Advanced Retrieval-Augmented Generation (RAG) for Large Language Models Archives - Page 2 of 2 - FutureLearn

FutureLearn uses cookies to enhance your experience of the website. All but strictly necessary cookies are currently disabled for this browser. Turn on JavaScript to exercise your cookie preferences for all non-essential cookies. You can read FutureLearn's Cookie policy here.

Embedding Lesson Summary and Reflection

Summary of Lesson on Text Embedding: Key Terms and Topics: Embedding Basics: Large language models (LLMs) and Retrieval-Augmented Generation (RAG) systems heavily use embeddings to encode text inputs. Embeddings convert …

Embedding – Hands-on Lab – Summary

Embedding – Hands-on Lab – Context Embedding

Embedding – Hands-on Lab – Sentence Encoding

Embedding – Hands-on Lab – Vocabulary

Embedding – Hands-on Lab – Tokenization

Embedding Introduction

Simple RAG – Homework Exercise

Homework Instructions: In this exercise, you will implement a simple RAG system to find and recommend old movies based on a dataset with 5,000 movies. You will practice loading a …

Lesson Summary and Reflection

Summary of Lesson on Simple RAG: In the lesson on Simple Retrieval-Augmented Generation (RAG), you traversed the foundational aspects of developing RAG applications. The core flow involved retrieval, augmentation, and …

Issues with Simple RAG

Simple RAG Hands-on Lab

Simple RAG Introduction

Hands-on labs and homework exercises instructions

Jupyter Notebooks Execution The course includes a set of Jupyter notebooks for hands-on labs and homework exercises. Prerequisites The labs and exercises use APIs from OpenAI, Anthropic, and Cohere. You …

Course Introduction

1
2