM offered the intelligence to relate my questions to what was in the book, and at the same time give the correct outputs to my questions. The code is on my GitHub.

See you on day 4.