Vector databases have quickly become a fundamental component in the GenAI technology stack. They are very powerful tools and unlock many possibilities, but using them in the right way is often a challenge and far from straightforward.
This talk will take you on a guided tour to vector databases, laying the conceptual and algorithmic foundations and then giving practical insights on how to harness their power - and how to avoid the pitfalls that you should be aware of. Alongside the explanations, we will also run several demos and live examples, including GenAI/RAG applications, to show you the power of vector databases in action.
The aim is to give you practical time-saving tips to better employ vector databases within applications, inspirational/creative usage examples … and a few counter-examples to serve as "don't to this" reminders.
Software engineer at DataStax, chiefly interested in AI and databases. Stefano has authored the LangChain integration with Apache Cassandra™ and DataStax Astra DB, and has developed toolkits and SDKs for AI-oriented usage of these databases along the way. A theoretical physicist by education, past work experiences include developer relations, data engineering, software architecture, fundamental re...