Prerequisite: None
This session will include a moderated Q&A featuring questions from the live audience.
The advent of the vector database has introduced a paradigm shift in data, analytics, and AI from storage to retrieval. Through high-dimensional vectors that represent features or attributes of diverse data types, vector technology enables fast and accurate insights by surfacing related details through mechanisms such as similarity searches. In this session, Krish Krishnan will discuss the power of vector databases, their underlying principles, and the transformative embedding functions that facilitate their use.
Krishnan will explain the key advantage of vector databases: the ability to perform semantic search and retrieval based on vector distance or similarity as opposed to reliance on exact matches or predefined criteria. Through a real-world example, Krishnan will show how vector databases can be utilized to find similar images, documents, and products based on their inherent characteristics, revealing the immense potential of this technology in applications such as natural language processing, computer vision, and recommendation systems. Krishnan will also discuss embeddings and embedding models, and explain why the vector database has earned a place in the modern technology stack.