Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

LangGraph Mastery: Develop LLM Agents with LangGraph

Name: LangGraph Mastery: Develop LLM Agents with LangGraph
Rating: 4.4 (702 reviews)

Master the Power of LLM Agents with LangChain and LangGraph: Create AI Workflows, Automate Tasks and Transform Your Apps

Created byAndrei Dumitrescu, Crystal Mind Academy

Last updated 5/2026

English

What you'll learn

How to create ReAct agents from scratch.
Gain a good understanding of LangGraph concepts and core components.
Implement advanced agents.
Dive deep into nodes, edges, and conditional edges.
Learn about Tavily AI and agentic search.
Understand LLM patterns such as reflection and reflexion.
Explore LangSmith and learn how to debug and trace LLM applications with it.
Learn about flow engineering.
This will be a learning-by-doing experience. Together, we'll build agentic LLM apps step-by-step, line-by-line.
Create a Knowledge Base for RAG from Scratch
Projects: 1. Create a ReAct agent from scratch 2. Develop a ChatBot app using LangGraph 3. Build a Tweet generator using reflection 4. Create an essay writer.
Master Project 5: Build a Research Agent with LangGraph, GPT-4o, RAG, Pinecone, ArXiv, and Google SerpAPI
Learn how to build a complex agentic LLM app step by step.

Course content

9 sections • 74 lectures • 5h 25m total length

Course Prerequisites2:38
Join Our Online Community!0:25
Course Resources0:30

Introduction to Agents and ReAct4:18
Develop a basic agent from scratch using the react pattern, where the LLM reasons, acts in an environment, and iterates with observations until it completes.
Creating the Agent Class2:41
Creating the ReAct Prompt2:30
Creating the Tools2:41
Testing the Agent6:06
Automating the Agent6:59
Automate the agent by looping prompts, parsing actions with a regex from the LLM response, and executing tool functions until a final answer.
Project Source Code0:03

LangGraph Concepts and Core Components5:40
Building a ChatBot5:30
Build a simple chatbot in LangGraph using line graph by defining a state graph with messages and an annotated node that appends responses, then compile and run the graph.
Visualizing the Graph2:15
Running the ChatBot1:33
Tavily AI8:29
Enhancing the ChatBot with Tools8:20
Adding Memory to the ChatBot7:06
Project Source Code0:03

Intro to Reflection2:12
Generate4:15
Develop an lm agentic app with a line graph to generate and refine a tweet on a subject through generate, reflect, give feedback, and refine, then post on X.
Reflect and Repeat2:33
Apply the reflection technique to generate, critique, and improve a tweet via a reflect chain that acts as a critic, repeating steps to refine the final output.
Define the Graph - Part 13:44
Connect the graph by defining nodes, edges, and an end node, build a message graph with generate and reflect nodes, and iteratively refine tweets from a stateful message history.
Define the Graph - Part 22:49
Running the App3:54
Demonstrates building an app workflow with a generation and reflection chain, using a line graph to iterate revisions and finalize a tweet about FIFA World Cup 26.
Project Source Code0:03

Project Overview1:45
Defining the AgentState and the Prompts7:37
Implementing the Agents and the Nodes9:38
Develop the agents and nodes for an llm app by building a planning node, research plan node, draft generation, and reflection, then refine with critique and further research.
Defining the Conditional Edge1:26
Defining the Graph4:24
Running the Agentic App4:06
Tracing the App with LangSmith2:50
Project Source Code0:03

Quick Note2:14
Providing an Overview of the Application3:34
Extracting Data from ArXiv into a Pandas DataFrame and Saving it as JSON12:45
Downloading the Research Papers (PDFs)4:52
Download pdf files from the data frame's urls, save them locally, and record their names; then split, embed, and upload the chunks to pinecone for retrieval augmented generation.
Loading and Splitting PDF Files into Chunks, Expanding the DataFrame9:54
Load PDFs, split into 512-character chunks with a 64-character overlap, embed the chunks, and expand the data frame with chunk metadata for efficient retrieval and generation in a vector store.
Building a Knowledge Base for the RAG System Using Embeddings5:36
Creating a Pinecone Index7:19
Set up Pinecone, a managed vector database, to store and query embeddings with cosine similarity for semantic search and recommendations, using an index on AWS US East 1.
Populating the Knowledge Base and Uploading it to Pinecone5:03
Developing Custom Tools5:12
Implementing the ArXiv Fetch Tool8:00
Integrating Google SerpAPI for Web Search3:27
Implementing Web Search Tools with Google SerpAPI4:25
Implement a web search tool with Google Serp API, securely handling the API key from environment variables and returning up to five organic results.
Creating RAG Tools for Retrieval-Augmented Generation6:19
Implementing the Final Answer Generation Tool2:16
Initializing the "Oracle" LLM11:03
Explore how the oracle LLM acts as a graph decision maker, selecting tools such as archives or web search, using a scratchpad to guide final answers.
Testing the Oracle and the Tools3:33
Test the oracle-driven LangGraph workflow by passing inputs, embedding arXiv queries, indexing with pinecone, and validating tool choices (web search, fetch archive) via scratchpad and system rules.
Building a Decision-Making Pipeline8:33
Defining the Agent State3:25
Defining the Graph for Decision-Making6:35
Generating Reports4:25
Develop and execute an agent-driven workflow using a state graph to select tools, collect outputs, and generate a formatted final report for a research topic.
Building a Final Research Report5:20
Concluding the Project6:21
Project Source Code0:03

README0:24
Intro to Object Oriented Programming (OOP)5:45
OOP Demonstration: The Turtle12:48
Defining Classes and Objects3:30
Define a class with the class keyword and a Pascal-case name, using indentation and a pass statement. Create an instance and access its docstring via dot notation and __doc__.
The __init__ Method7:45
Learn how the __init__ method serves as the class constructor, automatically invoked when creating a new instance, and how to use self to assign attributes like name and year.
The __del__ Method2:19
Instance Attributes and Class Attributes6:06
Magic Methods9:09
TypedDict: Type Hints for Dictionaries with a Fixed Set of Keys - Part 16:24
Typed dicts in Python 3.8 enable static type checking for dictionaries with fixed keys, improving readability, maintainability, and reliability through defined key types and type hints.
TypedDict: Type Hints for Dictionaries with a Fixed Set of Keys - Part 24:23
Python OOP Cheat Sheet0:11

Requirements

This course is not for beginners. Good knowledge of Python and LangChain is required.
Proficiency in Python and LangChain, including knowledge of flow control, data structures, functions, type annotations, OOP, environment variable management, OpenAI ChatCompletions API, Prompt Templates, Chains, and Output Parsers.

Description

Welcome to this brand new course on LangGraph, which allows us to build agentic LLM applications. Unleash the Full Potential of AI with LangGraph & LangChain!

By the end of this course, you will be equipped with the skills to seamlessly integrate LLM agents into your applications, opening up new possibilities and horizons.

We are witnessing a rapid ascent in AI capabilities, with groundbreaking advancements occurring annually. This swift progress has the potential to significantly reshape our world in the coming years.

Three pivotal advancements are poised to make a profound impact: Infinite Context Windows, Text to Action, and Agents.

Agents: The New Frontier in AI

Agents are autonomous intelligent entities designed to perform tasks, process information, and interact within a language-based framework. These agents are significantly expanding the potential of AI across various domains.

Agentic AI is revolutionizing industries, offering enhanced applications in fields such as legal document analysis, medical diagnostics, and software development. Imagine an army of skilled programmers working around the clock to develop software solutions for you.

In this course, we will delve into LangGraph, an extension of LangChain specifically designed for agent and multi-agent workflows. LangGraph enables highly customizable and controllable agent flows, ideal for complex scenarios.

We will also explore LangSmith, a platform for tracing and debugging your production-grade LLM applications.

What You'll Learn:

Master LangGraph: Explore nodes, edges, and state management for advanced agent workflows.
LangChain Integration: Connect LLMs to real-world tools for powerful multi-agent applications.
Develop Autonomous Agents: Build agents that can observe, reflect, and improve with memory and tool observation.
RAG & Embeddings: Implement Retrieval-Augmented Generation (RAG) with Pinecone for enhanced search capabilities.
Debug & Scale: Use LangSmith to debug and trace production-grade AI applications.

Why Enroll in This Course?

Cutting-Edge Skills: You'll master LangGraph and LangChain, tools at the forefront of AI development.
Practical Applications: Build real-world AI solutions that can be integrated into businesses, research, and more.
Step-by-Step Guidance: Whether you're experienced in AI or just getting started, our comprehensive tutorials will guide you through each project.
Join the AI Revolution: The demand for AI professionals is skyrocketing—position yourself at the forefront by mastering these critical technologies.

Hands-On Projects:

ReAct Agent from Scratch: Build a fully functional agent with LangGraph.
Custom Chatbot: Develop an intelligent chatbot powered by LangChain.
Content Generation Tools: Create AI tools that generate essays, tweets, and more using LangGraph’s reflection pattern.
Master Project: Build a robust research agent integrating GPT-4, Pinecone, ArXiv, and Google SerpAPI.

Ready to build AI agents that can transform industries? Enroll now and take your AI development skills to the next level with LangGraph!

Looking forward to seeing you in the course!

Who this course is for:

Software Developers aiming to build Generative AI applications using LangChain and LangGraph.
Enthusiasts who want to explore the new frontier of LLM agents.

LangGraph Mastery: Develop LLM Agents with LangGraph

What you'll learn

Explore related topics

Course content

Getting Started3 lectures • 4min

Building a Simple ReAct Agent from Scratch7 lectures • 25min

Building with LangGraph8 lectures • 39min

Reflection - Tweet Generator7 lectures • 20min

LangSmith: Platform for Building Production-grade LLM Apps5 lectures • 16min

Reflexion - Essay Writer8 lectures • 32min

Master Project: Build a Research Agent with LangGraph, GPT-4o, RAG,ArXiv,SerpAPI23 lectures • 2hr 10min

[Appendix]: Object Oriented Programming in Python11 lectures • 59min

BONUS SECTION2 lectures • 2min

Requirements

Description

Who this course is for: