What Is a Vector Database?

What is a vector database? And how can vector database offered as a cloud service help with machine learning?
 
I discuss this emerging technology with Pinecone Systems founder and CEO Edo Liberty in the very first episode of the new Cloud Database Report Podcast. 
 
Pinecone, a startup, came onto the radar earlier this year when it released its new cloud-native vector database into pubic beta. A vector database stores, searches, and retrieves vectors, which are long strings of numbers representing documents, images, and other data types used in machine learning applications. Use cases include recommendations, personalization, image search, and deduplication of records.
 
Pinecone aims to simplify and accelerate a process that until now has been a customized solution for many machine learning projects. "All the infrastructure [organizations] have doesn't quite work for this kind of data. It's not a graph, it's not a key value, it's not a row in a table,” Liberty explains. “It's a high-dimensional vector, and you have to deal with it.”

Our conversation ranged from the nitty-gritty of vectors and semantic search to business use cases and cloud database platforms. 

Listen here: Pinecone Systems CEO Edo Liberty: The Cloud Database Report Podcast

We will be watching Pinecone closely. The company's lead investor is Wing Venture Capital, and Wing founding partner Peter Wagner joined the Pinecone board. Wagner was an early investor in Snowflake, so comparisons will be hard to ignore.