As data scientists and machine learning professionals make the transition from theory to applied data science, they naturally expand their skill set beyond Python or Pandas.  They need to understand how to leverage a key-value store or database to store their embeddings or features, and how to load and fetch them very quickly for online predictions or to perform complex operations in milliseconds for real-time use cases. Because of that, Redis — the super-fast in-memory database, is being increasingly used for machine learning: from caching, messaging, and fast data ingestion, to vector similarity search and online feature stores.

This crash course is for ML and Data Engineers looking to learn more about deploying real-time AI/ML at scale, as well as Data Scientists making the transition from theory to applied Data Science. It assumes no prior experience in Redis.

• What a key-value store is, and the difference between Redis and SQL databases
• Which key machine learning concepts and use cases Redis enables
• Which data types and structures can be stored in Redis
• Key database considerations for deploying real-time AI/ML at scale
• Redis as an online feature store – why and how to get started
• Redis as a vector database for embeddings and neural search – why and how to get started