Agentic AI with LangGraph by Aravind choudhary

Agentic AI with LangGraph is a practical and comprehensive guide to building intelligent AI agents and autonomous workflows using LangGraph, LangChain, Generative AI, and Large Language Models (LLMs). The book explains how AI agents can reason about tasks, make decisions, plan actions, use external tools, maintain state and memory, interact with APIs and databases, and complete multi-step tasks. You will learn how LangGraph provides a powerful framework for designing stateful, controllable, and flexible agentic workflows. Starting with the fundamentals of Generative AI and LLMs, the book gradually progresses to prompt engineering, RAG, embeddings, vector databases, LangChain, LangGraph, tool calling, human-in-the-loop systems, and multi-agent architectures. Through practical examples and real-world projects, you will learn how to design and develop AI agents for research, data analysis, document processing, customer support, coding, automation, and other real-world applications. What You Will Learn Fundamentals of Artificial Intelligence and Generative AI Generative AI vs. Agentic AI Large Language Models (LLMs) Transformer architecture Tokens, context windows, and model parameters Prompt Engineering Zero-shot, one-shot, and few-shot prompting Structured output and prompt templates AI agent fundamentals and architecture Components of an AI agent LLM as a reasoning engine Planning and decision making Task decomposition Agent memory and state Tool usage and tool calling Function calling Building custom AI tools Integrating APIs, databases, and web search Retrieval-Augmented Generation (RAG) Document processing and text splitting Embeddings and vector databases Semantic search and retrievers LangChain fundamentals LangChain models and chat models Prompt templates and chains Runnables and workflows LangChain agents and tools Introduction to LangGraph LangGraph architecture Graphs, nodes, and edges State management Conditional routing Loops and iterative workflows ToolNode and tool execution Stateful AI agents Human-in-the-loop workflows Agent supervision and control Error handling and recovery Agent evaluation and monitoring LangSmith integration Multi-agent systems Supervisor and worker agent architectures Agent communication and collaboration Autonomous AI workflows External tool and API integration Hugging Face and LLM API integration Hallucination reduction Prompt injection and AI security Tool permissions and access control Cost and performance optimization Deployment of AI agent applications Real-World Projects AI Chatbot Agent LangGraph Research Assistant RAG-Based AI Agent PDF Document Analysis Agent Web Search Research Agent AI Data Analysis Agent Database Query Agent Customer Support Agent Coding Assistant Agent Human-in-the-Loop AI Agent Multi-Agent Research System Supervisor-Worker Multi-Agent System Intelligent Document Processing Agent Autonomous Task Automation Agent AI Agent with External Tools and APIs