LangChain- Develop LLM powered applications with LangChain

LangChain- Develop LLM powered applications with LangChain, available at $89.99, has an average rating of 4.55, with 72 lectures, based on 16690 reviews, and has 63931 subscribers.

You will learn about Become proficient in LangChain Have 3 end to end working LangChain based generative AI applications Prompt Engineering Theory: Chain of Thought, ReAct, Few Shot prompting and understand how LangChain is build under the hood Understand how to navigate inside the LangChain opensource codebase Large Language Models theory for software engineers LangChain: Lots of chains Chains, Agents, DocumentLoader, TextSplitter, OutputParser, Memory RAG, Vectorestores/ Vector Databasrs (Pinecone, FAISS) This course is ideal for individuals who are Software Engineers that want to learn how to build Generative AI based applications with LangChain or Backend Developers that want to learn how to build Generative AI based applications with LangChain or Fullstack engineers that want to learn how to build Generative AI based applications with LangChain It is particularly useful for Software Engineers that want to learn how to build Generative AI based applications with LangChain or Backend Developers that want to learn how to build Generative AI based applications with LangChain or Fullstack engineers that want to learn how to build Generative AI based applications with LangChain.

Enroll now: LangChain- Develop LLM powered applications with LangChain

Summary

Title: LangChain- Develop LLM powered applications with LangChain

Price: $89.99

Average Rating: 4.55

Number of Lectures: 72

Number of Published Lectures: 71

Number of Curriculum Items: 72

Number of Published Curriculum Objects: 71

Original Price: $19.99

Quality Status: approved

Status: Live

What You Will Learn

Become proficient in LangChain

Have 3 end to end working LangChain based generative AI applications

Prompt Engineering Theory: Chain of Thought, ReAct, Few Shot prompting and understand how LangChain is build under the hood

Understand how to navigate inside the LangChain opensource codebase

Large Language Models theory for software engineers

LangChain: Lots of chains Chains, Agents, DocumentLoader, TextSplitter, OutputParser, Memory

RAG, Vectorestores/ Vector Databasrs (Pinecone, FAISS)

Who Should Attend

Software Engineers that want to learn how to build Generative AI based applications with LangChain

Backend Developers that want to learn how to build Generative AI based applications with LangChain

Fullstack engineers that want to learn how to build Generative AI based applications with LangChain

Target Audiences

Software Engineers that want to learn how to build Generative AI based applications with LangChain

Backend Developers that want to learn how to build Generative AI based applications with LangChain

Fullstack engineers that want to learn how to build Generative AI based applications with LangChain

COURSE WAS RE-RECORDED and supports- LangChain Version 0.2.6

Welcome to first LangChain Udemy course – Unleashing the Power of LLM!
This comprehensive course is designed to teach you how to QUICKLY harness the power the LangChain library for LLM applications.
This course will equip you with the skills and knowledge necessary to develop cutting-edge LLM solutions for a diverse range of topics.

Please note that this is not a course for beginners. This course assumes that you have a background in software engineering and are proficient in Python. I will be using Pycharm IDE but you can use any editor you’d like since we only use basic feature of the IDE like debugging and running scripts .

In this course, you will embark on a journey from scratch to building a real-world LLM powered application using LangChain.
We are going to do so by build 3 main applications:

1. Ice Breaker– LangChain agent that given a name, searches in google to find Linkedin and twitter profiles, scrape the internet for information about a name you provide and generate a couple of personalized ice breakers to kick off a conversation with the person.

2. Documentation Helper– Create chatbot over a python package documentation. (and over any other data you would like)

3. A slim version of ChatGPT Code-Interpreter

4. Prompt Engineering Theory Section

The topics covered in this course include:

LangChain

LLM + GenAI History

LLMs: Few shots prompting, Chain of Thought, ReAct prompting

Chat Models

Open Source Models

Prompts, PromptTemplates, langchainub

Output Parsers, Pydantic Output Parsers

Chains: create_retrieval_chain, create_stuff_documents_chain

Agents, Custom Agents, Python Agents, CSV Agents, Agent Routers

OpenAI Functions, Tool Calling

Tools, Toolkits

Memory

Vectorstores (Pinecone, FAISS)

RAG (Retrieval Augmentation Generation)

DocumentLoaders, TextSplitters

Streamlit (for UI)

LCEL

LangSmith

Intro to LangGraph

FireCrawl

Throughout the course, you will work on hands-on exercises and real-world projects to reinforce your understanding of the concepts and techniques covered. By the end of the course, you will be proficient in using LangChain to create powerful, efficient, and versatile LLM applications for a wide array of usages.

This is not just a course, it’s  also  a community. Along with lifetime access to the course, you’ll get:

1. Dedicated 1 on 1 troubleshooting support with me

2. Github links with additional AI resources, FAQ, troubleshooting guides

3. Access to an exclusive Discord community to connect with other learners (5000+ members)

4. No extra cost for continuous updates and improvements to the course

DISCLAIMERS

1. Please note that this is not a course for beginners. This course assumes that you have a background in software engineering and are proficient in Python.
   I will be using Pycharm IDE but you can use any editor you’d like since we only use basic feature of the IDE like debugging and running scripts.

2. The first project of the course (Ice-Breaker) requires usage of 3rd party APIs-
   ProxyURL, SerpAPI, Twitter API  which are generally paid services.
   All of those 3rd parties have a free tier we will use to create stub responses development and testing.

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Lecture 2: Course Structure + How to get the best of Udemy [PLEASE DO NOT SKIP]

Lecture 3: What is LangChain?

Lecture 4: Courses Discord Server

Chapter 2: The GIST of LangChain- Get started by with your Hello World chain

Lecture 1: Project Setup (Pycharm) recommend)

Lecture 2: Project Setup (vscode) – optional

Lecture 3: Environment Variables and .env File

Lecture 4: Your First LangChain application – Chaining a simple prompt

Lecture 5: Using Open Source Models With LangChain (Ollama, Llama3, Mistral)

Lecture 6: LangChain Version In Course (V0.2.6) – (No breaking changes in 0.2.6)

Lecture 7: Quick Check In

Chapter 3: Ice Breaker Real World Generative AI Agent application

Lecture 1: Ice Breaker- What are we building here?

Lecture 2: Integrating Linkedin Data Processing – Part 1 – Scraping

Lecture 3: Linkedin Data Processing – Part 2 – Agents Theory

Lecture 4: Linkedin Data Processing- Part 3: Tools, Agent Executor, create_react_agent

Lecture 5: Linkedin Data Processing- Part 4: Custom Search Agent Implementation

Lecture 6: Linkedin Data Processing- Part 5: Custom Search Agent Testing

Lecture 7: [Optional] Twitter Data Processing- Part 1- Scraping

Lecture 8: [Optional] Twitter Data Processing- Part 2- Agents

Lecture 9: Output Parsers- Getting Ready to work with a Frontend

Lecture 10: FullsStack App- Building our LLM powered by LangChain FullStack Application

Lecture 11: Tracing application with LangSmith

Chapter 4: Diving Deep Into ReAct Agents- Whats is the magic?

Lecture 1: What are we building? ReAct AgentExecutor from scratch

Lecture 2: Environment Setup + ReAct Algorithm overview

Lecture 3: Defining Tools for our ReAct agent

Lecture 4: ReAct prompt, LLM Reasoning Engine, Output Parsing and Tool Execution

Lecture 5: AgentAction, AgentFinish, ReAct Loop

Lecture 6: CallbackHandlers, ReAct Prompt and finalizing the ReAct Agent loop

Lecture 7: Recap with LangSmith

Chapter 5: The GIST of RAG- Embeddings, Vector Databases and, & Retrieval

Lecture 1: Medium Analyzer- Boilerplate Project Setup

Lecture 2: Medium Analyzer- Class Review: TextLoader,TextSplitter,OpenAIEmbeddings,Pinecone

Lecture 3: Medium Analyzer- Ingestion Implementation

Lecture 4: Medium Analyzer- Retrieval Implementation Implementation with chains

Lecture 5: Medium Analyzer- Retrieval Implementation Implementation with LCEL

Lecture 6: Chat With Your PDF- FAISS Local Vectorstore

Chapter 6: Building a documentation assistant (Embeddings, VectorDBs, Retrieval, Memory)

Lecture 1: What are we building?

Lecture 2: Environment Setup

Lecture 3: OPTIONAL Manually Scraping the LangChain Documentation

Lecture 4: Pinecone Vectorstore Ingestion

Lecture 5: Retrieval + Augmentation + Generation = RAG

Lecture 6: Building an AI LangChain Chat Assistant- Frontend with Streamlit (UI)

Lecture 7: Building an AI LangChain Chat Assistant- Memory

Lecture 8: RAG Pipeline Optimization featuring FireCrawl

Chapter 7: Building a slim ChatGPT Code-Interpreter (Advanced Agents, OpenAI Functions)

Lecture 1: What are we building? (A slim Version of GPT Code-Interpreter)

Lecture 2: Project Setup

Lecture 3: Python Agent

Lecture 4: CSV Agent

Lecture 5: Wrapping Everything: Router Agent

Lecture 6: Function/ Tool Calling in LangChain

Lecture 7: OpenAI functions Vs ReAct

Chapter 8: LangChain Theory

Lecture 1: LangChain Token Limitation Handeling Strategies

Lecture 2: LangChain Memory Deepdive

Chapter 9: Prompt Engineering Theory

Lecture 1: The GIST of LLMs

Lecture 2: What is a Prompt? Composition of a formal prompt

Lecture 3: Zero Shot Prompting

Lecture 4: Few Shot Prompting

Lecture 5: Chain of Thought Prompting

Lecture 6: ReAct

Lecture 7: Prompt Engineering Quick Tips

Chapter 10: Troubleshooting Section

Lecture 1: Have a technical issue? WATCH THIS FIRST. I Promise this will help!

Lecture 2: Tweet API- tweepy.errors.Forbidden: 403 Forbidden

Lecture 3: Pinecone: AttributeError: init is no longer a top-level attribute of pinecone

Lecture 4: LangChain Version In Course (V0.2.6)

Chapter 11: Wrapping Up

Lecture 1: LLM Applications in Production

Lecture 2: LLM Application Development landscape

Lecture 3: Finished course? Whats next!

Chapter 12: Introduction To LangGraph

Lecture 1: What is LangGraph?

Lecture 2: LangGraph & Flow Engineering

Chapter 13: Useful tools when developing LLM Applications

Lecture 1: LangChain Hub – Downloads prompt from the community

Lecture 2: TextSplitting Playground

Lecture 3: LangChain VS LlamaIndex

Instructors

Eden Marco | LLM Specialist
Best Selling Instructor

Rating Distribution

1 stars: 88 votes

2 stars: 160 votes

3 stars: 1291 votes

4 stars: 5920 votes

5 stars: 9231 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!