1Z0-1127-25 Using OCI Generative AI Service Practice Test 4 — 15 Questions

Question 1

A healthcare organization is using OCI Generative AI to analyze medical records. They must comply with HIPAA. They have set up a dedicated AI cluster with private endpoints. However, they are concerned about model hallucinations that could lead to incorrect medical advice. They want to minimize hallucinations while maintaining usefulness. Which approach is most effective?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Implement a retrieval-augmented generation (RAG) pipeline with a verified medical knowledge base.. A Retrieval-Augmented Generation (RAG) pipeline grounds the model's responses in a verified medical knowledge base, directly reducing hallucinations by ensuring outputs are based on retrieved facts rather than purely generative predictions. This approach maintains usefulness by allowing the model to reference authoritative sources, which is critical for HIPAA compliance and accurate medical advice.

Answer

Use a smaller model to reduce complexity.

Answer

Increase the temperature to encourage diverse outputs.

Answer

Reduce max tokens to force shorter responses.

Question 2

Refer to the exhibit. A developer receives this error when trying to get details of a model they know exists. What is the most likely cause?

Accepted Answer

The model is in a different compartment that the developer cannot access. The error 'not found' or 'access denied' when retrieving a known model in OCI Generative AI typically indicates an authorization failure due to compartment restrictions. The model exists, but the developer's IAM policy does not grant access to the compartment where the model is deployed, causing the API to return a 404 or 403 error as if the resource does not exist.

Answer

The region is incorrect; the model is in a different region

Answer

The model ID is misspelled

Answer

The developer does not have the 'inspect' permission on the model

Question 3

A healthcare startup uses OCI Generative AI to automatically generate patient summary reports from clinical notes. They use the Cohere command model (command-r-plus) with default parameters. Over the past week, the team has noticed two issues: (1) the summaries occasionally contain medical inaccuracies, such as incorrect drug dosages or misinterpreted lab results, and (2) the response time has increased from an average of 2 seconds to over 10 seconds. The application has a high volume of concurrent requests, and the startup has already increased the max tokens to 4096 and set temperature to 0.1. The model appears to perform well on general language tasks but struggles with specialized medical terminology. The team is looking for a long-term solution that balances accuracy, latency, and cost. What should they do?

Accepted Answer

Fine-tune the Cohere command model using a curated dataset of medical notes and correct summaries. Fine-tuning the Cohere command model on a curated dataset of medical notes and correct summaries directly addresses the core issue: the model's poor performance on specialized medical terminology. Unlike prompt engineering or parameter adjustments, fine-tuning adapts the model's weights to the medical domain, improving accuracy without sacrificing latency or incurring the high cost of a larger base model. This approach balances accuracy, latency, and cost by using a smaller, optimized model that can handle concurrent requests efficiently.

Answer

Switch to a larger base model, such as Llama 2 70B, to improve knowledge of medical terms

Answer

Implement a caching layer to store and reuse responses for identical queries

Answer

Reduce the max tokens parameter from 4096 to 1024 to decrease response time

Question 4

A company uses OCI Generative AI Service to build a chatbot for customer support. They notice that the model sometimes generates inappropriate responses. What is the MOST effective way to mitigate this without retraining the model?

Accepted Answer

Configure system instructions to define acceptable behavior. Configuring system instructions is the most effective approach because it allows you to define the model's behavior and constraints at inference time without modifying the underlying model weights. In OCI Generative AI Service, system instructions act as a persistent prompt that guides the model's responses, enabling you to explicitly prohibit inappropriate content and enforce safety guidelines. This is a non-invasive, immediate mitigation that does not require the time, cost, or data preparation associated with retraining or fine-tuning.

Answer

Fine-tune the model with curated safe examples

Answer

Reduce the temperature parameter to 0

Answer

Use the moderation API to filter responses

Question 5

A developer wants to use OCI Generative AI Service to summarize long documents. Which endpoint should they use to send the document content?

Accepted Answer

/chat. The /chat endpoint in OCI Generative AI Service is designed for conversational interactions and can handle long document summarization by accepting the document content as part of the chat context. This endpoint supports multi-turn dialogues and large input payloads, making it suitable for processing and summarizing lengthy documents.

Answer

/generate

Answer

/classify

Answer

/embed

Question 6

An organization deploys a fine-tuned model for legal document analysis using OCI Generative AI Service. They need to ensure that only authorized users in the 'LegalTeam' group can access the model endpoint. Which policy statement should be used?

Accepted Answer

Allow group LegalTeam to use generative-ai-model in compartment ABC. The 'use' verb on the 'generative-ai-model' resource type grants the LegalTeam group permission to invoke the model endpoint for inference, which is the minimum privilege required for accessing a deployed fine-tuned model in OCI Generative AI Service. The 'use' permission specifically allows calling the model for text generation or analysis without granting broader management or read capabilities.

Answer

Allow group LegalTeam to manage generative-ai-family in compartment ABC

Answer

Allow group LegalTeam to read generative-ai-model in compartment ABC

Answer

Allow group LegalTeam to inspect generative-ai-model in compartment ABC

Question 7

A data scientist is using OCI Generative AI Service to generate product descriptions. They notice that the output often repeats phrases. Which parameter adjustment would MOST directly address this issue?

Accepted Answer

Increase the frequency penalty. The frequency penalty directly reduces the likelihood of the model repeating the same phrases by penalizing tokens that have already appeared in the generated text. In OCI Generative AI Service, this parameter subtracts a fixed value from the log-probability of each token each time it is generated, making repeated tokens less likely to be chosen again. This is the most direct mechanism to address repetitive output.

Answer

Increase the temperature

Answer

Increase the max tokens

Answer

Decrease the top-p value

Question 8

A company needs to integrate OCI Generative AI Service with an existing application that uses OCI IAM for authentication. They want to use resource principal to allow the application to call the service without storing API keys. Which step is REQUIRED?

Accepted Answer

Create a dynamic group and a policy granting access to the Generative AI Service. Resource principal authentication in OCI requires the application to be represented by a dynamic group, which matches instances or resources based on defined rules. A policy must then grant that dynamic group access to the Generative AI Service. This avoids storing API keys by using OCI IAM's built-in resource principal token exchange.

Answer

Create an OCI API key for the application

Answer

Enable the Generative AI Service for resource principal in the tenancy

Answer

Assign the application to a group with admin privileges

Question 9

A developer is using OCI Generative AI Service to generate code snippets. They want to ensure the output is as deterministic as possible for testing. Which combination of parameters should they use?

Accepted Answer

Temperature = 0, Top-p = 1. Setting Temperature=0 makes the model deterministic by always selecting the highest-probability token, while Top-p=1 includes all tokens in the sampling pool, ensuring no additional randomness is introduced. This combination eliminates stochastic variation, making outputs repeatable for testing.

Answer

Temperature = 0.5, Top-p = 0.5

Answer

Temperature = 0, Top-p = 0

Answer

Temperature = 1, Top-p = 1

Question 10

A company uses OCI Generative AI Service to generate personalized email content. They need to ensure that personally identifiable information (PII) is not included in the model's training data. What should they do?

Accepted Answer

Enable data redaction in the service. OCI Generative AI Service provides a built-in data redaction feature that automatically detects and removes personally identifiable information (PII) from training data before it is used for model training. This ensures compliance with data privacy regulations without requiring manual preprocessing or external tools.

Answer

Encrypt the training data with OCI Vault

Answer

Use the moderation API to scan outputs

Answer

Use a dedicated model endpoint

Question 11

Which TWO of the following are valid ways to reduce latency when using OCI Generative AI Service?

Accepted Answer

Use a dedicated AI cluster. A dedicated AI cluster provides isolated compute resources (GPU nodes) for inference, eliminating resource contention from other tenants or workloads. This ensures consistent low-latency responses because the model is always warm and available without queueing delays, which is critical for real-time applications.

Answer

Deploy the model in a different region

Answer

Use a larger model

Answer

Batch multiple requests

Question 12

Which THREE of the following are supported capabilities of OCI Generative AI Service?

Accepted Answer

Text summarization. OCI Generative AI Service includes a dedicated text summarization capability that uses large language models (LLMs) to generate concise summaries from longer documents. This feature is part of the service's core generative AI offerings, supporting use cases like meeting notes summarization and document abstraction.

Answer

Sentiment analysis

Answer

Image generation

Question 13

Which TWO of the following are required to fine-tune a model using OCI Generative AI Service?

Accepted Answer

A training dataset in the required format. A is correct because fine-tuning a model in OCI Generative AI Service requires a training dataset in the required format (JSONL with prompt-completion pairs) to provide the task-specific examples that adjust the model's weights. B is correct because you must specify the base model identifier (e.g., 'cohere.command-light-14-07-2024') to indicate which pre-trained model to fine-tune, as the service uses this to load the correct architecture and initial parameters.

Answer

A compartment with sufficient quota

Answer

An OCI API key

Answer

A dedicated AI cluster

Question 14

Refer to the exhibit. A user runs the command shown and receives the error: 'ServiceError: NotAuthorizedOrNotFound'. What is the MOST likely cause?

Accepted Answer

The user does not have the 'inspect' permission on the model. The error 'NotAuthorizedOrNotFound' in OCI is a generic error that can occur either when the resource does not exist or the user lacks the necessary permission to access it. Given that the model ID and region are likely correct (otherwise a different error like 'InvalidParameter' would appear), the most probable cause is that the user does not have the 'inspect' permission on the model. This permission is required to view model details. Option A would result in a credential configuration error, not this generic error. Option C would produce an invalid model ID error. Option D is less likely because if the model were in a different region, the error would typically indicate a region mismatch rather than a generic authorization error. Therefore, option B is correct.

Answer

The CLI is not configured with OCI credentials

Answer

The model ID is incorrectly formatted

Answer

The model is in a different region than iad

Question 15

Refer to the exhibit. A developer sends this JSON payload to the /chat endpoint. The response includes an error that 'maxTokens' must be an integer. What is the issue?

Accepted Answer

The parameter should be 'max_tokens' instead of 'maxTokens'. The OCI Generative AI service expects the parameter name 'max_tokens' (snake_case) for specifying the maximum number of tokens in the response, not 'maxTokens' (camelCase). The error message indicates that the value is not being recognized as an integer because the JSON key itself is incorrect, causing the service to fail validation.

Answer

The compartmentId is missing

Answer

The temperature value is too low

Answer

The model name 'cohere.command-light' is incorrect