BlackAbapLives21

What are some benefits of using an SDK for evaluating prompts within the context of generative AI? Note: There are 3 correct answers to this question. Supporting low code evaluations using graphical user interface. Creating custom evaluators that meet specific business needs. Automating prompt testing across various scenarios. Maintaining data privacy by using data masking techniques. Providing metrics to quantitatively assess response quality.

How does the Al API support SAP Al scenarios? Note: There are 2 correct answers to this question. By managing Kubernetes clusters automatically. By providing a unified framework for operating AI services. By integrating AI models into third-party platforms like aws. By integrating AI services into business applications.

Which statement best describes the Chain-of-Thought (COT) prompting technique?. Linking multiple AI models in sequence, where each models output becomes the input for the next model in the chain. Writing a series of connected prompts creating a chain of related information. Connecting related concepts by having the LLM generate chains of ideas. Concatenating multiple related prompts to form a chain, guiding the model through sequential reasoning steps.

What is the primary function of the generative Al hub in SAP's Al Foundation?. To provide ready-to-use AI services for document processing. To serve as an abstraction layer to access a range of foundation AI models. To manage the AI lifecycle efforts end-to-end. To store embeddings of unstructured data for semantic data retrieval.

Match the components of a Retrieval Augmented Generation architecture to the diagram. Box - Models - Backend and Frontend Box - Applications - Embedding Model and LLM Box - Retrieval - Vector Database. Box - Models - Embedding Model and LLM Box - Applications - Vector Database Box - Retrieval - Backend and Frontend. Box - Models - Vector Database Box - Applications - Backend and Frontend Box - Retrieval - Embedding Model and LLM. Box - Models - Embedding Model and LLM Box - Applications - Backend and Frontend Box - Retrieval - Vector Database.

What must be defined in an executable to train a machine learning model using SAP Al Core? Note: There are 2 correct answers to this question. Infrastructure resources such as CPUs or GPUs. Deployment templates for SAP AI Launchpad. Pipeline containers to be used. User scripts to manually execute pipeline steps.

What can be done once the training of a machine learning model has been completed in SAP Al Core? Note: There are 2 correct answers to this question. The model can be deployed in SAP HANA. The models accuracy can be optimized directly in SAP HANA. The model can be deployed for inferencing. The model can be registered in the hyperscaler object store.

How does SAP deal with vulnerability risks created by generative Al? Note: There are 2 correct answers to this question. By identifying human, technical, and exfiltration risks through an AI Security Taskforce. By focusing on technological advancement only. By implementing responsible AI use guidelines and strong product security standards. By relying on external vendors to manage security threats.

Which of the following are features of the SAP Al Foundation? Note: There are 2 correct answers to this question. AI runtime and lifecycle management. Ready-to-use- AI services. Open source AI model repository. Joule Integration in SAP SuccessFactors.

What contract type does SAP offer for Al ecosystem partner solutions?. Annual subscription-only contracts. Pay-as-you-go for each partner service. All-in-one contracts, with services that are contracted through SAP. Bring Your Own License (BYOL) for embedded partner solution.

Where can you configure language models in generative Al hub?. The Orchestration tab in SAP AI Launchpad. The Configuration tab of the SAP BTP cockpit. The Models tab in Prompt Editor. The Configuration tab within ML Operations in SAP AI Launchpad.

You want to use the orchestration service through SAP's generative-Al-hub-sdk. What does the following code do?. Define the Template and Default Input Values. Run the Orchestration Request. Define the LLM. Create the Orchestration Configuration.

Which of the following statements accurately describe the RAG process? Note: There are 2 correct answers to this question. The users question is used to search a knowledge base or a set of documents. The LLM directly answers the users questions without accessing external information. The embedding model stores the generated answers for future reference. The retrieved content is combined with the LLMs capabilities to generate a response.

How do resource groups in SAP Al Core improve the management of machine learning workloads? Note: There are 2 correct answers to this question. They enhance pipeline execution speeds through workload distribution. They ensure workload separation for different tenants or departments. They provide isolation for datasets and AI artifacts. They enable simultaneos orchestration of Kubernetes clusters.

What is Machine Learning (ML)?. A form of AI that only focuses on creating new content, including text, imagens, soudn, and videos. A technology that equips machines with human-like capabilities such as problem-solving visual perception, and decision-making. A statistical method for data processing that does not involve any AI techniques. A subset of AI that focuses on enabling computer systems to learn and improve from experience or data.

Which of the following must you do before connecting to a dataset in order to train a machine learning model in SAP Al Core? Note: There are 2 correct answers to this question. Grant access rights to the sap BTP cockpit. Store the dataset in a hyperscaler object store. Provide the storage secret to access the dataset. Store the dataset in the SAP HANA Vector Engine.

What is a significant risk associated with using LLMs?. Lack of scalability in business applications. Immediate accuracy without fine-tuning. Reduced computational requirements. Potential biases in generated content.

What is one primary benefit of using LLMs in business applications?. They are only applicable for customer support scenarios. They eliminate the need for data security measures. They enhance automation and scalability of processes. They require minimal computing power for training.

What are some benefits of the SAP Al Launchpad? Note: There are 2 correct answers to this question. Direct deployment of AI models to SAP HANA. Simplified model retraining and performance improvement. Centralized AI lifecycle management for all AI scenarios. Integration with non-SAP platforms like Azure and AWS.

Which of the following describes Large Language Models (LLMs)?. They rely on predefined scripts for decision-making. They are rule-based systems designed for specific tasks. They cannot process large datasets efficiently. They utilize deep learning to process and generate human-like text.

What does the Prompt Management feature of the SAP Al Iaunchpad allow users to do?. Interact with models through a conversational interface. Provide personalized user interactions. Create and edit prompts. Access and manage saved prompts and their versions.

Why would a user include formatting instructions within a prompt?. To force the model to separate relevant and irrelevant output. To redict the output to another software program. To ensure the models response follows a desired structure or style. To increase the faithfulness of the output.

What are some advantages of using agents in training models? Note: There are 2 correct answers to this question. To guarantee accurate decision making in complex scenarios. To streamline LLM workflows. To improve the quality of results. To eliminate the need for human oversight.

Which of the following capabilities does the generative Al hub provide to developers? Note: There are 2 correct answers to this question. Tools for prompt enfineering and experimentation. Code generation to extend SAP BTP applications. Proprietary LLMs exclusively. Integration of foundation models into applications.

Which of the following steps must be performed to deploy LLMs in the generative Al hub?. 1. Check for foundation model scenario 2. Create a deployment 3. Configuring entitlements. 1.Provision SAP AI Core 2. Check for foundation model scenario 3. Create a configuration 4. Create a deployment. 1. Provision SAP AI 2. Core Create a configuration 3. Run the booster. 1. Run the booster 2. Create service keys 3. Select the executable ID.

Which of the following is a principle of effective prompt engineering?. Write vague and open-ended instructions to encourage creativity. Use precise language and provinding detailed context in prompis. Keep prompts as short as possible to avoid confusion. Combine multiple complex tasks into a single prompt.

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?. Generate JSON strings based on extracted information. Train custom models based on the mail data. Generate random email content and send them to customers. Generate a new SAP application based on the mail data.

How does SAP ensure the enterprise-readiness of its Al solutions?. By ensuring that AI models make bias-freee decisions without human input. By using generic AI models without business context complying with AI ethics standards. By implementing rigorous product standards for AI capabilities.

Why is generative Al gaining significant attention and investment in the current business landscape? Note: There are 2 correct answers to this question. it can run entire business operations without human intervention. it can replicate complex technical skill without training or quality control. it only requires natural language skills to use. it lowers barriers to adoption.

Which of the following steps is NOT a requirement to use the Orchestration service?. Create a dployment for orchestration. Get an auth token for orchestration. Create an instance of an AI model. Modify the underluing AI models.

Which of the following sequence of steps does SAP recommend you use to solve a business problem using generative Al hub?. 1. Create a basic prompt SAP AI Launchpad 2. Scale the solution using generative-ai-hub-sdk 3. Create a baseline evaluation method for the simple prompt 4. Enhance the prompts 5. Evaluate various models for the problem using generative-ai-hub-sdk. 1. Create a basic prompt SAP AI Launchpad 2. Evaluate various models for the problem using generative-ai-hub-sdk 3. Scale the solution using generative-ai-hub-sdk 4. Create a baseline evaluation method for the simple prompt 5. Enhance the prompts. 1. Create a basic prompt SAP AI Launchpad 2. Enhance the prompts 3. Create a baseline evaluation method for the simple prompt 4. Evaluate various models for the problem using generative-ai-hub-sdk 5. Scale the solution using generative-ai-hub-sdk.

Which of the following are functionalities provided by the generative-Al-hub-SDK? Note: There are 2 correct answers to this question. Interact with LLMs. Create chat responses and embeddings. Configure SAP BTP credentials. Customize SAP AI Launchpad.

What are some use cases for fine-tuning of a model? Note: There are 2 correct answers to this question. To customize outputs for specific types of inputs. To introduce new knowledge to a model in a resource-efficient way. To quickly create interations on a new use case. To sanitize model outputs.

Which of the following is unique about SAP's approach to Al?. Focusing AI solely on customer support services. Offering AI capabilities in their future products as of 2025. SAPs deep integration of AI with business processes and analytics. Utilizing AI mainly for marketing purposes.

What are some components of the training pipeline in SAP AI Core? Note: There are 2 correct answers to this question. Automated deployment to Kubernetes clusters. The SAP HANA database for model storage. Input datasets stored in a hyperscaler object store. Executables that define the training process.

How can few-shot learning enhance LLM performance?. By offering input-output pairs that exemplify the desired behavior. By enhancing the models computational efficiency. By providing a large training set to improve generalization. By reducing overfitting through regularization techiniques.

What capabilities does the Exploration and Development feature of the generative Al hub provide? Note: There are 2 correct answers to this question. Automatic model selection. Prompt editor and management. AI playground and chat. Develop and debug ABAP code.

What are the benefits of SAP's generative Al hub? Note: There are 2 correct answers to this question. Accelerate AI development with flexible access to a broad range of models. Send your data to varios LLM providers for training feedback. Provide libraries for no-code development. Build custom AI solutions and extend SAP applications.

What are some metrics to evaluate the effectiveness of a Retrieval Augmented Generation system? Note: There are 2 correct answers to this question. Carbon footprint. Speed. Faithfulness. Relevance.

Which of the following techniques uses a prompt to generate or complete subsequent prompts (streamlining the prompt development process), and to effectively guide Al model responses?. Meta prompting. Few-shot prompting. Chain-of-thought prompting. One-shot prompting.

What is a Large Language Model (LLM)?. An AI model that specializes in processing, understanding, and generating human language. A rule-based expert system to analyze and generate grammatically correct sentences. A database system optimized for storing large volumes fo textual data. A gradient booested decision tree algorithm for predicting text.

You want to download a json output for a prompt and the response. Which of the following interfaces can you use in SAP's generative Al hub in SAP AI Launchpad?. Chat. Prompt Editor. Prompt management. Administration.

What is the primary function of the embedding model in a RAG system?. To evaluate the faithfulness and relevance of generated answers. To encode queries and documents into vector representations for comparison. To generate responses based on retrieved documents and user queries. To store vector representations of documents and search for relevant passages.

Which neural network architecture is primarily used by LLMs?. Recurrent neural network architecture. Sequential encoder-decoder architecture. Convolutional Neural Networks(CNNs). Transformer architecture with self-attention mechanisms.

What are some features of Joule? Note: There are 3 correct answers to this question. Streamlining tasks with an AI assistant that knows your unique role. Providing coding assistance and content generation. Generating standalone applications. Maintaining data privacy while offering generative AI capabilities. Downloading and processing data.

How can Joule improve workforce productivity? Note: There are 2 correct answers to this question. By resolving hardware malfunctions. By offering generic task recommendations unrelated to specific roles. By providing context-based role-specific task assistance. By maintaining strict adherence to data privacy regulations.

What are some characteristics of the SAP generative Al hub? Note: There are 2 correct answers to this question. it only supports traditional machine learning models. it ensures relevant, reliable, and responsible business AI. it provides instant access to a wide range of large language models (LLMSs). it operates independently of SAPs partners and ecosystem.

What defines SAP's approach to LLMs?. Avoiding partnerships with external AI providers. Prioritizing only the performance of open-source models. Using proprietary transformer-based models exclusively. Ensuring ethical AI practices and seamless business integration.

What are some benefits of SAP Business Al? Note: There are 3 correct answers to this question. Automatic human emotion recognition. AI-powered forecasting and predictions. Face detection and face recognition. Intelligent business document processing. Personalized recommendations based on AI algorithms.

What are some functionalities provided by SAP Al Core? Note: There are 3 correct answers to this question. Management of SAP S/4HANA cloud infrastructure. Integration of AI services with business applications using a standardized API. Monitoring and retraining models in SAP AI Core. Continuous delivery and tenant isolation for scalability. Orchestration of AI workflows such as model training and inference.

What is a part of LLM context optimization?. Providing the model with domain-specific knowledge needed to solve a problem. Reducing the models size to improve efficiency. Adjusting the models output format and style. Enhancing the computational speed of the model.

What are some examples of generative Al technologies? Note: There are 2 correct answers to this question. Rule-based algorithms. Foundation models. Robotic process automation. Ai models that generate new content based on training data.

What are some drivers for the rapid adoption of generative AI? Note: There are 2 correct answers to this question. Signigficant hardware cost savings. Availability of skilled developers. Ease of use. Wide availability.

What advantage can you gain by leveraging different models from multiple providers through the SAP's generative Al hub?. Enhance the accuracy and relevance of AI Applications that use SAPs data assets. Get more training data for new models. Design new product interfaces for SAP application. Train new models using SAP and non-SAP data.

Which of the following is a benefit of using Retrieval Augmented Generation?. it eliminates the need for fine-tuning LLMs for specific tasks. it enables LLMs to learn new languages without additonal training. it allows LLMs to access and utilize information beyond their initial training data. it reduces the computational resources required for language modeling.

What is the goal of prompt engineering?. To craft inputs that guide AI systems in generating desired outputs. To replace human decision-making with automated processes. To optimize hardware performance for AI computations. To develop new neural network architectures for AI models.

What does SAP recommend you do before you start training a machine learning model in SAP Al Core? Note: There are 3 correct answers to this question. Register the input dataset in SAP AI Core. Define the required infrastructure resources for training. Configure the training pipeline using templates. Perform manual data integration with SAP HANA. Configure the model deployment in SAP AI Launchpad.

Which technique is used to supply domain-specific knowledge to an LLM?. Prompt template expansion. Domain-adaptation training. Retrieval-Augmented Generation. Fine-tuning the model on general data.

Which of the following executables in generative Al hub works with Anthropic models?. SAP AI Core. GCP Vertex AI. AWS Bedrock. Azure OpenAI Service.

What is the purpose of splitting documents into smaller overlapping chunks in a RAG system?. To simplify the process fo training the embedding model. To reduce the storage space required for the vector database. To enable the matching of different relevant passages to user queries. To improve the efficiency of encoding queries into vector representations.

What are some SAP recommendations to evaluate pricing and rate information of model usage within SAP's generative Al hub? Note: There are 2 correct answers to this question. Adopt best practice pricing strategies, such as outcome-based pricing. Use pricing models that have fixed rates irrespective of the usage patterns. Avoid subscription-based pricing models. Weigh the cost of using advanced models against the expected return on investment.

Which of the following are grounding principles included in SAP's Al Ethics framework? Note: There are 3 correct answers to this question. Human agency and oversight. Maximize business profits. Store all user data for legal proceedings. Avoid bias and discrimination. Transparency and explainability.

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> {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"]). Train a language model from scratch. Evaluate the performance of a language model using few-shot-learning. Generate random examples for language model training. Preprocess a dataset for machine learning.

What are the applications of generative Al that go beyond traditional chatbot applications? Note: There are 2 correct answers to this question. To produce outputs based on software input. To interpret human instructions and control software systems without necessarily producing output for human consumption. To interpret human instructions and control software systems always producing output for human consumption. To follow a specific schema - human input, AI processing, and output for human consumption.