/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 a Server for Artificial Intelligence Logic, enabling developers to ship AI powered systems from prototyping & experimentation to production in a fast & scalable way. Tweet

What can you build with MindsDB?

  • Question Answering: This is useful when you have data (we support more than 120 data sources) and you need answers from your data given a question in natural language.
  • Semantic Search: Similar to Question Answering, but in this case, you want to retrieve specific parts of your data where the answer to a question may exist.
  • AI Agent serving: This is useful when you want to publish your AI Agents to enterprise conversational applications like Slack, email, Twilio, etc.
  • Recommendation systems: When you use your data to help predict, narrow down, and find what people are looking for among an exponentially growing number of options.
  • Time Series Forecasting: When you want to use your historical data to estimate how things will look in the future.
  • AI Automation pipelines: When you need your AI systems to consume enterprise data and have the AI output stored back into your enterprise tools in an automated way.

Generative AI Tables

MindsDB empowers developers to harness the power of AI by treating AI models as (Generative AI Tables). These tables are capable of learning from data in enterprise data sources. This abstraction makes AI highly accessible, allowing development teams to create AI-driven applications using their existing skills.

MindsDB

The data-centric approach of MindsDB AI Logic server brings the process closer to the source of the data minimizing the need to build and maintain data pipelines and ETL’ing, speeding up the time to deployment and reducing complexity and because it'sa server, everything you build on top of mindsdb is automatically ready for production.

MindsDB has an active and helpful community. Feel free to join our Slack and check-out the rewards and community programs. P.S. If you like our open-source project we'd appreciate if you star it on GitHub ⭐!


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


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. CONNECT MindsDB to your data platform. We support 100+ data platforms and this list is constantly growing. If you can’t find the integration you need, please let us know.
  2. CREATE MODEL to connect the AI Engine you pick that will learn from your data and serve it as 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 or Hugging Face models).
    2. Please check the docs if you want to have manual control over model engineering.
  3. JOIN such 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 re-training cycle and predictions pipelines for the new incoming data.
  5. Alternatively, use REST API to query the models

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 and popular applications.

Connect your Data Connect your Data Connect your Data
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 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