Part 2: AI Agents and Retrieval of Knowledge
This part focuses on extending the capabilities of LLMs by enabling them to access, retrieve, and reason over external sources of knowledge. It begins with the creation of AI agents that can interact with the web, retrieve live information, and execute tasks beyond simple question answering. The following chapters explore retrieval-augmented generation (RAG), starting from basic pipelines and advancing toward more modular and scalable systems that reduce hallucinations and improve factual accuracy. The use of structured knowledge through knowledge graphs (GraphRAG) is then introduced as a powerful method to represent and reason over information. Finally, this part discusses how reinforcement learning can be used to align agent behavior and improve decision-making through interaction with dynamic environments. These chapters collectively show how to build agents that are not only language-capable but also context-aware, goal-driven, and...
