Skip to main content

Table Completion

Introduction​

This guide demonstrates how to use the SAP AI SDK for Java to predict targets in structured data using SAP RPT models deployed on SAP AI Core.

warning

All classes under any of the ...generated package are generated from an OpenAPI specification. This means that these model and API classes are not guaranteed to be stable and may change with future releases. They are safe to use, but may require updates even in minor releases.

Prerequisites​

Before using the AI Core module, ensure that you have met all the general requirements outlined in the overview. Additionally, include the necessary Maven dependency in your project.

Maven Dependencies​

Add the following dependency to your pom.xml file:

<dependencies>
    <dependency>
        <groupId>com.sap.ai.sdk.foundationmodels</groupId>
        <artifactId>sap-rpt</artifactId>
        <version>${ai-sdk.version}</version>
    </dependency>
</dependencies>

See an example pom in our Spring Boot application

Usage​

warning

SAP RPT module is currently in Beta. The API may change in future minor releases.

In addition to the prerequisites above, we assume you have already set up the following to carry out the examples in this guide:

  • A Deployed RPT Model in SAP AI Core

    • Refer to How to deploy a model to AI Core for setup instructions.

    • Example deployed model from the AI Core /deployments endpoint
      {
        "id": "c4dfbfd3bet3d4f1",
        "createdAt": "2026-01-14T06:29:33Z",
        "modifiedAt": "2026-01-14T06:29:33Z",
        "status": "RUNNING",
        "details": {
          "scaling": {
            "backendDetails": {},
            "backend_details": {}
          },
          "resources": {
            "backendDetails": {
              "model": {
                "name": "sap-rpt-1-small",
                "version": "latest"
              }
            },
            "backend_details": {
              "model": {
                "name": "sap-rpt-1-small",
                "version": "latest"
              }
            }
          }
        },
        "scenarioId": "foundation-models",
        "configurationId": "54fe1b6a-2d4b-4e2f-9f4b-5c8e9f1a2b3c",
        "latestRunningConfigurationId": "54fe1b6a-2d4b-4e2f-9f4b-5c8e9f1a2b3c",
        "lastOperation": "CREATE",
        "targetStatus": "RUNNING",
        "submissionTime": "2026-01-14T06:30:08Z",
        "startTime": "2026-01-14T06:31:44Z",
        "configurationName": "sap-rpt-1-small",
        "deploymentUrl": "https://api.ai.intprod-eu12.eu-central-1.aws.ml.hana.ondemand.com/v2/inference/deployments/c4dfbfd3bet3d4f1"
      }

Simple table completion​

Predict missing targets in tabular data using RptClient with a SAP RPT model.

List<Map<String, RowsInnerValue>> rows =
    List.of(
        Map.of(
            "fruit", RowsInnerValue.create("Apple"),
            "category", RowsInnerValue.create("[PREDICT]")),
        Map.of(
            "fruit", RowsInnerValue.create("Banana"),
            "category", RowsInnerValue.create("Tropical")),
        Map.of(
            "fruit", RowsInnerValue.create("Mango"),
            "category", RowsInnerValue.create("Tropical")));

var targetColumns =
    List.of(
        TargetColumnConfig.create()
            .name("category")
            .predictionPlaceholder(PredictionPlaceholder.create("[PREDICT]")));

var request =
    PredictRequestPayload.create()
        .predictionConfig(PredictionConfig.create().targetColumns(targetColumns))
        .rows(rows);

PredictResponsePayload response = RptClient.forModel(SAP_RPT_1_SMALL).tableCompletion(request);

Please find more to the example in the sample application including dataSchema specification.

Table Completion with Parquet Files​

For larger datasets, you can provide data as a Parquet file instead of constructing the data structure in code.

var parquetFile = new File("path/to/your/data.parquet");

var targetColumns =
    List.of(
        TargetColumnConfig.create()
            .name("category")
            .predictionPlaceholder(PredictionPlaceholder.create("[PREDICT]"))
            .taskType(TargetColumnConfig.TaskTypeEnum.CLASSIFICATION));

var predictionConfig = PredictionConfig.create().targetColumns(targetColumns);

PredictResponsePayload response =
    RptClient.forModel(SAP_RPT_1_SMALL).tableCompletion(parquetFile, predictionConfig);

Please find more examples in the sample application.