Transform structured business data into actionable insights
What is SAP-RPT-1?
SAP-RPT-1 is a relational pretrained transformer model that delivers accurate predictive insights from structured business data. SAP-RPT-1 uses in-context learning, allowing users to provide data records to generate instant, reliable predictions without any model training.
Pretrained for structured data to eliminate costly and time-consuming model training.
In-context learning to deliver instant results directly from data records at runtime.
Resilient to changing and incomplete data to deliver dependable predictions.
Powered by business data for accurate, enterprise data-driven insights.
Available in two commercial versions in the generative AI hub, each tuned for a different speed and accuracy balance, and also as an open-source release.
Key benefits
Accelerate time to insights
Deploy predictive AI for structured data instantly and reduce weeks of data preparation to hours without the need of model training or specialised ML expertise.
Generate accurate insights from imperfect data
Achieve up to 2X prediction quality compared to narrow AI models and 3.5X compared to language models, even when business data is incomplete or changing. SAP-RPT-1’s resilient architecture is designed to handle real-world data quality challenges that limit traditional models.
Scale predictive power across the enterprise
Leverage a single model for classification and regression, across business units and scenarios, simplifying deployment and reducing the need for hundreds of use case–specific models.
Key features
In-context learning API
SAP-RPT-1 processes classification and regression tasks using real or sample data records provided directly in API calls. The model identifies data patterns within each request context to generate accurate predictions.
Pretrained relational architecture
Built with an inherent understanding of tabular structures, data relationships, and business logic, SAP-RPT-1 handles structured datasets, changing values, and enterprise data formats without custom preprocessing or feature engineering.
No-code testing playground
The SAP-RPT playground enables users to configure prediction scenarios and evaluate model performance through an intuitive, interactive interface. Test multiclass classification and numerical regression using your own data or SAP-provided samples.
Resources
ConTextTab: semantics-aware learning for tabular data
ConTextTab unites language model semantics with table-native efficiency to achieve high performance on real business tabular prediction tasks.
Try SAP-RPT-1
Explore AI-powered predictions in seconds. Upload your CSV or use our sample data files, run real-world scenarios, and see instant insights from your business data with no setup or coding required.