Introduction
The realm of enterprise applications is constantly expanding, and the integration of multimedia capabilities, particularly video, is becoming increasingly valuable for communication, training, marketing, and more. While SAP ABAP remains the bedrock for many core business processes, leveraging advanced video generation models like Veo requires bridging the gap between traditional transactional systems and cutting-edge AI. This blog delves into the exciting possibility of invoking Veo models directly from your SAP ABAP applications or Agents to generate compelling videos based on input prompts.
Veo, a powerful video generation model recently released by Google at Google Next 2025, allows you to create dynamic video content from simple textual descriptions or image inputs in seconds. Imagine the potential of automating video creation within your SAP workflows – generating product demos, training materials, marketing snippets, or even visual representations of complex data – all triggered directly from your familiar ABAP environment.
Potential Use Cases within SAP
The ability to invoke Veo video generation from ABAP unlocks a plethora of innovative applications:
- Automated Product Demonstrations: Generate short videos showcasing new products based on product master data in SAP S/4HANA, based on events or data changes within SAP, eliminating manual effort.
- Dynamic Training Materials: Create personalized training videos based on employee roles and learning paths defined in SAP SuccessFactors.
- Marketing Content Generation: Automatically produce promotional videos based on marketing campaigns managed within SAP Marketing Cloud.
- Visualizing Complex Data: Generate animated data visualizations from SAP Business Warehouse (BW) or SAP Analytics Cloud (SAC) to enhance reporting and understanding.
- Personalized Customer Communication: Create tailored video messages for customers based on data in SAP CRM.
- Equipment Maintenance Tutorials: Generate visual guides for maintenance procedures based on equipment master data and maintenance plans in SAP Plant Maintenance.
- Enhanced User Engagement: Embed visually rich content generated by Veo directly within SAP applications or disseminate it through integrated channels.
To successfully invoke Veo models from ABAP, make sure:
- You have a Google Cloud account and project. Please keep the Project Id with you which is available in Google Cloud Dashboard.
- Billing is enabled for your project. See how to confirm that billing is enabled for your project.
- Vertex AI API is enabled for your GCP project.
- You have the latest version of ABAP SDK for Google Cloud installed and configured to invoke Vertex AI API in your SAP system (installation and configuration guide).
ABAP SDK for Google Cloud brings the power of Google Cloud to SAP developers in the programming language of their choice - ABAP. The SDK is available as a set of client libraries in the form of ABAP classes. Using these classes, ABAP developers can connect to and use Google Cloud APIs.
Note: Along with client key configuration, you would also have to setup service mapping of client key to call Vertex AI API endpoint for Veo as it supports location specific endpoint. For this,
- Create a SM59 Type “G” endpoint as below.
- Add an entry in table /GOOG/SERVIC_MAP for the client key and the RFC destination as below.
Invoke Veo models from an ABAP Agent
We would be using class /GOOG/CL_AIPLATFORM_V1 of the SDK to invoke Veo models on Vertex AI platform. You can invoke Veo with a prompt to place the generated video in your choice of GCS folder, below example shows how to do this programmatically using ABAP SDK for Google Cloud.
TYPES:
BEGIN OF ty_instance,
prompt TYPE string,
END OF ty_instance,
tt_instances TYPE STANDARD TABLE OF ty_instance,
BEGIN OF ty_parameters,
sample_count TYPE i,
storage_uri TYPE string,
END OF ty_parameters.
DATA:
ls_input TYPE /goog/cl_aiplatform_v1=>ty_1013,
ls_instance TYPE ty_instance,
lt_instances TYPE tt_instances,
ls_parameters TYPE ty_parameters,
lv_raw TYPE string.
TRY.
* Open HTTP Connection
DATA(lo_client) = NEW /goog/cl_aiplatform_v1( iv_key_name = '<CLIENT_KEY>' ).
* Populate relevant parameters
ls_instance-prompt = '<INPUT_PROMPT>'.
APPEND ls_instance TO lt_instances.
CLEAR ls_instance.
GET REFERENCE OF lt_instances INTO ls_input-instances.
ls_parameters-storage_uri = '<GCS_URI>'.
ls_parameters-sample_count = <SAMPLE_COUNT>.
GET REFERENCE OF ls_parameters INTO ls_input-parameters.
* Call API method: aiplatform.projects.locations.publishers.models.predictLongRunning
CALL METHOD lo_client->predict_long_running_models
EXPORTING
iv_p_projects_id = '<GCP_PROJECT_NAME>'
iv_p_locations_id = '<LOCATION_ID>'
iv_p_publishers_id = 'google'
iv_p_models_id = '<VEO_MODEL_ID>'
is_input = ls_input
IMPORTING
es_raw = lv_raw
es_output = DATA(ls_output)
ev_ret_code = DATA(lv_ret_code)
ev_err_text = DATA(lv_err_text)
es_err_resp = DATA(ls_err_resp).
IF lo_client->is_success( lv_ret_code ).
MESSAGE 'Success' TYPE 'S'.
ELSE.
MESSAGE lv_err_text TYPE 'E'.
ENDIF.
* Close HTTP Connection
lo_client->close( ).
CATCH /goog/cx_sdk INTO DATA(lo_exception).
MESSAGE lo_exception->get_text( ) TYPE 'E'.
ENDTRY.
Replace,
- CLIENT_KEY with the client key configured in ABAP SDK configuration table /GOOG/CLIENT_KEY as per instructions here,
- INPUT_PROMPT with the text based prompt to instruct Veo model to generate the video,
- SAMPLE_COUNT with the number of videos that you would like to generate for the prompt,
- GCS_URI with the target GCS folder URI where you want the generated videos to be placed,
- GCP_PROJECT_NAME with your Google Cloud Project name where Vertex AI API is enabled,
- LOCATION_ID with the region of your Google Cloud project,
- VEO_MODEL_ID with the Veo model ID that you would like to invoke, select one from the list here.
An example invocation
Below is an example invocation of the code snippet when run with below parameter values,
- INPUT_PROMPT: ‘Generate a video of a toy car bursting out of confetti of it’s packaging. Make it fun to be put on the toy company website.’,
- SAMPLE_COUNT: 1,
- GCS_URI: ‘gs://gen-veo-videos/,’
- VEO_MODEL_ID: ‘veo-2.0-generate-001’.
CLIENT_KEY, GCP_PROJECT_NAME and LOCATION_ID can be entered based on your configurations and Google Cloud project setup.
Once executed, the generated video is placed at the GCS folder location.
Here is the video generated for reference.
Bingo….with few configurations and minimum lines of code, we were able to invoke Veo video generation model in SAP ABAP using ABAP SDK for Google Cloud.
There are other input parameters that you can pass along with the prompt and “sample count”. Refer to the link to the list of parameters that you can define under TY_PARAMETERS and pass in LS_INPUT of the code snippet. You can also achieve these features along with text based video generation with Veo.
Conclusion
Integrating the visual power of Veo’s video generation capabilities with the robust functionality of SAP ABAP opens up exciting new avenues for automation, communication, and user engagement within the enterprise. ABAP SDK for Google Cloud provides comprehensive tools to integrate Google’s AI with your SAP ABAP applications or ABAP AI Agents.
The ability to generate videos programmatically from text or image prompts within SAP workflows marks a significant step towards a more dynamic and visually rich enterprise experience.Refer to the blog linked here to show how to invoke Gemini models from your ABAP applications. You can also refer to the blog linked here to invoke Gemini models in free tier without the need of any Google Cloud project.
Let us know your use cases that you would like to explore with Veo by starting a conversation on our Google Cloud Channel.