Chatgpt And Langchain: The Complete Developer’S Masterclass

Published 10/2023
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 4.33 GB | Duration: 11h 54m

Intensive masterclass on ChatGPT and LangChain. Build production-ready apps with a focus on real-world AI integration.

What you’ll learn
Integrate ChatGPT into production-style apps with LangChain
Use LangChain components to build complex text generation pipelines
Enhance ChatGPT’s output by automatically integrating user feedback
Teach ChatGPT new facts through Retrieval Augmented Generation
Extend LangChain to implement server-to-browser text streaming
Use OpenAI Plugins to add new capabilities to ChatGPT, such as database access and code execution
Understand every line of code we write so you can use these exact same techniques on your own projects
Build your own chat-with-a-PDF web application, complete with document upload and authentication
See how users interact with your chat features using observability and tracing

Requirements
Basic programming experience

Description
You’ve found the most advanced, most complete, and most intensive masterclass online for learning how to integrate LangChain and ChatGPT into production-ready applications!Thousands of engineers have learned how to build amazing applications using ChatGPT, and you can too. This course uses a time-tested, battle-proven method to make sure you understand exactly how ChatGPT works, and is the perfect pathway to help you get a new job as a software engineer working on AI-enabled apps.The difference between this course and all the others: you will go far beyond the basics of simple ChatGPT prompts, and understand how companies are integrating text generation into their apps today.___________ChatGPT is being used across industries to enhance applications with text generation. But with this new feature comes many challenges: Building complex text generation pipelines that incorporate outside informationCreating reusable configuration components that can be reassembled in different waysApplying user feedback (like upvotes/downvotes) to enhance ChatGPT’s outputWiring in observability and tracing to see how users are interacting with your AIGenerate text performantly using distributed processingThis course will walk you through production-ready, repeatable techniques for addressing each of these challenges and many more.What will you build?This course focuses on creating a series of different projects of increasing complexity. You’ll start from the very basics, understanding how to access ChatGPT 4 programatically. From there, we will quickly increase in complexity, building more complex projects with many more features. By the end, you will make a fully-featured web app that implements a “Chat-with-a-PDF” feature. Note: no previous web development experience is required.Here’s a partial list of some of the topics you’ll cover:Understand how complex text-generation pipelines workWrite reusable code using chains provided by LangChainConnect chains together in different ways to dramatically change your apps behavior with easeStore, retrieve, and summarize chat messages using conversational memoryImplement semantic search for Retrieval-Augmented Generation using embeddingsGenerate and store embeddings in vector databases like ChromaDB and PineconeUse retrievers to refine, reduce, and rank context documents, teaching ChatGPT new informationCreate agents to automatically accomplish tasks for you using goals you defineWrite tools and plugins to allow ChatGPT to access the outside worldMaintain a consistent focus on performance through distributed processing using Celery and RedisExtend LangChain to implement server-to-browser text streamingImprove ChatGPT’s output quality through user-generated feedback mechanismsGet visibility into how users interact with your text generation features by using tracingThere are a ton of courses that show how to use ChatGPT at a very basic level. This is one of the very few courses online that goes far beyond the basics to teach you advanced techniques that top companies are using today. I have a passion for teaching topics the right way – the way that you’ll actually use technology in the real world. Sign up today and join me!

Overview
Section 1: Let’s Start – Dive In Here!

Lecture 1 How to Get Help

Lecture 2 What is LangChain?

Lecture 3 How a Typical AI-Enabled App Works

Lecture 4 Here It Is, This Is Why We Use LangChain

Section 2: ChatGPT and LangChain Integration

Lecture 5 Project Overview and Setup

Lecture 6 Creating an OpenAI API Key

Lecture 7 Using LangChain the Simple Way

Lecture 8 Introducing Chains

Lecture 9 Adding a Chain

Lecture 10 Parsing Command Line Arguments

Lecture 11 Securing the API Key

Lecture 12 Connecting Chains Together

Lecture 13 Chains in Series with SequentialChain

Section 3: Deep Dive into Interactions with Memory Management

Lecture 14 App Overview

Lecture 15 Receiving User Input

Lecture 16 Chat vs Completion Style Models

Lecture 17 Representing Messages with ChatPromptTemplates

Lecture 18 Implementing a Chat Chain

Lecture 19 Understanding Memory

Lecture 20 Using ChatBufferMemory to Store Conversations

Lecture 21 Saving and Extending Conversations

Lecture 22 Summarizations Conversation Summary Memory

Section 4: Adding Context with Embedding Techniques

Lecture 23 Project Overview

Lecture 24 Facts File Download

Lecture 25 Project Setup

Lecture 26 Loading Files with Document Loaders

Lecture 27 Search Criteria

Lecture 28 Introducing Embeddings

Lecture 29 The Entire Embedding Flow

Lecture 30 Chunking Text

Lecture 31 Generating Embeddings

Section 5: Custom Document Retrievers

Lecture 32 Introducing ChromaDB

Lecture 33 Building a Retrieval Chain

Lecture 34 What is a Retriever?

Lecture 35[Optional] Understanding Refine, MapReduce, and MapRerank

Lecture 36 Removing Duplicate Documents

Lecture 37 Creating a Custom Retriever

Lecture 38 Custom Retriever in Action

Lecture 39 Understanding Embeddings Download

Lecture 40 Visualizing Embeddings

Section 6: Empower ChatGPT with Tools and Agents

Lecture 41 App Overview

Lecture 42 Understanding Tools

Lecture 43 Understanding ChatGPT Functions

Lecture 44 SQLite Database Download

Lecture 45 Defining a Tool

Lecture 46 Defining an Agent and AgentExecutor

Lecture 47 Understanding Agents and AgentExecutors

Lecture 48 Shortcomings in ChatGPT’s Assumptions

Lecture 49 Recovering from Errors in Tools

Lecture 50 Adding Table Context

Lecture 51 Adding a Table Description Tool

Lecture 52 Being Direct with System Messages

Lecture 53 Adding Better Descriptions for Tool Arguments

Lecture 54 Tools with Multiple Arguments

Lecture 55 Memory vs Agent Scratchpad

Lecture 56 Preserving Messages with Agent Executor

Lecture 57 Understanding Callbacks

Lecture 58 Implementing a Basic Callback Handler

Lecture 59 More Handler Implementaion

Section 7: Pinecone as a Vector Database

Lecture 60 App Overview

Lecture 61 Taking a Look at Mockups

Lecture 62 Boilerplate Download

Lecture 63 Boilerplate Setup

Lecture 64 How This App is Designed

Lecture 65 Outlining the First Feature

Lecture 66 Loading and Splitting From a PDF

Lecture 67 Sample PDF

Lecture 68 Testing the PDF Upload

Lecture 69 Introducing Pinecone

Lecture 70 Initializing the Pinecone Client

Lecture 71 Adding Documents to the Vector Store

Section 8: Distributed Text Generation with Celery

Lecture 72 Why is Processing Taking Forever?

Lecture 73 Introducing Background Jobs

Lecture 74 Redis Setup

Lecture 75 Redis – MacOS Setup

Lecture 76 Redis – Ubuntu and Windows Subsystem for Linux Setup

Lecture 77 Redis – Windows Setup *Without* WSL

Lecture 78 Adding in the Worker

Lecture 79 Queuing Up Jobs

Lecture 80 Updating Document Metadata

Section 9: Custom Message Histories

Lecture 81 Understanding the Apps Requirements

Lecture 82 Persistent Message Storage

Lecture 83 Introducing the Conversational Retrieval Chain

Lecture 84 Building the Retriever

Lecture 85 Custom History Objects

Lecture 86 Building a Custom SQL History

Lecture 87 Testing the Chain

Section 10: Streaming Text Generation

Lecture 88 Streaming Text Generation

Lecture 89 Creating a Working Playground

Lecture 90 Experimenting with a Streaming Language Model

Lecture 91 Chains Don’t Want to Stream

Lecture 92 Receiving Chunks with a Callback

Lecture 93 Extending a LLM Chain

Lecture 94 Adding a Queue for Communication

Lecture 95 The Chain Really Wants to Wait

Lecture 96 Solving the Slow Chain

Lecture 97 It Works!

Lecture 98 Ending the Loop

Section 11: Extending LangChain

Lecture 99 Isolating the Queue and Handler

Lecture 100 Using a Mixin Approach

Lecture 101 Integrating the Streaming Code

Lecture 102 Testing the Streaming Setup

Lecture 103 Here’s the Issue

Lecture 104 Isolating the Handler

Lecture 105 Streaming Complete!

Section 12: Self-Improving Text Generation

Lecture 106 Random Component Parts

Lecture 107 Component Part Flow

Lecture 108 Partial KWArg Application

Lecture 109 Building Component Maps

Lecture 110 Randomly Picking a Component

Lecture 111 Generalizing Component Picking

Lecture 112 Collecting User Feedback

Lecture 113 Redis Connection Setup

Lecture 114 Storing Votes in Redis

Lecture 115 Weighted Randomness

Lecture 116 Extracting Scores

Lecture 117 Calculating the Average Score

Lecture 118 Selecting Components By Score

Section 13: Implementing Tracing and Observability

Lecture 119 Adding Score Observability

Lecture 120 Building the Score Aggregate

Lecture 121 Adding Another Form of Memory

Lecture 122 Window Memory Implementation

Lecture 123 Text Generation Tracing

Lecture 124 Langfuse Signup

Lecture 125 Adding in Tracing

Lecture 126 Understanding the Trace

Lecture 127 Automatic Trace Creation

Software engineers looking to add AI into their apps

Password/解压密码www.tbtos.com

转载请注明：0daytown » Chatgpt And Langchain: The Complete Developer’S Masterclass