This tutorial helps build a real-time product recommendation system using content-based filtering and vector similarity search, leveraging tools like Redis and DocArray. Recommendation systems are crucial for e-commerce sites to generate good conversions and maintain customer loyalty. The system uses CLIP-as-service to encode visual data and exploits all modalities of the data by modeling user and items as feature vectors. Vector similarity is computed in real-time using efficient techniques such as Hierarchical Navigable Small World (HNSW), implemented in vector databases like Redis. DocArray serves as a universal vector database client with support for multimodal data, making it easy to build a recommendation system in just a few lines of code. The procedure involves provisioning a Redis instance, installing necessary tools, and assembling the tools for the application. The tutorial demonstrates how to create a weighted average of the embeddings of recently-viewed items to recommend products based on user filters and view history, taking into account the importance of recent items.