Introduction To Langchain

Introduction To Langchain
Published 11/2023
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English

| Size: 6.29 GB[/center]
| Duration: 7h 21m
Learn to build Software Applications with Large Language Models

What you'll learn

Build software applications with Large Language models

Learn how to augment LLMs with tools and databases

Learn how to connect LLMs to external data

Learn the fundamentals of Prompt Engineering

Learn the fundamentals of Vector Databases

Learn the fundamentals of Retrieval Augmented Generation

LangChain: Models, Chains, Prompts, Memory, Vector stores, Agents!

Requirements

Python

Jupyter notebooks

VS Code

Description

Welcome to the Introduction to LangChain course! Very recently, we saw a revolution with the advent of Large Language Models. It is rare that something changes the world of Machine Learning that much, and the hype around LLM is real! That's something that very few experts predicted, and it's essential to be prepared for the future.LangChain is an amazing tool that democratizes machine learning for everybody. With LangChain, every software engineer can use machine learning and build applications with it. Prior to LangChain and LLMs, you needed to be an expert in the field. Now, you can build an application with a couple of lines of code. Think about language models as a layer between humans and software. LangChain is a tool that allows the integration of LLMs within a larger software.Topics covered in that course:LangChain BasicsLoading and Summarizing DataPrompt Engineering FundamentalsVector Database BasicsRetrieval Augmented GenerationRAG Optimization and Multimodal RAGAugmenting LLMs with a Graph DatabaseAugmenting LLMs with toolsHow to Build a Smart Voice AssistantHow to Automate Writing NovelsHow to Automate Writing SoftwareThe course is very hands-on! We will work on many examples to build your intuition on the different concepts we will address in this course. By the end of the course, you will be able to build complex software applications powered by Large Language Models!

Overview

Section 1: Introduction

Lecture 1 Introduction to the course

Lecture 2 Course structure

Lecture 3 Setting up your Jupyter Notebook (optional)

Section 2: LangChain Basics

Lecture 4 Introduction

Lecture 5 What is LangChain - OpenAI API Key - Installing the Python Packages

Lecture 6 LLMs

Lecture 7 Chains

Lecture 8 Prompt Templates

Lecture 9 Output parsers

Lecture 10 Simple Sequence

Lecture 11 Written material

Lecture 12 Outro

Section 3: Loading and Summarizing Data

Lecture 13 Introduction

Lecture 14 Loading Data

Lecture 15 Summary strategies

Lecture 16 Summarization examples

Lecture 17 Written material

Lecture 18 Outro

Section 4: Prompt Engineering Fundamentals

Lecture 19 Introduction

Lecture 20 Elements of a Prompt

Lecture 21 Few-Shot Learning

Lecture 22 Memetic Proxy

Lecture 23 Chain of Thought

Lecture 24 Self-Consistency

Lecture 25 Inception

Lecture 26 Self-Ask

Lecture 27 ReAct

Lecture 28 Plan and Execute

Lecture 29 Written material

Lecture 30 Outro

Section 5: Vector Database Basics

Lecture 31 Intro

Lecture 32 Why Vector Databases?

Lecture 33 Similarity Metrics

Lecture 34 Why do we need Indexing?

Lecture 35 Product Quantization

Lecture 36 Locality Sensitive-Hashing

Lecture 37 Navigable Small World

Lecture 38 Hierarchical Navigable Small World

Lecture 39 Maximum Marginal Relevance

Lecture 40 Written material

Lecture 41 Outro

Section 6: Retrieval augmented generation

Lecture 42 Introduction

Lecture 43 Indexing data

Lecture 44 Loading data into a vector database

Lecture 45 Providing sources

Lecture 46 Indexing a website

Lecture 47 Indexing a GitHub repository

Lecture 48 The Stuff Strategy

Lecture 49 The Map-Reduce Strategy

Lecture 50 The Refine strategy

Lecture 51 The Map-Rerank strategy

Lecture 52 Written material

Lecture 53 Outro

Section 7: RAG optimization and Multimodal RAG

Lecture 54 Introduction

Lecture 55 Multi-Vector Retriever

Lecture 56 Hypothetical Queries

Lecture 57 Parsing a Multimodal Document

Lecture 58 Summarizing the Data

Lecture 59 Describing Images with LlaVA

Lecture 60 Index the Data into a Database

Lecture 61 Finalizing the RAG Pipeline

Lecture 62 Written material

Lecture 63 Outro

Section 8: Augmenting LLMs with a Graph Database

Lecture 64 Intro

Lecture 65 What is a Knowledge Base

Lecture 66 Getting the Data

Lecture 67 Create the Graph Representation

Lecture 68 Augmenting LLMs with a Knowledge Base

Lecture 69 Using the Diffbot Graph Transformer

Lecture 70 Creating a Local Graph Database

Lecture 71 Augmenting an LLM with the Graph Database

Lecture 72 Written material

Lecture 73 Outro

Section 9: Augmenting LLMs with Tools

Lecture 74 Intro

Lecture 75 What is an Agent?

Lecture 76 Agent Example

Lecture 77 Dissecting the Iterative Process

Lecture 78 The Different Tools

Lecture 79 Building Custom Tools

Lecture 80 Written material

Lecture 81 Outro

Section 10: How to build a Smart Voice Assistant

Lecture 82 Introduction

Lecture 83 What are we building

Lecture 84 Setting up the Project

Lecture 85 From Speech to Text

Lecture 86 From Text to Speech

Lecture 87 Building a Conversational Agent

Lecture 88 Augmenting the Agent with Tools

Lecture 89 Written material

Lecture 90 Outro

Section 11: How to Automate Writing Books

Lecture 91 Introduction

Lecture 92 Formalizing the Book Writing Process

Lecture 93 Setting up the Project

Lecture 94 The Main Character

Lecture 95 The Title

Lecture 96 The Plot

Lecture 97 The Chapters List

Lecture 98 The Events List

Lecture 99 The Chapters' Plots

Lecture 100 Writing the Book

Lecture 101 Writing to File

Lecture 102 Reading the Book

Lecture 103 Written material

Lecture 104 Outro

Section 12: Automating Writing Software

Lecture 105 Introduction

Lecture 106 The Strategy

Lecture 107 Setting up the Project

Lecture 108 The Technical Requirements

Lecture 109 The Class Structure

Lecture 110 The File Structure

Lecture 111 The File Paths

Lecture 112 The Code

Lecture 113 Iterate

Lecture 114 Written material

Lecture 115 Outro

Section 13: Thank you!

Lecture 116 Parting words

Intermediate Python developers curious to learn how to develop software applications with Large Language Models,Machine Learning enthusiasts that want to to improve their knowledge on Large Language Models