How does the Al API support SAP AI scenarios? Note: There are 2 correct answers to this question.

A. By integrating Al services into business applications

B. By providing a unified framework for operating Al services

C. By integrating Al models into third-party platforms like AWS

D. By managing Kubernetes clusters automatically

What is a part of LLM context optimization?

A. Reducing the model's size to improve efficiency

B. Adjusting the model's output format and style

C. Enhancing the computational speed of the model

D. Providing the model with domain-specific knowledge needed to solve a problem

What is the goal of prompt engineering?

A. To replace human decision-making with automated processes

B. To craft inputs that guide Al systems in generating desired outputs

C. To optimize hardware performance for Al computations

D. To develop new neural network architectures for Al models

What can be done once the training of a machine learning model has been completed in SAP AICore? Note: There are 2 correct answers to this question.

A. The model can be deployed in SAP HANA.

B. The model's accuracy can be optimized directly in SAP HANA.

C. The model can be deployed for inferencing.

D. The model can be registered in the hyperscaler object store.

You want to assign urgency and sentiment categories to a large number of customer emails. You want to get a valid json string output for creating custom applications. You decide to develop a prompt for the same using generative Al hub.
What is the main purpose of the following code in this context?
prompt_test = """Your task is to extract and categorize messages. Here are some examples: {{?technique_examples}}
Use the examples when extract and categorize the following message: {{?input}}
Extract and return a json with the following keys and values:
-"urgency" as one of {{?urgency}}
-"sentiment" as one of {{?sentiment}}
"categories" list of the best matching support category tags from: {{?categories}}
Your complete message should be a valid json string that can be read directly and only contains the keys mentioned in t import random random.seed(42) k = 3
examples random. sample (dev_set, k) example_template = """ {example_input} examples '\n---\n'.join([example_template.format(example_input=example ["message"], example_output=json.dumps (example[ f_test = partial (send_request, prompt=prompt_test, technique_examples examples, **option_lists) response = f_test(input=mail["message"])

A. Generate random examples for language model training

B. Evaluate the performance of a language model using few-shot learning

C. Train a language model from scratch

D. Preprocess a dataset for machine learning

You want to extract useful information from customer emails to augment existing applications in your company. How can you use generative-ai-hub-sdk in this context?

A. Generate a new SAP application based on the mail data.

B. Generate JSON strings based on extracted information.

C. Generate random email content and send them to customers.

D. Train custom models based on the mail data.

How does SAP deal with vulnerability risks created by generative Al? Note: There are 2 correct answers to this question.

A. By implementing responsible Al use guidelines and strong product security standards.

B. By identifying human, technical, and exfiltration risks through an Al Security Taskforce.

C. By focusing on technological advancement only.

D. By relying on external vendors to manage security threats.

What contract type does SAP offer for Al ecosystem partner solutions?

A. Annual subscription-only contracts

B. All-in-one contracts, with services that are contracted through SAP

C. Pay-as-you-go for each partner service

D. Bring Your Own License (BYOL) for embedded partner solutions

Which of the following describes Large Language Models (LLMs)?

A. They rely on traditional rule-based algorithms to generate responses

B. They utilize deep learning to process and generate human-like text

C. They can only process numerical data and are not capable of understanding text

D. They generate responses based on pre-defined templates without learning from data

What does the Prompt Management feature of the SAP AI launchpad allow users to do?

A. Create and edit prompts

B. Provide personalized user interactions

C. Interact with models through a conversational interface

D. Access and manage saved prompts and their versions

Which of the following steps must be performed to deploy LLMs in the generative Al hub?

A. Run the booster
•Create service keys
•Select the executable ID

B. Provision SAP AI Core
•Check for foundation model scenario
•Create a configuration
•Create a deployment

C. Check for foundation model scenario
•Create a deployment
•Configuring entitlements

D. Provision SAP AI
•Core Create a configuration
•Run the booster

How can few-shot learning enhance LLM performance?

A. By enhancing the model's computational efficiency

B. By providing a large training set to improve generalization

C. By reducing overfitting through regularization techniques

D. By offering input-output pairs that exemplify the desired behavior