Course Content
- Introduction (1:03)
- What is a Knowledge Base (2:02)
- Getting the Data (2:06)
- Create the Graph Representation (7:28)
- Augmenting LLMs with a Knowledge Base (3:13)
- Using the Diffbot Graph Transformer (3:43)
- Creating a Local Graph Database (2:16)
- Augmenting an LLM with the Graph Database (5:10)
- Outro (0:39)
- Introduction (0:57)
- Formalizing the Book Writing Process (2:33)
- Setting up the Project (3:05)
- The Main Character (6:42)
- The Title (5:53)
- The Plot (5:19)
- The Chapters List (8:12)
- The Chapters' Plots (14:32)
- The Events List (12:08)
- Writing the Book (9:20)
- Writing to File (4:10)
- Reading the Book (0:49)
- The code from this lesson
- Outro (0:21)
Damien Benveniste, PhD
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 Basics
- Loading and Summarizing Data
- Prompt Engineering Fundamentals
- Vector Database Basics
- Retrieval Augmented Generation
- RAG Optimization and Multimodal RAG
- Augmenting LLMs with a Graph Database
- Augmenting LLMs with tools
- How to Build a Smart Voice Assistant
- How to Automate Writing Novels
- How to Automate Writing Software
The 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!
Warning: during the course, I used a lot of the OpenAI models through their API. If you choose to use the OpenAI API as well, be aware that this will generate additional costs. I expect that reproducing all the examples in the course should not require more than $50 in OpenAI credits. However, all the examples can be reproduced for free if you choose to use open-source LLMs.
Who this course is for:
- Intermediate Python developers curious to learn how to develop software applications with Large Language Models
- Machine Learning enthusiasts that want t to improve their knowledge on Large Language Models
