English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 46 Lessons (6h 38m) | 5.13 GB
Learn LangChain 1.0 Typescript with AI Agents, Tools, RAG Pipelines, Agentic RAG,, MCP Integration& LangGraph Deployment
Are you excited about building real AI applications, not just chatting with an LLM?
This beginner-friendly LangChain course is designed to take you from zero to confidently building AI Agents, RAG systems, custom tools, middleware, MCP integrations, and deployable LangGraph servers — all with hands-on clarity.
LangChain has quickly become the most powerful framework for building AI-powered applications. But with v1.0+ changes, breaking updates, new middleware patterns, and deeper concepts like RAG, MCP, embeddings, and vector stores, students often feel lost.
This course removes that confusion by teaching you every concept step-by-step with simple explanations and practical demos.
You will start by understanding AI Agents, how they think, how they invoke tools, and how they manage memory. Then you’ll build your own tools using Zod validation, pass dynamic context, and learn prompt-engineering tricks using system prompts and middleware.
Next, you’ll master RAG (Retrieval-Augmented Generation) — loading documents, splitting text, generating embeddings, creating vector stores, and performing similarity search & MMR retrieval to eliminate hallucinations.
You’ll also learn how to integrate external systems using MCP (Model Context Protocol), and finally deploy everything using LangGraph to build production-ready AI servers.
By the end of this course, you’ll be fully capable of building your own AI Agent systems — for automation, business workflows, customer support, data retrieval, internal tooling, and more.
No prior knowledge of LangChain required.
If you want to build practical, real AI systems, this is the perfect place to start.
Who this course is for:
- Backend Developers and Full-Stack Engineers
- QA Engineers, Test Automation Developers, and SDETs
- AI Enthusiasts and Prompt Engineers
- Anyone curious about the next evolution of AI tooling
Table of Contents
Introduction to LangChain Framework & Course content Overview
1 Introduction to Langchain Framework to build Intelligent AI Agents
2 Course Content overview – What you will learn
3 LangChain with Typescript – How to make best use of this course
Setting up Langchain & Invoke First Agent with responses understanding
4 Code download
5 Setting up Environments – Node, VS Code to get started with Langchain
6 Setting up Node Project with Langchain related dependencies
7 Setting up First Agent & invoke it with Langchain methods
8 Understand the Agent response messages and extract the core content
Importance of LangChain tools & Runtime config – Build AI Agents with Tool calls
9 What are LangChain tools functions – The core component in Framework
10 Understand tool function implementation – How to construct metadata
11 Analyze the Agent output to understand how Agent and tool communication
12 What is Run time Configuration and how Agents takes this config as input
13 How tool gets run time information from Config which helps for dynamic response
System Prompts, ResponseSchema & MemoryManagement – Core components of Langchain
14 What is System Prompt How it can tweak Agent behaviour at run time
15 Understand Response Schema and how we can direct Agent to generate custom resp
16 Customize the Model to setup temperature, tokens & timeout parameters
17 Langchain Memory Management – How to preserve memory in conversation AI Agent
Middleware Component Techniques – Customize AI Agent Behaviour at every Step
18 Importance of Middleware component in Langchain Framework – Uses
19 Middleware – Condition the Agent to dynamically select the Model at run time
20 Define Fall back Model for your AI Agent with ModelFallbackMiddleware
21 SummarizationMiddleware to Alert Agent for compact responses to save tokens
22 LLMToolSelector to select the model for choosing tools – Save Agent model cost
23 How you can setup Guardrails for AI Agent to filter Personal Information
Introduction to RAG Pipeline -Understand RAG Architecture with Agent Integration
24 Understand the Retrieval Augmented Architecture – its importance
25 Documents download
26 How Embedding works & Why use Embedding for content retrieval
27 Understand Retrieval Pipeline and how we can implement it in Langchain Agent
Load Documents, Split into Chunks & Build VectorStores with Embedding -Examples
28 Chunk the Documents with RecursiveTextSplitter and understand its config Props
29 Select VectorStore and load the content with Embeddding format in RAG pipeline
30 Understand how retrieval works with VectorSearch configuration props -Example
Build 2 Step RAG solution with Langchain by loading Multiple PDF’s & Word docs
31 Step RAG – Build Custom Middleware for retrieval and enable Agent with RAG
32 Load Multiple PDF’s into Vectorstore and retrieve with Langchain RAG Integration
33 Load Word docs into Vectorstore and retrieve with Langchain RAG Integration
Build Agentic RAG with MCP Server tools & Langchain Native tools – E2E Agent
34 What is Model Context Protocol Its advantages to use in AI Agent Systems
35 Setting up MCP local server into local systems for RAG Agentic Implementation
36 Integrate MCP tools into Langchain and enable AI Agents with MCP tools
37 End to End Agentic RAG Implementation with MCP tools & Langchain Tools – Example
Export Agent to LangGraph Visual Studio & LangSmith for UI Mode, Debug & Traces
38 Install & Setup LangGraph Visual Studio and expose AI Agent as Graph node
39 Integrate Langsmith & Interact with Agent in UI Mode & Debug Traceslogs
40 Final recap Summary – what did we learn from this course
41 Resume showcase points you can add after course completion
Learn TypeScript Basics
42 Comprehensive Tutorial on Javascript – Learn with examples
43 Understand the differences between TypeScript & JavaScript
44 Deep dive into TypeScript type syntaxes and their usage – 1
45 Deep dive into TypeScript type syntaxes and their usage -2
Bonus Lecture
46 Bonus Lecture
Resolve the captcha to access the links!
