This document describes how to install and configure the Vertex AI SDK for ABAP in your SAP environment.
Installation
On-premises or any cloud edition
When you install the version 1.8 of the on-premises or any cloud edition of ABAP SDK for Google Cloud, the Vertex AI SDK for ABAP is installed for you. For information about the installation steps, see Install and configure the on-premises or any cloud edition of ABAP SDK for Google Cloud.
If you're already using version 1.7 or earlier of the on-premises or any cloud edition of ABAP SDK for Google Cloud, then update your SDK to the latest version to get the Vertex AI SDK for ABAP. For more information, see Update ABAP SDK for Google Cloud.
SAP BTP edition
When you install the version 1.1 of the SAP BTP edition of ABAP SDK for Google Cloud, the Vertex AI SDK for ABAP is installed for you. For information about the installation steps, see Install and configure the SAP BTP edition of ABAP SDK for Google Cloud.
We understand that access to Vertex AI and cloud resources might be limited for some developers. To enable prototyping and experimentation with minimal setup, see Quick prototyping with Gemini.
Enable the Vertex AI API
Enable the Vertex AI API in your Google Cloud project.
For information about how to enable Google Cloud APIs, see Enabling APIs.
Authentication
On-premises or any cloud edition
Once you set up authentication to access Google Cloud APIs in your on-premises or any cloud edition of ABAP SDK for Google Cloud, the Vertex AI SDK for ABAP utilizes the same authentication method to access the Vertex AI API. For information about how to set up authentication in the on-premises or any cloud edition of ABAP SDK for Google Cloud, see Authentication overview.
Make a note of the client key that you've created as part of the authentication setup. You use this client key when configuring AI model generation parameters and search parameters.
SAP BTP edition
Once you set up authentication to access Google Cloud APIs in your SAP BTP edition of ABAP SDK for Google Cloud, the Vertex AI SDK for ABAP utilizes the same authentication method to access the Vertex AI API. For information about how to set up authentication in the SAP BTP edition of ABAP SDK for Google Cloud, see Authentication overview.
Make a note of the client key that you've created as part of the authentication setup. You use this client key when configuring AI model generation parameters and search parameters.
IAM permissions
Ensure that the dedicated service account for API access that you've configured in the client key table has access to the Vertex AI resources.
Vertex AI
To use the Vertex AI resources, you must grant the
Vertex AI User (roles/aiplatform.user)
role to the dedicated service account to which you have granted
permissions to access the Vertex AI API.
If you need to provide specific permissions to create, modify, deploy artifacts, then grant specific Vertex AI IAM permissions as appropriate.
Vertex AI Feature Store
To use the Vertex AI Feature Store, you must grant the following roles to the service account:
| AI capability | Required IAM roles |
|---|---|
| Vertex AI Feature Store |
Verify the addition of Fiori apps to the launchpad
On-premises or any cloud edition
You can skip this section because it doesn't apply to the on-premises or any cloud edition of ABAP SDK for Google Cloud.
SAP BTP edition
To let your administrators and developers configure the model generation parameters and the Vector Search parameters, the SAP BTP edition of ABAP SDK for Google Cloud provides SAP Fiori apps. The SDK also provides display-only Fiori apps for viewing the maintained parameters.
You add these Fiori apps to your launchpad while you're installing the SAP BTP edition of ABAP SDK for Google Cloud. Verify that these apps are available in your launchpad. For more information, see Add Fiori apps to the launchpad.
Configure the model generation parameters
Large language models (LLMs) are deep learning models trained on massive amounts of text data. A model includes parameter values that control how the model generates a response. You can get different results from the model by changing the parameter values.
To define the generation parameters
for a model, the Vertex AI SDK for ABAP uses the table /GOOG/AI_CONFIG.
To configure the generation parameters for a model, perform the following steps:
On-premises or any cloud edition
In SAP GUI, execute the transaction code
/GOOG/SDK_IMG.Alternatively, execute the transaction code
SPRO, and then click SAP Reference IMG.Click ABAP SDK for Google Cloud > Basic Settings > Vertex AI SDK: Configure Model Generation Parameters.
Click New Entries.
Enter values for the following fields:
Field Data type Description Model Key String A unique name that you specify to identify the model configuration, such as
Gemini.You use this model key while instantiating the generative model class or the embeddings class to specify the generation configuration to take effect.
Model ID String Model ID of the LLM, such as
gemini-1.5-flash-001.For information about Vertex AI model versions, see Model versions and lifecycle.
Google Cloud Key Name String The client key that you've configured for authentication to Google Cloud during the authentication setup. Google Cloud Region Location ID String The location ID of the Google Cloud region where the Vertex AI features that you want to use are available.
Typically, you use the region closest to your physical location or the physical location of your intended users. For more information, see Vertex AI locations.
Publisher ID of the LLM String Optional. The publisher of the LLM, such as google.Response MIME type String Optional. Output response MIME type of the generated candidate text. Supported MIME type: text/plain: (default) Text output.application/json: JSON response in the candidates.
Randomness temperature String Optional. Controls the randomness of predictions. For more information, see Temperature.
Range: [0.0, 1.0]
Top-K Sampling Float Optional. Top-K changes how the model selects tokens for output.
Specify a lower value for less random responses and a higher value for more random responses. For more information, see Top-K.
Range: [1, 40]
Top-P Sampling Float Optional. Top-P changes how the model selects tokens for output.
Specify a lower value for less random responses and a higher value for more random responses. For more information, see Top-P.
Range: [0.0, 1.0]
Maximum number of output tokens per msg Integer Optional. Maximum number of tokens that can be generated in the response. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words.
Specify a lower value for shorter responses and a higher value for potentially longer responses.
Positive Penalties Float Optional. Positive values penalize tokens that have appeared in the generated text, thus increasing the possibility of generating more diverse topics.
Range: [-2.0, 2.0]
Frequency Penalties Float Optional. Positive values penalize tokens that repeatedly appear in the generated text, thus decreasing the possibility of repeating the same content.
Range: [-2.0, 2.0]
If you don't provide a value for an optional parameter, then the SDK uses the default value of the parameter specific to the model version configured in
Model ID.Save the new entry.
SAP BTP edition
Access the SAP Fiori launchpad.
Go to the space that contains the Fiori apps for SDK configuration.
Open the Vertex AI SDK: Configure Model Generation Parameters app.
Click Create.
In the Create dialog that appears, enter a value for the Model Key field, and then click Continue.
Enter values for the fields that appear.
The following table describes the fields and how they correspond to the model generation parameters:
Field Data type Description Model Key String A unique name that you specify to identify the model configuration, such as
Gemini.You use this model key while instantiating the generative model class or the embeddings class to specify the generation configuration to take effect.
Model ID String Model ID of the LLM, such as
gemini-1.5-flash-001.For information about Vertex AI model versions, see Model versions and lifecycle.
Google Cloud Key Name String The client key that you've configured for authentication to Google Cloud during the authentication setup. Google Cloud Region Location ID String The location ID of the Google Cloud region where the Vertex AI features that you want to use are available.
Typically, you use the region closest to your physical location or the physical location of your intended users. For more information, see Vertex AI locations.
Publisher ID of the LLM String Optional. The publisher of the LLM, such as google.Response MIME type String Optional. Output response MIME type of the generated candidate text. Supported MIME type: text/plain: (default) Text output.application/json: JSON response in the candidates.
Randomness temperature String Optional. Controls the randomness of predictions. For more information, see Temperature.
Range: [0.0, 1.0]
Top-K Sampling Float Optional. Top-K changes how the model selects tokens for output.
Specify a lower value for less random responses and a higher value for more random responses. For more information, see Top-K.
Range: [1, 40]
Top-P Sampling Float Optional. Top-P changes how the model selects tokens for output.
Specify a lower value for less random responses and a higher value for more random responses. For more information, see Top-P.
Range: [0.0, 1.0]
Maximum number of output tokens per msg Integer Optional. Maximum number of tokens that can be generated in the response. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words.
Specify a lower value for shorter responses and a higher value for potentially longer responses.
Positive Penalties Float Optional. Positive values penalize tokens that have appeared in the generated text, thus increasing the possibility of generating more diverse topics.
Range: [-2.0, 2.0]
Frequency Penalties Float Optional. Positive values penalize tokens that repeatedly appear in the generated text, thus decreasing the possibility of repeating the same content.
Range: [-2.0, 2.0]
If you don't provide a value for an optional parameter, then the SDK uses the default value of the parameter specific to the model version configured in
Model ID.Click Create to save the entry.
Configure the Vector Search parameters
To define Vector Search configurations, the Vertex AI SDK for ABAP
uses the table /GOOG/SEARCHCONF.
To configure the Vector Search parameters, perform the following steps:
On-premises or any cloud edition
In SAP GUI, execute the transaction code
/GOOG/SDK_IMG.Alternatively, execute the transaction code
SPRO, and then click SAP Reference IMG.Click ABAP SDK for Google Cloud > Basic Settings > Vertex AI SDK: Configure Vector Search Parameters.
Click New Entries.
Enter values for the following fields:
Field Data type Description Search Key String A unique name that you specify to identify the search configuration. Google Cloud Key Name String The client key that you've configured for authentication to Google Cloud during the authentication setup. Google Cloud Region Location ID String The location ID of the Google Cloud region where the Vertex AI features that you want to use are available.
Typically, you use the region closest to your physical location or the physical location of your intended users. For more information, see Vertex AI locations.
Deployment ID of Vector Index String The deployment ID of an index. When you deploy an index to an endpoint, you assign it a unique deployment ID. For information about index deployment, see Deploy a vector index to an index endpoint.
Vector Index Endpoint ID String The ID of the index endpoint to which the index is deployed to.
For information about index endpoint, see Create a vector index endpoint.
Save the new entry.
SAP BTP edition
Access the SAP Fiori launchpad.
Go to the space that contains the Fiori apps for SDK configuration.
Open the Vertex AI SDK: Vector Search Configuration app.
Click Create.
In the Create dialog that appears, enter a value for the Model Key field, and then click Continue.
Enter values for the fields that appear.
The following table describes the fields and how they correspond to the Vector Search parameters:
Field Data type Description Search Key String A unique name that you specify to identify the search configuration. Google Cloud Key Name String The client key that you've configured for authentication to Google Cloud during the authentication setup. Google Cloud Region Location ID String The location ID of the Google Cloud region where the Vertex AI features that you want to use are available.
Typically, you use the region closest to your physical location or the physical location of your intended users. For more information, see Vertex AI locations.
Deployment ID of Vector Index String The deployment ID of an index. When you deploy an index to an endpoint, you assign it a unique deployment ID. For information about index deployment, see Deploy a vector index to an index endpoint.
Vector Index Endpoint ID String The ID of the index endpoint to which the index is deployed to.
For information about index endpoint, see Create a vector index endpoint.
Click Create to save the entry.
What's next
- Explore the built-in Generative AI demos for SAP.
- Learn about Generative AI on Vertex AI for SAP.