Book Image

Mastering NLP from Foundations to LLMs

By : Lior Gazit, Meysam Ghaffari
Book Image

Mastering NLP from Foundations to LLMs

By: Lior Gazit, Meysam Ghaffari

Overview of this book

Do you want to master Natural Language Processing (NLP) but don’t know where to begin? This book will give you the right head start. Written by leaders in machine learning and NLP, Mastering NLP from Foundations to LLMs provides an in-depth introduction to techniques. Starting with the mathematical foundations of machine learning (ML), you’ll gradually progress to advanced NLP applications such as large language models (LLMs) and AI applications. You’ll get to grips with linear algebra, optimization, probability, and statistics, which are essential for understanding and implementing machine learning and NLP algorithms. You’ll also explore general machine learning techniques and find out how they relate to NLP. Next, you’ll learn how to preprocess text data, explore methods for cleaning and preparing text for analysis, and understand how to do text classification. You’ll get all of this and more along with complete Python code samples. By the end of the book, the advanced topics of LLMs’ theory, design, and applications will be discussed along with the future trends in NLP, which will feature expert opinions. You’ll also get to strengthen your practical skills by working on sample real-world NLP business problems and solutions.
Table of Contents (14 chapters)

Exploring advanced system design – RAG and LangChain

Retrieval-Augmented Generation (RAG) is a development framework designed for seamless interaction with LLMs. LLMs, by virtue of their generalist nature, are capable of performing a vast array of tasks competently. However, their generality often precludes them from delivering detailed, nuanced responses to queries that necessitate specialized knowledge or in-depth expertise in a domain. For instance, if you aspire to use an LLM to address queries concerning a specific discipline, such as law or medicine, it might satisfactorily answer general queries but fail to respond accurately to those needing detailed insights or up-to-date knowledge.

RAG designs offer a comprehensive solution to the limitations typically encountered in LLM processing. In a RAG framework, the text corpus undergoes initial preprocessing, where it’s segmented into summaries or distinct chunks and then embedded within a vector space. When a query...