AutoML in MariaDB: train and query machine learning models straight from MariaDB

This video was presented at the MariaDB Server Fest, held online from 14-20 September 2020.

Q&A links

Other links


Our open-source project (MindsDB) makes ML possible straight from MariaDB. It occurred to us that Machine Learning models could be queried in plain SQL, therefore, they could be seen as tables. Furthermore, that ML-models could be created and trained straight from standard SQL insert statements. This approach could simplify and democratize the whole ML engineering process and since there can’t be Machine Learning without data, what better than bringing ML to where the data lives?


Jorge Torres is the Co-founder & CEO of MindsDB and visiting scholar at UC Berkeley. Prior to founding MindsDB, he worked for a number of data-intensive start-ups, most recently working with Aneesh Chopra (the first CTO in the US government) building data systems that analyze billions of patient’s records that led to savings for millions of patients. He started his work on scaling solutions using Machine Learning in early 2008 while working as first full-time engineer at Couchsurfing.

Date and time

  • New York: Thursday September 17: 14.15 – 14.35 / 2.15pm – 2.35pm EDT (UTC -4)