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 Mastery - Most Practical Course To Build AI Apps

Name: LangChain Mastery - Most Practical Course To Build AI Apps
Rating: 4.6 (17 reviews)

The Complete Guide to Building Advanced AI Apps with LangChain, Perfect for Both Beginners and Experienced Professionals

Created byAditya Shrivastava

Last updated 12/2024

English

What you'll learn

Understand the basics of Large Language Models (LLMs) and LangChain to build a strong foundation for AI applications.
Master core concepts like chains, memory, models, prompt templates, and output parsers, explained with visuals and in simple language.
Excel in prompt engineering and output parsing to guide AI responses for diverse use cases.
Implement Retrieval-Augmented Generation (RAG) for data handling, then delve into Advanced RAG techniques, including query translation, multi-query, indexing
Build robust, stateful AI systems with LangGraph’s multi-agent workflows and real-time interaction capabilities.
Deploy and optimize AI applications with LangSmith, ensuring effective monitoring and debugging
Create interactive AI applications using Streamlit, enhancing user engagement and experience.

Course content

16 sections • 95 lectures • 9h 30m total length

Welcome2:10
Course Outline5:35
Explore LangChain mastery by building practical generative AI apps, from fundamentals to prompts, memory, RAG, and agents, with deployment options using Streamlit and Hugging Face Spaces.
How to make most out of this course1:57
Maximize your learning by using the Udemy discussion board for help, downloading the latest code from GitHub, and accessing updated samples and the long chain repository.
Complete project code and resources1:37

ChatGPT and OpenAI7:35
Models & Machine Learning6:47
Understanding LLM and AI Basics - Quiz 1
Artificial Intelligence and Generative AI4:54
Large Language Model(LLM)5:19
Prompts and Tokens4:27
Learn how prompts steer ai apps by defining prompts, practicing prompt engineering, and shaping input and output tokens. Understand token costs and api call calculations for models like ChatGPT.
Understanding LLM and AI Basics - Quiz 2
(Optional) How ChatGPT works behind the scene?4:45
Explore how ChatGPT works behind the scenes, from pre-training and fine-tuning with prompts and feedback to a transformer with self-attention that encodes input into vectors and generates responses.
(Optional) Supervised & Un-supervised Learning4:58
Summary: Understanding LLM and AI Basics0:41

Environment Set Up (Mac)6:22
Environment Set Up (Windows)3:16
Setup API Keys5:55
Write our first GenAI code Part-124:38
Write our first GenAI code Part-1 teaches you to call the OpenAI chat completion API from Python, using a virtual environment and dotenv to securely load API keys.
Write our first GenAI code Part-29:44
What is LangChain6:30
Getting started with LangChain - Quiz 1
Write our first LangChain code6:30
Benefits of LangChain4:18
Getting started with LangChain - Quiz 2
Summary: Getting started with LangChain0:29
Set up your environment, configure api keys for Windows and Mac, and write your first generative ai code while exploring LangChain's benefits through coding and quizzes for building with llms.

LLM Application Workflow2:01
Models: Chat Model6:42
Chat Model vs LLM3:27
Access Open Source Models6:17
Build a Financial Concept Explainer App Using LangChain
Assignment Solution: Financial Concept Explainer App7:59
Build an interactive financial concept explainer app in Python using a chat model, with continuous user prompts and a quit command, as shown in assignment one of LangChain mastery.
Token Usage10:54
(Optional) Interface and Classes4:31
Models - Quiz 1
Summary: Models0:34

Prompts4:54
Explore prompts and output parsers in llm-powered apps, learning to craft effective prompts, use prompt templates, and dynamic prompts with f-strings for well-organized outputs.
Prompt Template10:20
Learn to build dynamic prompts using chat prompt templates, human message templates, and prompt templates with placeholders and input variables to format system and user messages for task-specific prompts.
Few Shot Template6:40
Prompts & Output Parsers - Quiz 1
App: Travel App7:45
Context Window & Token Limit7:00
Example Selectors7:44
Output parsers13:18
Explore how to structure language model outputs with LangChain output parsers, using Pydantic models for JSON and validation, and leverage format instructions and partial variables to produce reliable, formatted results.
Prompts & Output Parsers - Quiz 2
Summary: Prompts & Output Parsers0:30
Build a Smart Email Responder Using LangChain and GPT

What is Streamlit6:27
LangChain with Streamlit6:06
App: Financial QA System with Streamlit7:31
App: Refactored Financial QA System with Streamlit8:29
Refactor a Streamlit financial concept explainer chat app into modular, readable code following the single responsibility principle, separation of concerns, session state management, and environment variables.
App: Social Media Script Writing App9:59
Streamlit for AI Apps - Quiz 1
Summary: Streamlit for AI Apps0:41

Introduction to Chains6:49
Runnable7:09
RunnableSequence8:13
Sequential Chains6:26
Master sequential chains by wiring two components in one workflow: generate content from a topic, then generate hashtags from the content, showcasing a two-chain sequence in a practical LangChain workflow.
RunnablePassthrough10:34
Chains - Quiz 1
Summary: Chains0:37
Build a Streamlit app to create social media content generator

Why we need Memory in AI Apps?3:38
Add Memory in AI Apps17:16
Memory - Quiz 1
Memory With Sessions12:15
Memory with user sessions4:02
Memory - Quiz 2
Summary: Memory0:34
Develop AI applications that remember past conversations by leveraging session based memory and memory for user sessions, maintaining context across interactions for a more personalized experience.
Build an Event Planning Chatbot with Conversational Memory

Jupyter Notebook: Intro & Installation4:04
Intro to Prompt Engineering6:36
Prompt Engineering Exercise 1
BenchMark of Good Prompt3:28
Prompt Engineering Exercise 2
Prompt Engineering Techniques Part-110:12
Learn prompt engineering techniques to guide AI models toward desired outputs, including zero-shot, one-shot, few-shot, multi-step prompting, and chain of thought methods.
Prompt Engineering Techniques Part-29:31
Prompt Engineering - Quiz 1
Prompt Engineering Exercise 3
Summary: Prompt Engineering0:42

Requirements

Basic Python programming
Interest in Building Real-World AI Applications

Description

Course is created with latest LangChain Version 0.3 and also covered LangSmith.

Welcome to LangChain Mastery - Most Practical Course To Build AI Apps! This course is designed to give you a comprehensive, hands-on experience with LangChain, covering everything from foundational concepts to advanced AI applications. Whether you’re looking to build AI-driven tools, automate data workflows, or leverage the latest in LLM technology, this course will guide you through every step.

Prepare yourself for a hands-on, interactive experience that will transform your understanding of LangChain. With our simple, three-step approach—Why, What, and How—you’ll learn to apply LangChain to solve real-world challenges.

Who This Course Is For:

New to LLM/GenAI but from the IT Industry: If you’re familiar with the IT world but new to Generative AI and Large Language Models, we’ll start from the ground up and help you build advanced applications by the end.
Career Transitioners: If you’re transitioning into IT from another field and want to get into Generative AI, this course will give you a solid foundation with practical skills to launch your career.
Learners with Some GenAI Experience: For those who have dabbled in GenAI and want to learn LangChain in depth, this course will take your understanding and skills to the next level.
Experienced AI Developers: If you’ve built GenAI applications before but have been piecing things together from scattered resources, this course will offer a structured, comprehensive guide to building AI apps the right way.

What You Will Learn

Through practical projects, you’ll master essential skills in LangChain and the LangChain ecosystem. Here’s what we’ll cover:

Understanding LLM and AI Basics
Start with AI fundamentals, covering LLMs, their workings, prompts, tokens, and more—setting a strong foundation.
Getting Started with LangChain
Set up your environment, write your first GenAI code, and explore LangChain’s benefits.
Models
Learn about chat models, LLMs, token usage, and work on hands-on projects.
Prompts & Output Parsers
Master prompt creation and output parsing, including handling JSON for real-world use case.
Streamlit for AI Apps
Build a user-friendly UI for your AI apps with Streamlit.
Chains
Explore LangChain chains and Runnables and built apps like video analyzer, resume enhancer, and email generator.
Memory
Learn to manage memory in LangChain, enhancing conversation flow in apps.
Prompt Engineering
Dive deeper into advanced prompt engineering techniques.
Real-World LLM Use Cases
Explore practical LLM applications and understand where GenAI adds the most value.
RAG: Working with Your Data
Implement Retrieval-Augmented Generation, creating tools like a QA bot, summarizer, and comparison tool.
LangSmith: Debugging and Evaluation
Learn to debug and observe LangChain apps using LangSmith.
Advanced RAG
Expand on RAG with multi-query and indexing, building more sophisticated applications.
Callbacks
Implement callbacks to optimize and monitor application workflows.
Deploy and Share AI Apps
Deploy your AI apps on Streamlit Cloud and Hugging Face Spaces, sharing your projects seamlessly.

Course Structure and Benefits

Major benefit of this course is its simplicity—complex concepts are broken down into easy-to-understand explanations, making both theory and practical applications accessible for all learners.
Project-Based Learning: Each section includes interactive projects, allowing you to apply concepts directly to real-world scenarios.
Structured Learning Path: Topics are organized sequentially, moving from foundational to advanced topics for a comprehensive understanding.

By the End of This Course, You Will Be Able To:

Build, debug, and deploy LangChain applications tailored to solve real-world problems.
Implement effective prompt engineering techniques and handle complex workflows with agents.
Create dynamic, user-friendly UIs with Streamlit and manage context in AI applications using memory.
Optimize your applications with LangSmith and deploy your solutions confidently.

Join us and start building powerful AI apps today!

Who this course is for:

New to LLM/GenAI but from the IT Industry
Career Transitioners
Learners with Some GenAI Experience
Experienced AI Developers

LangChain Mastery - Most Practical Course To Build AI Apps

What you'll learn

Explore related topics

Course content

Introduction4 lectures • 11min

Understanding LLM and AI Basics8 lectures • 39min

Getting started with LangChain9 lectures • 1hr 8min

Models8 lectures • 42min

Prompts & Output Parsers8 lectures • 58min

Streamlit for AI Apps6 lectures • 39min

Chains6 lectures • 40min

Memory5 lectures • 38min

Prompt Engineering6 lectures • 35min

Real World LLM Uses3 lectures • 15min

Requirements

Description

Who this course is for: