Short promotional announcement for a new course, "Vector Databases: from Embeddings to Applications with Weaviate." The host (Andrew) introduces the course and instructor, Sebastian Vitalette (head of Developer Relations at Weaviate). The instructor summarizes course content: forming embeddings, similarity metrics, scalable search algorithms for billions of entries, retrieval‑augmented generation (RAG), multilingual search, and hands‑on labs to build vector-database-enabled applications. The video positions vector databases as essential for applications like semantic search, recommendations, image recognition, and RAG workflows that let apps use proprietary data with LLMs without fine‑tuning.
Chapters
Hi, I'm excited to introduce vector databases from embeddings to applications. Built in partnership with weaviate and taught by Sebastian Vitalette, vector databases are used in many fields like natural language processing, image recognition, recommended systems, and semantic search. Recently, they've become an integral part of retrieval, augmented generation, or RAG systems. These systems retrieve relevant data, which can even be proprietary data that wasn't available to the LLM during training, and include that data in the prompt sent to the LLM. This enables developers like you to develop chat applications that operate on your own data without needing to train or fine tune an LLM yourself. To use vector databases effectively, it's helpful to understand how they really work. Under the hood, vector databases rely on having useful embeddings to represent the meaning of data, and they also need a way to measure the similarity between different pairs of vectors and also to rapidly search through millions or billions of entries to find a few vectors that are most similar. Understanding these fundamentals will help you to decide when best to apply a vector database to your application. Sebastian is head of Developer Relations at weaviate and he's an expert in vector database technology. He's actually been educating developers for over a decade and in fact his full time job is to help developers like you build successfully using vector databases.
Thanks Andrew. I'm really excited to be teaching this course. In this course you'll learn about vector databases and how to use them to get deeper insights into your data. You build labs that show how to form embeddings and use several search techniques to find similar embeddings. This is what makes vector databases so powerful. You explore algorithms to rapidly search billions of entries and you build several exciting practical applications from retrieval, augmented generation to multilingual search.
All this sounds very exciting. I invite you to join this course and learn how to build your own vector database enabled applications.
