Teach on Udemy

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

Learn More

Your cart is empty.

Keep shopping

LangChain Framework for Beginners – Build AI Systems + RAG

Name: LangChain Framework for Beginners – Build AI Systems + RAG
Rating: 4.6 (161 reviews)

Learn LangChain 1.0 Typescript with AI Agents, Tools, RAG Pipelines, Agentic RAG, MCP Integration, LangGraph Deployment

Created byRahul Shetty Academy - 1.2 Million QA Learners

Last updated 1/2026

English

What you'll learn

Build AI Agents with LangChain using tools, memory, prompts, and multi-model configurations.
Create custom tools with Zod validation and enable LLMs to choose and execute tools intelligently.
Implement dynamic system prompts, middleware, and context injection for accurate agent responses.
Design complete RAG pipelines using embeddings, vector stores, similarity search, and document loaders.
Integrate LangChain Agents with external APIs, databases, and MCP servers for real-world automation.
Deploy production-ready LangGraph agent servers with environment setup, tracing, and safety guardrails.

Course content

12 sections • 46 lectures • 6h 38m total length

Introduction to Langchain Framework to build Intelligent AI Agents9:57
Course Content overview - What you will learn?0:42
LangChain with Typescript - How to make best use of this course2:22
Explore how to use the long chain framework with TypeScript to build AI applications and agentic rag systems, with prior basics in JavaScript or TypeScript and a fundamentals section.
Section-1 Quiz

Code download0:03
Setting up Environments - Node, VS Code to get started with Langchain8:02
Set up a TypeScript workspace by installing node and Visual Studio Code, then install Lang Chain core and Lang Graph packages and configure your path for macOS and Windows.
Setting up Node Project with Langchain related dependencies7:52
Set up a new node project for LangChain with TypeScript by creating a folder, initializing npm, and installing LangChain core, TypeScript, and jot, plus optional OpenAI or cloud models.
Setting up First Agent & invoke it with Langchain methods7:54
Set up a LangChain agent in a TypeScript file and configure a model (anthropic or OpenAI). Invoke it with a user prompt in a messages array, then run with npx.
Understand the Agent response messages and extract the core content7:00
Section-2 Quiz

What are LangChain tools functions? - The core component in Framework8:15
Understand tool function implementation - How to construct metadata11:49
Analyze the Agent output to understand how Agent and tool communication7:44
Analyze how an agent uses internal tools to fetch weather and time, orchestrating tool calls and interpreting outputs to answer user queries.
What is Run time Configuration and how Agents takes this config as input13:42
How tool gets run time information from Config which helps for dynamic response8:55
Section-3 Quiz

What is System Prompt? How it can tweak Agent behaviour at run time8:16
Understand Response Schema and how we can direct Agent to generate custom resp7:12
Define a custom response schema with jarred to produce structured outputs. Learn to adjust agent behavior using qa config and system prompts for humanized, weather-like responses.
Customize the Model to setup temperature, tokens & timeout parameters3:46
Langchain Memory Management - How to preserve memory in conversation AI Agent12:13
Section-4 Quiz

Importance of Middleware component in Langchain Framework - Uses14:45
Middleware - Condition the Agent to dynamically select the Model at run time12:48
Define Fall back Model for your AI Agent with ModelFallbackMiddleware10:25
Summarization Middleware to Alert Agent for compact responses to save tokens9:31
LLMToolSelector to select the model for choosing tools - Save Agent model cost5:47
How you can setup Guardrails for AI Agent to filter Personal Information12:45
Section-5 Quiz

Understand the Retrieval Augmented Architecture - its importance5:29
Documents download0:03
How Embedding works & Why use Embedding for content retrieval11:47
Explore the rag architecture, where embedding models power semantic search over a vector store to retrieve top documents, augment a query, and generate answers in an end-to-end pipeline.
Understand Retrieval Pipeline and how we can implement it in Langchain Agent12:49
Section-6 Quiz

Chunk the Documents with RecursiveTextSplitter and understand its config Props12:00
Select VectorStore and load the content with Embeddding format in RAG pipeline10:32
Learn to choose a vector store and load embeddings in a rag pipeline with LangChain, store documents, perform semantic search, and retrieve context for an llm.
Understand how retrieval works with VectorSearch configuration props -Example9:08
Configure vector search retrieval with similarity or MMR and fetch k for top documents. Tune retriever parameters and monitor retrieval context to implement two-step rag and agent rag.
Section-7 Quiz

2 Step RAG - Build Custom Middleware for retrieval and enable Agent with RAG19:17
Build a custom middleware in LangChain to enable retrieval augmented generation. Customize the dynamic system prompt to pull vector store context and retrieved documents before invoking the agent.
Load Multiple PDF's into Vectorstore and retrieve with Langchain RAG Integration14:47
learn how to load multiple pdf documents into a vector store and perform retrieval with LangChain rag integration, enabling multi-document queries with scalable embedding and retrieval.
Load Word docs into Vectorstore and retrieve with Langchain RAG Integration8:44

What is Model Context Protocol? Its advantages to use in AI Agent Systems5:28
Setting up MCP local server into local systems for RAG Agentic Implementation6:10
Integrate MCP tools into Langchain and enable AI Agents with MCP tools19:56
End to End Agentic RAG Implementation with MCP tools & Langchain Tools - Example7:16
Showcases an end-to-end agentic rag workflow by integrating MCP tools with LangChain to perform retrieval, tool orchestration, and product data validation (Nike Air ID 28).

Install & Setup LangGraph Visual Studio and expose AI Agent as Graph node7:43
Integrate Langsmith & Interact with Agent in UI Mode & Debug Traces/logs12:41
Add the Lang Smith API key to enable tracing, real-time monitoring, and observability of agent behavior in the UI, then explore rag agents and debugging with the observability dashboard.
Final recap Summary - what did we learn from this course ?4:47
Resume showcase points you can add after course completion0:22

Requirements

Basic knowledge on Typescript will be helpful

Description

If you’ve been hearing words like “AI Agents”, “LangChain”, or “RAG” everywhere and wondering how people are building smart AI apps that can search data, answer questions, or take actions on their own — you’re in the right place.

This beginner-friendly course will show you how to build real AI applications from scratch, even if you have never worked with AI before.

Most people only use ChatGPT to write text…
But companies today are building applications that can think, read, search, decide, and act automatically.

These applications are powered by LangChain — the leading framework for building AI-powered software.

In this course, you will learn how to:

Build simple AI apps that actually do useful tasks
Make an AI use tools (like checking the weather or sending an email)
Let an AI read documents and give answers based on your data
Organize information so the AI can “remember” things
Build small automation systems that can save time and effort

We will start from zero, explain every concept in plain English, and build everything step-by-step together.

By the end of the course, you will be able to build your own AI apps that can be used for:

Personal projects
Business automation
Customer support
Data lookup
Testing and QA
Real-world workflows

No complex math
No advanced AI background
No prior LangChain knowledge required.

Just practical learning, short lessons, real projects, and the confidence to build your own AI applications.

If you want simple, hands-on learning that focuses on doing — not theory — this course is perfect for you.

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

LangChain Framework for Beginners – Build AI Systems + RAG

What you'll learn

Explore related topics

Course content

Introduction to LangChain Framework & Course content Overview3 lectures • 13min

Setting up Langchain & Invoke First Agent with responses understanding5 lectures • 31min

Importance of LangChain tools & Runtime config - Build AI Agents with Tool calls5 lectures • 50min

System Prompts, ResponseSchema & MemoryManagement - Core components of Langchain4 lectures • 31min

Middleware Component Techniques - Customize AI Agent Behaviour at every Step6 lectures • 1hr 6min

Introduction to RAG Pipeline -Understand RAG Architecture with Agent Integration4 lectures • 30min

Load Documents, Split into Chunks & Build VectorStores with Embedding -Examples3 lectures • 32min

Build 2 Step RAG solution with Langchain by loading Multiple PDF's & Word docs3 lectures • 43min

Build Agentic RAG with MCP Server tools & Langchain Native tools - E2E Agent4 lectures • 39min

Export Agent to LangGraph Visual Studio & LangSmith for UI Mode, Debug & Traces4 lectures • 26min

Requirements

Description

Who this course is for: