Langchain For Beginners : Build Genai Llm Apps In Easy Steps

A Step-by-Step Guide to Master LangChain

[b]What you'll learn[/b]

Learn what LangChain is how it simplifies using LLMs in our applications

Use OpenAI LLMS in a python application

Use Open Source LLMS like Mistral,Gemma in a python application

Run Open Source LLMs on your local machine using OLLAMA

Use PromptTemplates to reuse and build dynamic prompts

Understand how to use the LangChain expression language

Create Simple and Regular Sequential chains using LCEL

Work with multiple LLMs in a single chain

Learn why and how to maintain Chat History

Learn what embeddings are and use the Embeddings Model to find text Similarity

Understand what a Vector Store is and use it to store and retrieve Embeddings

Understand the process of Retrieval Augmented Generation(RAG)

Implement (RAG) to use our own data with LLMs in simple steps

Analyze images using Multi Modal Models

Build multiple LLM APPs using Streamlit and LangChain

All in simple steps

[b]Requirements[/b]

Knowledge of Python

OpenAI Account to work with OpenAI LLMs

[b]Description[/b]

Welcome to LangChain for Beginners!This course is designed to provide a gentle, step-by-step introduction to LangChain, guiding youfrom the basics to more advanced concepts. Whether you're a complete novice or have someexperience with AI, this course will help you understand and leverage the power of LangChain forbuilding AI-powered applications.Course Goals:- Gradual Learning: Learn LangChain gradually from basic to advanced topics with clear andconcise instructions.- Comprehensive Understanding: Understand why LangChain is a powerful tool for building AIapplications and how it simplifies the integration of language models into your projects.- Hands-On Experience: Gain practical experience with essential LangChain features such asprompt templates, chains, agents, document loaders, output parsers, and model classes.What You Will Learn:- Introduction to LangChain: Get started with the basics of LangChain and understand its coreconcepts.- Building Blocks of LangChain: Learn about prompt templates, chains, agents, document loaders,output parsers, and model classes.- Creating AI Applications: See how these features come together to create a smart and flexible- Practical Coding: Write and run code examples to get a hands-on sense of how LangChaindevelopment looks like.Course Structure:- Concise Chapters: Each chapter focuses on a specific topic in LangChain programming,ensuring you gain a deep understanding of each concept.- Interactive Learning: Code along with the examples provided to reinforce your learning and buildyour skills.By the end of this course, you will:Learn what LangChain is how it simplifies using LLMs in our applicationsUse OpenAI LLMs in a python applicationUse Open Source LLMs like Mistral,Gemma in a python applicationRun Open Source LLMs on your local machine using OLLAMAUse PromptTemplates to reuse and build dynamic prompts Understand how to use the LangChain expression languageCreate Simple and Regular Sequential chains using LCEL Work with multiple LLMs in a single chainLearn why and how to maintain Chat HistoryLearn what embeddings are and use the Embeddings Model to find text SimilarityUnderstand what a Vector Store is and use it to store and retrieve EmbeddingsUnderstand the process of Retrieval Augmented Generation(RAG) Implement (RAG) to use our own data with LLMs in simple stepsAnalyze images using Multi Modal ModelsBuild multiple LLM APPs using Streamlit and LangChainAll in simple steps

Overview

Section 1: Introduction

Lecture 1 Introduction

Lecture 2 How to make the best

Lecture 3 Download Completed Project

Section 2: The Fundamentals

Lecture 4 What is GenAI

Lecture 5 What is OpenAI

Lecture 6 Other LLMs

Lecture 7 What is Langchain

Section 3: Software Setup

Lecture 8 Setup OpenAI Account

Lecture 9 Setup Open Source LLMs

Section 4: Langchain in action

Lecture 10 Setup Project

Lecture 11 Langchain in action

Lecture 12 Use Open Source Models Locally

Lecture 13 What is Streamlit

Lecture 14 Use Streamlit GUI

Lecture 15 Turn on Debug

Section 5: Prompt Templates

Lecture 16 Introduction

Lecture 17 PromptTemplate in action

Lecture 18 Add two more place holders

Lecture 19 Improve the prompt

Lecture 20 Create a Travel Guide App

Section 6: Chains

Lecture 21 Introduction

Lecture 22 LCEL In Action

Lecture 23 UseCase and Code Walkthrough

Lecture 24 Simple Sequential Chain

Lecture 25 Display the title

Lecture 26 Using Multiple LLMs

Lecture 27 Sequential Chain

Lecture 28 Format Output

Lecture 29 Organize Files

Section 7: Maintaining ChatHistory

Lecture 30 Introduction

Lecture 31 Use ChatPromptTemplate

Lecture 32 Code Walk Through

Lecture 33 Use StreamlitChatMessageHistory

Lecture 34 Display History

Lecture 35 Use ChatMessageHistory

Section 8: Embeddings

Lecture 36 Introduction

Lecture 37 Using the Embeddings Model

Lecture 38 Similarity Finder

Section 9: Vector Stores

Lecture 39 Introduction

Lecture 40 Code Walk Through

Lecture 41 Implement Job Search Helper

Lecture 42 Test

Lecture 43 Use Retriever

Section 10: RAG - Working With Documents

Lecture 44 What is RAG

Lecture 45 UseCase and Code Walkthrough

Lecture 46 Implement RAG Part 1

Lecture 47 Implement RAG Part 2

Lecture 48 Test

Lecture 49 History Aware RAG Bot

Lecture 50 Test

Section 11: Image Processing

Lecture 51 Introduction

Lecture 52 Create Image Analyzer App

Lecture 53 Use Streamlit

Section 12: Agents

Lecture 54 Introduction

Lecture 55 Code Walk Through

Lecture 56 Setup Project

Lecture 57 Create an Agent

Lecture 58 Test

Section 13: Deployment

Lecture 59 Introduction

Lecture 60 Update Code

Lecture 61 Push to GitHub

Lecture 62 Deploy

Python Developers who want to use LangChain to build GenAI LLM applications,Any students who has completed my Python or OpenAI course and who want to master LanChain

[Image: HKm3079m_o.jpg]

[To see links please register or login]