The AI revolution is here, and at its core lies a game-changing technology that most developers haven’t fully explored: vector databases. From powering semantic search to enabling large language models (LLMs) and generative AI, vector databases are reshaping how we build applications with unstructured data like text, images, and audio. But how do you go from curious to capable with this vital technology? That’s where this book comes in. In this hands-on guide, author Nitin Borwankar takes you through the why, what, and how of vector databases, starting with the basic theory behind vector embeddings and progressing to building applications with real-world tools. You’ll learn about Word2vec, how to convert open source SQL databases like SQLite3 and PostgreSQL into vector databases, and how to integrate them into retrieval-augmented generation (RAG) applications. Whether you’re a Python developer, data engineer, or ML practitioner, this book gives you the foundation to leverage vector databases confidently in your AI projects.

• Understand the connection between vector databases, embeddings, and LLMs

• Learn practical approaches for transforming SQL databases into vector databases

• Build RAG applications for both personal and enterprise use

• Apply vector databases to solve real-world AI challenges

• Learn how to use vector databases with LLMs to build applications

Table of Contents

Chapter 1. Introduction to Vector Databases

Chapter 2. Embeddings

Chapter 3. Similarity Search with FAISS

Chapter 4. Semantic Search with SQLite3

Chapter 5. Building an ArXiv Paper Search System with PostgreSQL pgvector

Chapter 6. Building a Retrieval-Augmented Generation System with SQLite VSS and Ollama

Chapter 7. Building a Scientific RAG System with PostgreSQL and pgvector

Chapter 8. Building a Complete Conversation Search and RAG System

Chapter 9. Vector Query Language

About the Author

Nitin Borwankar is a seasoned data scientist and database professional, known for his contributions to data education and open source machine learning tools over a career spanning three decades. He is a frequent conference speaker, offering a pragmatic approach to AI and large language models