Large Language Models: From Foundations to Production AI Applications — Second Edition

Large Language Models: From Foundations to Production AI Applications — Second Edition

Learn how Large Language Models work—and how to build, customize, and deploy real-world AI applications from development to production.

Large Language Models (LLMs) such as GPT, Claude, Gemini, Llama, Mistral, and DeepSeek are transforming software development, business automation, search, content generation, knowledge management, and enterprise AI. As organizations adopt Generative AI at scale, there is growing demand for professionals who understand not only how LLMs work, but also how to build, customize, deploy, secure, and operate AI-powered applications.

Updated for the Second Edition, this practical, hands-on guide provides a structured learning path from the foundations of Artificial Intelligence, Natural Language Processing, and Generative AI to Transformer architectures, modern LLMs, Retrieval-Augmented Generation (RAG), fine-tuning, and production AI systems. Rather than focusing only on theory, the book combines technical concepts with architecture diagrams, hands-on labs, code examples, and end-to-end projects that demonstrate how modern LLM applications are designed and built.

• Foundations of AI, Machine Learning, Deep Learning, NLP, and Generative AI

• How LLMs work, including tokenization, embeddings, attention, and Transformer architecture

• Encoder, decoder, BERT, GPT, and modern language-model architectures

• Major LLM families, including GPT, Claude, Gemini, Llama, Mistral, and DeepSeek

• Accessing LLMs through APIs and running local models with Ollama

• Prompt engineering, structured outputs, function calling, tool usage, and reliable LLM workflows

• Retrieval-Augmented Generation (RAG), embeddings, vector databases, semantic search, hybrid search, and re-ranking

• Fine-tuning and efficient model adaptation using LoRA, QLoRA, PEFT, adapter layers, and quantization

• Building AI chatbots, enterprise knowledge assistants, PDF applications, and content-generation systems

• LLM evaluation, hallucination detection, security, guardrails, safety, and responsible AI practices

• Production deployment with REST APIs, FastAPI, Docker, cloud platforms, and serverless architectures

• Monitoring, logging, caching, load balancing, cost optimization, GPU inference, vLLM, scalability, and high availability

• AI agents and agentic workflows

Apply what you learn by building complete end-to-end AI solutions:

AI Chatbot — Build a conversational AI application using modern LLM APIs, prompt engineering, backend integration, and deployment.

Enterprise Knowledge Assistant — Build a RAG-powered assistant using embeddings, vector search, document retrieval, and organizational knowledge.

Local AI Assistant — Build a private AI assistant using Ollama, local LLMs, and a custom knowledge base that can operate locally.

Code examples, hands-on labs, and project source code are available through a dedicated GitHub repository, allowing you to follow the implementations, experiment with the examples, and build the solutions yourself.

Master the technologies behind modern Large Language Models and start building intelligent, production-ready AI applications.