Redis Vector Store and RAG

Build AI search systems using Redis Vector Database, semantic search, embeddings, and Retrieval Augmented Generation

What you’ll learn
Understand how vector embeddings work and how they enable semantic search in AI applications.
Learn how to build a Redis Vector Database from scratch using Redis Stack and Python.
Implement vector similarity search using Redis and HNSW indexing for fast semantic retrieval.
Build a complete Retrieval Augmented Generation (RAG) pipeline using Redis Vector Store and LLMs.

Requirements
Basic understanding of Python programming will be helpful.

Description
Artificial Intelligence applications today rely heavily on vector databases and semantic search to retrieve knowledge efficiently. In this course, you will learn how to build powerful AI systems using Redis Vector Database and Retrieval Augmented Generation (RAG).

This course provides a hands-on, practical approach to understanding how modern AI applications store and retrieve information using vector embeddings. You will learn how to convert documents into embeddings, store them inside Redis, and perform high-performance vector similarity search.

We will start by understanding the fundamentals of embeddings, vector databases, and semantic search. Then you will learn how to use Redis Stack and RedisVL to create and manage a vector index.

You will also build a complete Retrieval Augmented Generation (RAG) pipeline where Redis retrieves the most relevant information and an LLM generates accurate answers based on that context.

Throughout the course, we will implement real working examples using Python, including document processing, vector storage, similarity search, and AI-powered question answering.

By the end of this course, you will understand how modern AI systems like ChatGPT with custom knowledge bases work behind the scenes.

If you want to learn how to build scalable AI search and knowledge systems using Redis, this course will give you the practical skills you need.

Who this course is for
Backend developers interested in implementing semantic search and RAG systems.