Vector Databases Fundamentals [NEW]

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction – Course prerequisites and structure

Chapter 2: Source Code and Resources

Lecture 1: Source code and resources

Chapter 3: Vector Databases Deep Dive – Fundamentals

Lecture 1: Introduction to Vector Databases – Full Overview

Lecture 2: Why Vector Databases

Lecture 3: Vector Databases – Benefits and Advantages

Chapter 4: Traditional vs Vector Databases – Differences

Lecture 1: Traditional vs Vector Databases – Limitations and Challenges

Lecture 2: Vector Databases & Embeddings – Full Work Flow

Lecture 3: Embeddings vs Vectors – Differences

Lecture 4: Vector Databases – How They Work and Advantages

Lecture 5: Vector Databases Use Cases

Lecture 6: Vector and Traditional Databases – Summary

Chapter 5: Vector Databases Solutions – Top 5 Vector Databases

Lecture 1: The Top 5 Vector Databases – Overview

Lecture 2: Understanding LLM (Large Language Models)

Lecture 3: Check in

Chapter 6: Building Vector Databases – Hands-on – Chroma Vector Database

Lecture 1: Development Environment Setup

Lecture 2: Setup VS-Code, Python and OpenAI API Key

Lecture 3: Chroma Database workflow

Lecture 4: Creating a Chroma Vector Database & Adding Documents & Querying them

Lecture 5: Looping Through the Results & Showing Similarity Search Results

Lecture 6: Chroma Default Embedding Function

Lecture 7: Chroma Vector Database – Persisting Data and Saving

Lecture 8: Creating an OpenAI Embeddings – Raw without Chroma

Lecture 9: Using OpenAIs Embedding API to Create Embedding in Chroma

Lecture 10: Vector Databases Metrics and Data Structures

Lecture 11: Section Summary

Chapter 7: Common Measures of Vector Similarity

Lecture 1: Vector Similarity Deep Dive – Cosine Similarity

Lecture 2: Euclidean Distance – L2 Norm

Lecture 3: Dot Product

Lecture 4: Section Summary

Chapter 8: Vector Databases and LLM – the Full Workflow

Lecture 1: Vector Databases and LLM – Deep Dive

Lecture 2: Loading all Documents

Lecture 3: Generating Embeddings from Documents & Insert then into Chroma Database

Lecture 4: Getting the Relevant Chunks when Given a Query

Lecture 5: Using OpenAI LLM to Generate Response – Full Flow

Lecture 6: Section Summary

Chapter 9: Vector Databases & the Langchain Framework

Lecture 1: The LangChain Framework – Quick Overview

Lecture 2: Getting started with LangChain and the OpenAIChat Wrapper

Lecture 3: Loading Documents with LangChain Document Loader

Lecture 4: Splitting the Documents with LangChain

Lecture 5: Creating a Chroma Vector Database with LangChain

Lecture 6: Getting the Response from the Model – the Complete WorkFlow

Chapter 10: Pinecone Vector Database

Lecture 1: Pinecone – Deep Dive

Lecture 2: Create Pinecone Account & Dashboard Overview

Lecture 3: Creating our Pinecone Index in Code

Lecture 4: Upserting and Querying our Pinecone Index

Lecture 5: Querying Pinecone Manually in the Dashboard

Lecture 6: Using LangChain Pinecone Wrapper – Create Index and Upsert & Similarity Search

Lecture 7: Creating a Retriever and Chain Objects & a LLM to get a Response

Lecture 8: Clean up – Delete Pinecone Index

Lecture 9: Challenge – Explore other Vector Database

Lecture 10: Section Summary

Chapter 11: Choosing the Right Vector Database

Lecture 1: Choosing the Right Vector Database – Comparison Tables

Lecture 2: Which Database Should I Choose?

Lecture 3: Choosing the Right Database – Criterias

Chapter 12: Wrap up & Next Steps

Lecture 1: Congratulations and Next Steps