What you’ll learn

With Redis, you can build advanced use cases thanks to the support of the vector data type. This course introduces you to semantic search and explains its advantages over the traditional full-text search. You will understand the concepts of vector embeddings and embedding models, learn to use Redis as a vector database and perform vector searches. To complete the picture, you will comprehend how Redis represents the core component of applications integrated with Large Language Models. In addition, you will understand how Redis is well-integrated in the most popular frameworks like LangChain, LlamaIndex, or FeatureForm and service providers such as Amazon Bedrock or AzureOpenAI to leverage the vector capabilities out-of-the-box.

What you’ll build

Through the course, you will put the main concepts from the theory into practice and test the main ideas behind semantic search using the most popular programming languages: Python, Java, C#, and JavaScript. You will also run examples with Jupiter notebooks. You will start with a simple application to perform a semantic search of texts and understand how to model the data for complex applications with real data. In particular, you will implement:

• A smart recommender system with a real dataset of books
• A face recognition system leveraging vector search to spot the identity of test subjects using their face
• An AI-assisted intelligent chatbot integrated with OpenAI ChatGPT

You will define the data model using the Redis Hash and JSON data types and understand how to lay down the skeleton of such projects with a few lines of code and the most popular client libraries, including RedisVL, the native Python client library optimized to work with vectors.

Course Outline