welcome

Thank you for purchasing the MEAP edition of Build LLM Applications (from Scratch).

I’m excited to share this journey with you as we explore the intricacies of building search engines and Retrieval-Augmented Generation (RAG) systems—without relying on pre-built frameworks like Langchain or Llamaindex.

To get the most from this book, you should be familiar with general AI concepts and have some hands-on experience with Python. Prior knowledge of basic machine learning, and APIs will also help you dive deeper into the material and fully customize your applications.

Throughout this book, you’ll learn how to build LLM-based applications from the ground up. We’ll focus on the fundamentals of search systems, RAG solutions, and how to deeply customize each step of your AI pipelines. By the end, you’ll be able to create LLM applications tailored to your specific needs, going beyond the limitations of existing frameworks. But we don’t intend to stop there - we will also work with some advanced topics such as Fine-tuning, Semantic Caching, Knowledge Graphs and Agents.

I hope this book empowers you to unlock the full potential of LLMs and search technologies. Please feel free to share your thoughts and questions in the liveBook discussion forum—your feedback is invaluable in helping us improve the book.

Best regards,

Hamza Farooq

Founder Traversaal.ai

Adjunct Professor, UCLA & Stanford