/mindsdb

Predictive AI layer for existing databases.

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

MindsDB

MindsDB workflow

Python supported PyPi Version PyPi Downloads Docker pulls MindsDB Website MindsDB Community

MindsDB is a predictive platform that makes databases intelligent and machine learning easy to use. It allows data analysts to build and visualize forecasts in BI dashboards without going through the complexity of ML pipelines, all through SQL. It also helps data scientists to streamline MLOps by providing advanced instruments for in-database machine learning and optimize ML workflows through a declarative JSON-AI syntax. Tweet


Installation - Overview - Features - Database Integrations - Quickstart - Documentation - Support - Contributing - Mailing lists - License


Machine Learning using SQL

MindsDB

Installation

To install the latest version of MindsDB please pull the following Docker image:

docker pull mindsdb/mindsdb

Or, use PyPI:

pip install mindsdb

Overview

MindsDB automates and abstracts machine learning through virtual AI Tables in databases - all through SQL (MongoDB query syntax is also supported).

You can get forecasts from complex multivariate time-series data or detect anomalies in real-time without building & maintaining ETL pipelines, ML workflows and API integrations.

How it works:

  1. Let MindsDB connect to your database.

  2. Make MindsDB learn from historical data automatically by training a predictor using a single SQL statement. (if you'd rather configure some of your models manually or bring your own, MindsDB supports that too via declarative JSON-AI syntax).

  3. Make predictions immediately by querying MindsDB virtual AI Tables. There’s no need to deploy models.

  4. Visualize forecasts in your BI dashboards, all through standard SQL. AI Tables behave the same way as normal database tables.

Check our docs and blog for tutorials and use case examples.

Features

  • Automatic data pre-processing, feature engineering and encoding.
  • Classification, regression, time-series tasks.
  • Automatic model deployment through virtual AI Tables.
  • Data quality check for potential biases & outliers.
  • Model accuracy scoring and confidence intervals for each prediction.
  • Batch predictions by joining predictor with other tables.
  • Anomaly detection.
  • Model explainability analysis with graphical user interface.
  • GPU support for faster model training.
  • Tune model internals with declarative JSON-AI syntax.
  • Import your own models.
  • HTTP API available

Database Integrations

Connect your Data
Connect MongoDB
Connect MySQL
Connect PostgreSQL
Connect MariaDB
Connect MongoDB
Connect Snowflake
Connect Clickhouse
Connect Cassandra
Connect Redis
Connect SQL Server
Connect Singlestore
Connect ScyllaDB
Connect CockroachDB

❓ 👋 Missing integration?

Quickstart

To get your hands on MindsDB, we recommend using the Docker image or simply sign up for a free cloud account. Feel free to browse documentation for other installation methods and tutorials.

Documentation

You can find the complete documentation of MindsDB at docs.mindsdb.com. Documentation for our HTTP API can be found at apidocs.mindsdb.com.

Support

If you found a bug, please submit an issue on Github.

To get community support, you can:

If you need commercial support, please contact the MindsDB team.

Contributing

Being part of the core team is accessible to anyone who is motivated and wants to be part of that journey!

If you'd like to contribute to the project, refer to the contributing documentation.

Please note that this project is released with a Contributor Code of Conduct. By participating in this project, you agree to abide by its terms.

Current contributors

Made with contributors-img.

Mailing lists

Subscribe to MindsDB Monthly Community Newsletter to get general announcements, release notes, information about MindsDB events, and the latest blog posts. You may also join our beta-users group, and get access to new beta features.

License

MindsDB is licensed under GNU General Public License v3.0