C1000-185最も有効な質問と解答で勉強

You are tasked with integrating a generative AI model on watsonx.ai into a custom business workflow. The workflow requires complex prompt chains and interaction with external APIs.
Which of the following best describes how you should approach the integration using watsonx.ai and LangChain?

• A. Use only watsonx.ai's built-in APIs and SDKs for integration, as LangChain is not required for chaining multiple prompts.
• B. Implement LangChain to handle complex multi-step workflows, using watsonx.ai's APIs to generate responses at specific stages in the chain.
• C. Write custom scripts to manage all prompt sequences manually, leveraging watsonx.ai's SDK to call the generative AI model at every step.
• D. Directly integrate the external APIs with watsonx.ai without any intermediate framework, since LangChain would add unnecessary overhead.

You want a generative AI model to summarize a lengthy text in one sentence. You provide the following prompt: "Summarize the following paragraph in one sentence: 'Artificial intelligence (AI) is the simulation of human intelligence in machines that are programmed to think and learn. The field of AI includes everything from speech recognition to problem-solving and robotics.'" No prior examples are given.
What type of prompting is being used, and what are the expectations?

• A. Zero-shot prompting, but the model may fail without detailed instructions on what aspects of the text to focus on.
• B. Few-shot prompting, but the model will likely struggle without a few examples of summaries provided.
• C. Zero-shot prompting, with the expectation that the model can summarize common concepts like AI due to pre-training.
• D. Zero-shot prompting, but it requires the addition of a few examples for the model to generate a summary.

You are tasked with designing a prompt using a few-shot strategy for Watsonx AI to generate a legal contract summary. You provide two examples of contract summaries before asking the model to summarize a new contract.
Which of the following options best demonstrates an effective few-shot prompt for this task?

• A. "Example 1: [First Contract] Summary: [First Contract Summary]
  Example 2: [Second Contract] Summary: [Second Contract Summary]
  Generate a summary of the following contract: [New Contract]."
• B. "Example 1: [First Contract]
• C. "Provide a summary of the following contract: [New Contract].
  Example 1: [First Contract]
  Summary: [First Contract Summary]
  Example 2: [Second Contract]
  Summary: [Second Contract Summary]."
• D. "Generate a summary for [New Contract]."

You are enhancing an existing relational database system to support vector-based similarity search, integrating RAG into your infrastructure.
Which of the following technologies or approaches represents a valid method for extending a traditional SQL database to handle vector embeddings and similarity searches?

• A. Normalizing vector embeddings into relational tables with foreign key constraints
• B. Using a full-text indexing engine, such as Elasticsearch, to store the vector embeddings
• C. Adding a plugin that provides support for k-nearest neighbors (k-NN) search
• D. Using graph database extensions to enable vector embeddings within a SQL database

You are tasked with deploying two generative AI systems: one for document summarization and another for question-and-answer (Q&A). Both systems need to handle large volumes of unstructured text, but they differ in their response time requirements and interaction with users.
Which deployment strategy would be most appropriate for this scenario?

• A. Use a rule-based model for summarization and a machine learning-based model for Q&A, combining them into a single service endpoint for deployment.
• B. Use a single deployment strategy where both the summarization and Q&A systems are integrated into a shared model that processes all requests through the same inference pipeline.
• C. Deploy both systems as a single pipeline, with the summarization model providing input to the Q&A model to improve the quality of answers.
• D. Deploy the summarization model as a batch processing system, while the Q&A system is deployed as an on-demand service using a low-latency inference model.