MindsDB AutoML Server is a new open-source platform designed to accelerate machine learning workflows for people with data inside databases by introducing virtual AI tables. It will add a new predictive AI layer that will let you basically create and consume machine learning models as regular database tables.

Adam and Jorge the creator of MindsDB have written : “With the plethora of data available in databases today, predictive modeling can often be a pain, especially if you need to write complex applications for ingesting data, training encoders and embedders, writing sampling algorithms, training models, optimizing, scheduling, versioning, moving models into production environments, maintaining them and then having to explain the predictions and the degree of confidenceā€¦ we knew there had to be a better way!”

MindsDB features

Some of its amazing features include :

  • AutoML. With MindsDB built-in Automated Machine Learning you can quickly generate the right machine learning model.
  • AI Tables. Move your models instantly to production, reduce resources, and overhead costs with AI Tables that deliver the results as database tables.
  • Explainable AI. Use MindsDB Studio to interpret predictions made by the model. Identify potential data biases, evaluate and visualize model accuracy using the Explainable AI.

MindsDB support MariaDB, MySQL, PostgreSQL, ClickHouse, SQL Server, SnowFlake, and work on MongoDB support is on progress. It’s written in Python so it can be installed on Docker, Windows, Linux, Macos or even from sources.

Enable Automated Machine Learning in MySQL

A database is surely the best place for Machine Learning – because data is the main ingredient of it. And now you can build, train, test & query Machine Learning models using standard SQL queries within a MySQL database!

This doesn’t require hardcore data science knowledge – the whole Machine Learning workflow is automated.

This solution is called AI-Tables and is available in MySQL thanks to integration with an open-source predictive engine from MindsDB. AI-Tables look like normal database tables and return predictions upon being queried as if they were data that exists in the table. In plain SQL, it looks like this:

SELECT <predicted_variable> FROM <ML_model> WHERE <conditions>

The video below explains how it works :

The project is very well documented, and you can find documentation to install, train, and model data for all the supported databases, in addition to integration examples using python native or the SDK.

So globally MindsDB will help you instead of constantly reinventing the wheel by abstracting most of the unnecessary complexities around building, training, and deploying machine learning models. MindsDB provides you with two techniques for this: build and train models as simply as you would write an SQL query, and seamlessly publish and manage machine learning models as virtual tables inside your databases.

It also support support data from other sources, such as Snowflake, s3, SQLite, and any excel, JSON, or CSV file.

The solution is actually being used for reducing financial risk in the payments sector to predicting in-app usage statistics – one user is even trying to predict the price of Bitcoin using sentiment analysis, which sounds really crazy ! Also if you already have models, you can also bring your own models from frameworks like Pytorch, Tensorflow, scikit-learn, Keras, XGBoost, CatBoost, LightGBM, etc. directly into your database.

A new and very promising AI project that provides also commercial support. However the project will always remain free and open-source, because democratizing machine learning is at the core of every decision we make, according to its authors. The project is also backed by the founders of MySQL & MariaDB, which give them more credibility and support to make the solution even better, and launch the cloud edition for those who do not want to worry about DevOps, scalability, and managing GPU clusters.

MindsDB is an open source software released under a GPL v3 license. For more information https://github.com/mindsdb/mindsdb

LEAVE A REPLY

Please enter your comment!
Please enter your name here