Vector Similarity Search

Overview

Explore the future of search technology in this 49-minute panel discussion featuring experts from Redis, Microsoft, Relevance AI, Superlinked, and Weaviate. Dive into the world of Vector Similarity Search, learning how deep learning and vector representations are revolutionizing search capabilities across various domains. Understand the concept of embeddings, their generation, and the role of vector databases in modern search applications. Discover different types of indices, their applications, and how to integrate them with other services. Gain insights into the growing interest in this field and explore real-world use cases, including contact center analytics, generative search methodologies, and recommendation systems. Learn about off-the-shelf models for specific applications and hear the panelists' excitement about future developments in vector search technology.

Syllabus

– Introduction
– What are Embeddings.
– How to get embeddings?
– What are vector databases
– Types of indices, when you use them, and how to get access?
– How to use indices, and how to combine them with other services.
– Why is there an increased interest in this space?
– Day-to-day things used in workflows
– Contact Center Analytics using Speech API & Open AI
– Generative search methodology
– Recommendation systems and how vector search use case
– Off-the-shelves models for particular use cases
– One thing you’re excited about in this space