English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 70 lectures (5h 7m) | 3.13 GB
Gain cutting-edge AI skills: Master the LangChain framework to build and deploy real-world AI applications
Are you an aspiring AI engineer excited to integrate AI into your product?
Are you thrilled about the breakthroughs in the field of AI?
Or maybe you’re eager to learn this new and exciting LangChain framework everyone’s talking about.
If yes, then you’ve come to the right place!
Why should you consider taking this LangChain course?
In this Build Chat Applications with OpenAI and LangChain course, we’ll explore the increasingly popular LangChain Python library to develop engaging chatbot applications.
With detailed, step-by-step guidance, you will use OpenAI’s API key to access their powerful large language models (LLMs). Once we have access to foundational models, we’ll utilize LangChain and its integrations to create compelling prompts, add memory, input external data, and link it to third-party tools.
LangChain’s integration with third-party tools distinguishes it by enabling connections to various language models and loading documents in multiple formats. It also allows for selecting suitable embedding models, storing embeddings in a vector store, and linking to search engines, code interpreters, and tools like Wikipedia, GitHub, Gmail, and more.
None of this would be possible without mastering the LangChain Expression Language (LCEL)—essential for developing stateful, context-aware reasoning chatbots. These chatbots remember past conversations, answer questions about unseen data, and tackle more complex problems.
Additionally, we’ll spend much of our time discussing the state-of-the-art Retrieval Augmented Generation (RAG), both theoretically and practically. This technique allows LLM-powered applications to analyze and answer questions about information outside their training data. Ultimately, we’ll create a chatbot that answers students’ questions on courses from the 365 library.
What skills do you gain?
- Integrate existing applications with powerful LLMs.
- Connect to OpenAI’s language and embedding models using an OpenAI API key.
- Develop prompt engineering techniques to enhance AI response performance and relevance.
- Implement RAG to enrich your AI-driven product with a knowledge base.
- Master the LCEL protocol—essential for developing applications with the LangChain Python library.
- Connect external tools to your LLM-powered application.
- Understand the mechanics behind agents and agent executors.
Enhance your career prospects with rare and highly sought-after AI Engineering skills by enrolling in this LangChain and OpenAI course.
What you’ll learn
- Master LangChain to seamlessly integrate existing applications with potent Large Language Models (LLMs)
- Learn to connect to OpenAI’s language and embedding models
- Develop prompt engineering skills that improve performance and relevance of AI responses
- Apply the state-of-the-art Retrieval Augmented Generation (RAG) technique to empower your AI-driven product with a knowledge base
- Leverage AI to open up endless opportunities for your organization
- Enhance your career prospects with rare and highly sought-after AI Engineering skills
Table of Contents
Introduction to the Course
1 Introduction to the Course
2 Business Applications of LangChain
3 What Makes LangChain Powerful
4 What Does the Course Cover
Tokens Models and Prices
5 Tokens
6 Models and Prices
Setting Up the Environment
7 Setting Up a Custom Anaconda Environment for Jupyter Integration
8 Obtaining an OpenAI API Key
9 Setting the API Key as an Environment Variable
The OpenAI API
10 First Steps
11 System User and Assistant Roles
12 Creating a Sarcastic Chatbot
13 Temperature Max Tokens and Streaming
Model Inputs
14 The LangChain Framework
15 ChatOpenAI
16 System and Human Messages
17 AI Messages
18 Prompt Templates and Prompt Values
19 Chat Prompt Templates and Chat Prompt Values
20 FewShot Chat Message Prompt Templates
21 LLMChain
Message History and Chatbot Memory
22 Chat Message History
23 Conversation Buffer Memory Implementing the Setup
24 Conversation Buffer Memory Configuring the Chain
25 Conversation Buffer Window Memory
26 Conversation Summary Memory
27 Combined Memory
Output Parsers
28 String Output Parser
29 CommaSeparated List Output Parser
30 Datetime Output Parser
LangChain Expression Language LCEL
31 Piping a Prompt Model and an Output Parser
32 Batching
33 Streaming
34 The Runnable and RunnableSequence Classes
35 Piping Chains and the RunnablePassthrough Class
36 Graphing Runnables
37 RunnableParallel
38 Piping a RunnableParallel with Other Runnables
39 RunnableLambda
40 The chain Decorator
41 Adding Memory to a Chain Part 1 Implementing the Setup
42 RunnablePassthrough with Additional Keys
43 Itemgetter
44 Adding Memory to a Chain Part 2 Creating the Chain
Retrieval Augmented Generation RAG
45 How to Integrate Custom Data into an LLM
46 Introduction to RAG
47 Introduction to Document Loading and Splitting
48 Introduction to Document Embedding
49 Introduction to Document Storing Retrieval and Generation
50 Indexing Document Loading with PyPDFLoader
51 Indexing Document Loading with Docx2txtLoader
52 Indexing Document Splitting with Character Text Splitter Theory
53 Indexing Document Splitting with Character Text Splitter Code Along
54 Indexing Document Splitting with Markdown Header Text Splitter
55 Indexing Text Embedding with OpenAI
56 Indexing Creating a Chroma Vector Store
57 Indexing Inspecting and Managing Documents in a Vector Store
58 Retrieval Similarity Search
59 Retrieval Maximal Marginal Relevance Search
60 Retrieval Vector StoreBacked Retriever
61 Generation Stuffing Documents
62 Generation Generating a Response
Tools and Agents
63 Introduction to Reasoning Chatbots
64 Tools Toolkits Agents and Agent Executors
65 Fixing the GuessedAtParserWarning
66 Creating a Wikipedia Tool and Piping It to a Chain
67 Creating a Retriever and a Custom Tool
68 LangChain Hub
69 Creating a Tool Calling Agent and an Agent Executor
70 AgentAction and AgentFinish
Resolve the captcha to access the links!