AI As Data

Models often sit outside the warehouse, so every prediction needs a separate service. The page treats them instead as AI tables you query with SQL, through MindsDB: what the server does, who it is for, and the article that introduces the idea.

The tool behind the idea is MindsDB ML-SQL Server enables machine learning workflows for the most powerful databases and data warehouses using SQL. The code is on GitHub. Both addresses now present the company's newer product, MindsHub, a unified workspace for choosing among AI models and providers.

The same server serves three audiences. Developers can quickly add AI capabilities to your applications. Data Scientists can streamline MLOps by deploying ML models as AI Tables. Data Analysts can easily make forecasts on complex data (like multivariate time-series with high cardinality) and visualize them in BI tools like Tableau.

The AI-table idea itself is explained in Javi's Medium article, Introduction to AI Tables, which shows how to integrate ML inside databases using MindsDB. The same Medium article is also at its original address: https://towardsdatascience.com/introduction-to-ai-tables-a719251e1a58