SAP-RPT Playground | Try with your own data or SAP-provided example datasets

Introduction

SAP-RPT is a relational pretrained foundation model that delivers accurate predictive insights from structured business data. It uses in-context learning, allowing users to provide example records directly in API calls, to generate instant, reliable predictions without any model training.

Key Features

Pretrained Model

Eliminates costly and time-consuming model training

In-Context Learning

Instant results through example records at runtime

Data Resilient

Delivers dependable predictions even with changing data

Business-Grounded

Accurate, enterprise data-driven insights

Natural Language Interface

Ask questions in natural language via Chat-RPT

What-If Scenarios

Simulate changes and predict outcomes instantly

Uploading CSV Data

Supported File Format

SAP-RPT accepts CSV (Comma-Separated Values) files with the following specifications:

File extension: .csv
Maximum file size: 5MB
First row should contain column headers
Data should be properly formatted with consistent columns

Limitations

Maximum rows: 2,073 rows per file
Maximum columns: 100 columns per file
Maximum cell length: 1,000 characters per cell
Maximum column name length: 100 characters

Best Practices

Ensure your data is clean and free of missing values where possible
Use descriptive column names (under 100 characters)
Keep consistent data types within each column
Remove any unnecessary columns before upload

API Tokens

Authenticate programmatic requests to SAP-RPT

Create and manage API tokens in Settings. You can create multiple tokens for different tasks — give each a descriptive name so you can easily identify which token is used for what.

Best Practices

Create a separate token per environment or use case (e.g. "production", "development", "local testing")
Always specify a meaningful name when creating a token
Revoke or delete tokens immediately if they are leaked or no longer needed
Never commit tokens to version control or share them in public forums

Usage

Include your API token in the Authorization header:

curl -X POST https://rpt.cloud.sap/api/predict \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"rows": [...]}'