/mindsdb

A low-code Machine Learning platform to help developers build #AI solutions

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

MindsDB

ROSS Index - Fastest Growing Open-Source Startups | Runa Capital

MindsDB workflow Python supported PyPi Version
PyPI - Downloads Docker pulls MindsDB Website MindsDB Community
Launch in Deepnote
Open in Gitpod


MindsDB is an emerging low-code machine learning platform to help developers easily build #AI-powered solutions Tweet

NEW! Check-out the rewards and community programs.


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


MindsDB automates and integrates top machine learning frameworks (including GPT-4) into the data stack as "AI Tables" to streamline the integration of AI into applications, making it accessible to developers of all skill levels. "AI tables" allow you to get predictions via SQL queries and continuously learn from your data.



MindsDB

Use cases

Here are some popular use cases you can build with MindsDB:

  • Conversational AI: Leverage MindsDB native integrations with data platforms and pre-trained large language models, like OpenAI's GPT, to quickly build conversational AI solutions without the overhead of managing complex data pipelines.
  • Fraud Detection: MindsDB can help developers build models to detect fraudulent activity in financial transactions, eCommerce platforms etc. Sales Forecasting: MindsDB can be used to develop models to predict future sales based on historical sales data, allowing businesses to make better-informed decisions.
  • Customer Segmentation: MindsDB can help developers segment customers based on their behavior, preferences, and other factors, allowing businesses to tailor their marketing efforts.
  • Sentiment analysis: MindsDB native integration with pre-trained models like OpenAI GPT or Hugging Face can be used to analyze the sentiment of a text data, such as a customer reviews - in a single command, instead of individual API calls and ETL-ing data.
  • Predictive Maintenance: MindsDB can be used to build models to predict when equipment or machinery is likely to fail, allowing for proactive maintenance and minimizing downtime.

See more examples and community tutorials here

Demo

You can try MindsDB using our demo environment with sample data for most popular use cases.

Installation

The prefered way is to use MindsDB Cloud free demo instance or use a dedicated instance. If you want to move to production use the AWS AMI image/

To install locally or on-premise pull the latest Docker image:

docker pull mindsdb/mindsdb

How it works

  1. First, CONNECT MindsDB to your data platform. We support 70+ data platforms and this list is constantly growing. If you can’t find the integration you need, please let us know.
  2. Run the CREATE MODEL query pointing to your data table or a view, that will automatically create and deploy a machine learning model as an AI Table.
    1. If you have an NLP use case, CREATE MODEL will integrate the AI Table with already pre-trained model you choose (like OpenAI’s GPT-3 or Hugging Face models).
    2. Please check the docs if you want to have manual control over model engineering.
  3. JOIN the model with your database tables to make predictions for thousands or even millions of data points at once, or run SELECT statements or API calls to make one time predictions.
  4. Set up a JOB to automate your model re-training cycle and predictions pipelines for the new incoming data.

Follow the quickstart guide with sample data to get on-boarded as fast as possible.

Database Integrations

MindsDB works with most of the SQL and NoSQL databases, data lakes, data Streams and popular applications.

Connect your Data Connect your Data Connect your Data
Connect Apache Kafka Connect Microsoft Access Oracle Badge
Connect Amazon Redshift Airtable Badge Pinot Badge
Connect Cassandra DataStax Badge Amazon S3 Badge
Connect CockroachDB ckan Badge Supabase Badge
Connect Clickhouse Google Big Query Badge SQLite Badge
Connect MariaDB Couchbase Badge TiDB Badge
Connect SQL Server CrateDB Badge Timescale Badge
Connect MongoDB DoIt Badge Amazon DynamoDB Badge
Connect PostgreSQL IBMDB2 Badge openGauss Badge
Connect MySQL Databricks Badge YugabyteDB Badge
Connect QuestDB Apache Druid Badge StarRocks Badge
Connect Redis Vertica Badge DuckDB Badge
Connect SAP HANA Elastic Badge Cloud Spanner Badge
Connect ScyllaDB Firebird Badge
Connect Singlestore Apache Hive Badge
Connect Teradata Matrixone Badge
Connect Snowflake Informix Badge
Connect Trino Monetdb Badge

❓ 👋 Missing integration?

Documentation

You can find the complete documentation of MindsDB at docs.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 MindsDB team.

Contributing

A great place to start contributing to MindsDB is to check our GitHub projects 🏁

We are always open to suggestions so feel free to open new issues with your ideas and we can guide you!

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.

Also, check out the rewards and community programs.

Current contributors

Made with contributors-img.

Subscribe to updates

Join our Slack community and subscribe to the monthly Developer Newsletter to get product updates, information about MindsDB events and contests, and useful content, like tutorials.

License

MindsDB is licensed under GNU General Public License v3.0