LangChain in Action: Develop LLM-Powered Applications

Course Curriculum

Chapter 1: Before we start…

Lecture 1: What to expect from this course and how to get all ressources

Lecture 2: Why this course is different

Lecture 3: Prerequisites

Lecture 4: Essential topics and terms (theory)

Lecture 5: Why this course does not cover Open Source models like LLama2

Lecture 6: Optional: Install Visual Studio Code

Lecture 7: Get the source files with Git from Github

Lecture 8: Create OpenAI Account and create API Key

Chapter 2: Preparation

Lecture 1: What we have to do before delving into LangChain

Lecture 2: Setup of a virtual environment

Lecture 3: Setup OpenAI Api-Key as environment variable

Lecture 4: Exploring the vanilla OpenAI package

Chapter 3: LangChain Basics

Lecture 1: IMPORTANT NOTE – LANGCHAIN 0.1 Codechanges

Lecture 2: LLM Basics

Lecture 3: Prompting Basics

Lecture 4: Theory: Prompt Engineering Basics

Lecture 5: Few Shot Prompting

Lecture 6: Chain of thought prompting

Lecture 7: Pipeline-Prompts

Lecture 8: Prompt Serialisation

Chapter 4: Chains – From basic to advanced chains

Lecture 1: Introduction to chains

Lecture 2: Basic chains – the LLMChain

Lecture 3: Response Schemas and OutputParsers

Lecture 4: LLMChain with multiple inputs

Lecture 5: SequentialChains

Lecture 6: RouterChains

Chapter 5: Callbacks

Lecture 1: Callbacks

Chapter 6: Memory

Lecture 1: Memory basics – ConversationBufferMemory

Lecture 2: ConversationSummaryMemory

Lecture 3: EXERCISE: Use Memory to build a streamlit Chatbot

Lecture 4: SOLUTION: Chatbot with Streamlit

Chapter 7: OpenAI Function Calling

Lecture 1: OpenAI Function Calling – Vanilla OpenAI Package

Lecture 2: Function Calling with LangChain [DEPRECATED]

Lecture 3: Limits and issues of the langchain Implementation [DEPRECATED]

Lecture 4: Tool/Function Calling with LangChain – The new way

Chapter 8: Retrieval Augmented Generation (RAG)

Lecture 1: RAG – Theory and building blocks

Lecture 2: Loaders and Splitters

Lecture 3: Embeddings – Theory and practice

Lecture 4: VectorStores and Retrievers

Lecture 5: RAG Service with FastAPI

Chapter 9: Agents

Lecture 1: Agents Basics – LLMs learn to use tools

Lecture 2: Agents with a custom RAG-Tool

Lecture 3: ChatAgents

Chapter 10: Indexing API

Lecture 1: Indexing API – keep your documents in sync

Lecture 2: PREREQUISITE: Docker Installation

Lecture 3: Setup of PgVector and RecordManager

Lecture 4: Indexing Documents in practice

Lecture 5: Document Retrieval with PgVector

Chapter 11: LangSmith

Lecture 1: Introduction to LangSmith (User Interface and Hub)

Lecture 2: LangSmith Projects

Lecture 3: LangSmith Datasets and Evaluation

Chapter 12: Microservice Architecture for LLM Applications

Lecture 1: Before you watch this section

Lecture 2: Introduction to Microservice Architecture

Lecture 3: How our Chatbot works in a Microservice Architecture

Lecture 4: Introduction to Docker

Lecture 5: Introduction to Kubernetes

Lecture 6: Deployment of the LLM Microservices to Kubernetes

Chapter 13: LangChain Expression Language (LCEL)

Lecture 1: LangChain Expression Language

Lecture 2: Intro to LangChain Expression Language

Lecture 3: LCEL Part 1 – Pipes and OpenAI Function Calling

Lecture 4: LCEL – Part 2 – VectorStores, ItemGetter, Tools

Lecture 5: LCEL – Part 3 – Arbitrary Functions, Runnable Interface, Fallbacks

Chapter 14: Congratulations!

Lecture 1: Thank you for participating in this course