Correct Answer:

Explanation:

Correct Answer:

Explanation:
Two distinct RAG problems require two distinct solutions. When retrieved results frequently include duplicated content from the same document, the cause is overlapping chunks receiving similarly high similarity scores. The solution is Maximum Marginal Relevance reranking, which diversifies the result set by penalizing results that are semantically similar to already-selected results, reducing redundancy. When retrieved chunks sometimes span unrelated policy sections, the cause is fixed-size character chunking that splits content without regard for semantic boundaries. The solution is semantic chunking - splitting on natural sentence or section boundaries - ensuring each chunk is semantically coherent and does not straddle unrelated content. Both problems must be addressed together: reranking alone solves duplication but not relevance; semantic chunking alone solves relevance but not duplication.
Microsoft Learn Reference Topic: Optimize RAG retrieval in Azure AI Search - Chunking strategies and MMR reranking

Correct Answer:

Explanation:
Detect when the system is slow at returning output: Latency
Identify when the system cannot sustain expected request volume: Throughput Measure the duration of handling a request: Response time Latency measures delay experienced while waiting for model output and is therefore the appropriate metric for identifying degradation in perceived responsiveness. Microsoft describes latency as the time required to obtain a response from the model and exposes metrics such as Time to Response/Time to First Token and Time Between Tokens for generative AI workloads. An increase indicates that users are waiting longer for output to begin or continue.
Throughput represents the amount of workload the system can process over a unit of time. Microsoft describes system-level throughput in terms such as requests per minute and tokens per minute. Consequently, throughput is the correct metric when determining whether a deployment can sustain the required request volume as demand increases.
Response time represents the overall duration required to handle an individual request. It is appropriate for measuring end-to-end request processing and validating request-duration SLOs. Microsoft specifically includes latency, throughput, and response times among the performance metrics candidates are expected to monitor for generative AI applications.
Concurrency measures simultaneous active requests and can influence capacity and latency, but none of these requirements directly asks for simultaneous-request count.
Study Guide Reference: Implement generative AI quality assurance and observability - continuous monitoring, latency, throughput, response times, production troubleshooting, and SLO monitoring.

Correct Answer:

Explanation:
Correct sequence:
* Create a Developer Tier deployment.
* Evaluate and validate the model.
* Create a Global Standard deployment.
The fine-tuned model should first be deployed using the Developer Tier because Microsoft specifically positions this deployment type for fine-tuned model candidate evaluation rather than production use .
Developer Tier deployments provide a cost-efficient environment for testing custom models and do not provide a production SLA.
After deployment, the model should be evaluated and validated . Microsoft Foundry supports running the model through the playground and the Evaluations service to assess the deployed candidate against expected quality, safety, and task-performance criteria. Microsoft explicitly documents that evaluations can be executed against a deployed fine-tuned model candidate and compared with other model versions.
Only after the candidate satisfies the required validation criteria should it be promoted to a Global Standard deployment for production inference. Global Standard is designed for general production workloads and provides substantially more appropriate production characteristics than Developer Tier.
Register the fine-tuned model version is the distractor here. The scenario already states that fine-tuning is complete and the resulting model variant exists in Microsoft Foundry; the required promotion workflow is therefore test deployment # validation # production deployment .
Study Guide Reference: Implement machine learning model lifecycle and operations - fine-tuned model evaluation, controlled promotion, Developer Tier deployments, production deployment, and model lifecycle governance.

Correct Answer: A  🗳️

Explanation: Only visible for DumpsTorrent members. You can sign-up / login (it's free).