A. 与亚马逊 S3 集成以进行对象存储 

B. 支持地理空间索引和查询 

C. 可扩展的索引管理和最近邻搜索功能 

D. 能够对流式数据进行实时分析

Which feature of Amazon OpenSearch Service gives companies the ability to build vector database applications?

A. Integration with Amazon S3 for object storage

B. Support for geospatial indexing and queries

C. Scalable index management and nearest neighbor search capability

D. Ability to perform real-time analysis on streaming data

A. 通过使用入侵检测系统来提高网络安全性 

B. 从文本描述中创建逼真的图像以用于数字营销 

C. 通过使用优化索引来提高数据库性能 

D. 分析财务数据以预测股票市场趋势

Which option is a use case for generative Al models?

A. Improving network security by using intrusion detection systems

B. Creating photorealistic images from text descriptions for digital marketing

C. Enhancing database performance by using optimized indexing

D. Analyzing financial data to forecast stock market trends

A. 温度（参数） 

B. 上下文窗口 

C. 批量大小 

D. 模型大小

A company wants to build a generative Al application by using Amazon Beedrock and needs to choose a foundation model (FM). The company wants to know how much information can fit into one prompt.

Which consideration will inform the company's decision?

A. Temperature

B. Context window

C. Batch size

D. Model size

以下哪个解决方案符合这些要求？ 

A. 对基础模型能够生成的令牌数量设置一个较低的限制。 

B. 使用批量推理来处理详细的回复。 

C. 进行实验并优化prompt，直到基础模型生成所需的回复。 

D. 为温度参数设置一个更高的值。

A company wants to make a chatbot to help customers. The chatbot will help solve technical problems without human intervention

The company chose a foundation model (FM) for the chatbot. The chatbott needs to produce responses that adhere to company tone.

Which solution meets these requirements?

A. Set a low limit on the number of tokens the FM can produce.

B. Use batch inferencing to process detailed responses.

C. Experiment and refine the prompt until the FM produces the desired rresponses

D. Define a higher number for the temperature parameter.

哪种提示工程策略符合这些要求？ 

A. 在提示中提供带有相应积极或消极标签的文本段落示例，随后跟上要分类的新文本段落。 

B. 在提示中详细解释情感分析以及大语言模型的工作原理。 

C. 提供要分类的新文本段落，不添加任何额外上下文或示例。 

D. 提供新文本段落，并附带一些不相关任务的示例，如文本摘要或问答。

A company wants to use a large language model (LLM) on Amazon Bedroock for sentiment analysis. The company wants to classify the sentiment of text passages as positive or negative.

Which prompt engineering strategy meets these requirements?

A. Provide examples of text passages with corresponding positive or negative labels in the prompt followed by the new text passage to be classified.

B. Provide a detailed explanation of sentiment analysis and how LLMs work in the prompt.

C. Provide the new text passage to be classified without any additional context or examples.

D. Provide the new text passage with a few examples of unrelated tasks, such as text summarization or question answering.

该公司应使用哪个 AWS 服务来识别试图访问亚马逊 Bedrock 的未授权用户？

A. AWS 审计管理器 

B. AWS CloudTrail（AWS 云迹） 

C. 亚马逊欺诈检测器 

D. AWS 可信顾问

A security company is using Amazon Bedrock to run foundation models (FMs). The company wants to ensure that only authorized usersinvoke the models. The company needs to identify any unauthorized accessattempts to set appropriate AWS Identity and Access Management (IAM) policies and roles for future iterations of the FMs.

Which AWS service should the company use to identify unauthorizedusers that are trying to access Amazon Bedrock?

A. AWS Audit Manager

B. AWS Cloud Trail

C. Amazon Fraud Detector

D. AWS Trusted Advisor

该公司需要实施一个解决方案来托管该模型并提供预测结果，同时无需管理任何底层基础设施。 

哪种解决方案能够满足这些要求？ 

A. 使用亚马逊 SageMaker 无服务器推理来部署该模型。 

B. 使用亚马逊 CloudFront 来部署该模型。 

C. 使用亚马逊 API 网关来托管该模型并提供预测结果。 

D. 使用 AWS Batch 来托管该模型并提供预测结果。

A company has developed an ML model for image classification. The company wants to deploy the model to production so that a web application can use the model.

The company needs to implement a solution to host the model and servepredictions without managing any of the underlying infrastructure.

Which solution will meet these requirements?

A. Use Amazon SageMaker Serverless Inference to deploy the model.

B. Use Amazon CloudFront to deploy the model.

C. Use Amazon API Gateway to host the model and serve predictions.

D. Use AWS Batch to host the model and serve predictions.

该公司可以使用以下哪个 AWS 服务来满足这一要求？ 

A. AWS 审计管理器 

B. AWS Artifact

C. AWS 可信顾问 

D. AWS 数据交换

An Al company periodically evaluates its systems and processes with thhe help of independent software vendors (ISVs). The company needs to receive email message notifications when an ISV's compliance reports become available.

Which AWS service can the company use to meet this requirement?

A. AWS Audit Manager

B. AWS Artifact

C. AWS Trusted Advisor

D. AWS Data Exchange

以下哪项行动将降低这些风险？ 

A. 创建一个提示模板，教导大语言模型检测攻击模式。 

B. 增加对大语言模型调用请求中的温度参数。 

C. 避免使用未在亚马逊 SageMaker 中列出的大语言模型。 

D. 减少对大语言模型调用时的输入令牌数量。

A company wants to use a large language model (LLM) to develop a conversational agent. The company needs to prevent the LLM from being manipulated with common prompt engineering techniques to perform unddesirable actions or expose sensitive information

Which action will reduce these risks?

A. Create a prompt template that teaches the LLM to detect attack paatterns

B. Increase the temperature parameter on invocation requests to the ILM

C. Avoid using LLMs that are not listed in Amazon SageMaker.

D. Decrease the number of input tokens on invocations of the LLM.

哪种解决方案范围让公司承担最多的安全责任？ 

A. 使用具有嵌入式生成式人工智能功能的第三方企业应用程序。 

B. 使用现有的第三方生成式人工智能基础模型（FM）构建应用程序。 

C. 通过使用特定于业务的数据对现有的第三方生成式人工智能基础模型（FM）进行微调来优化该模型。 

D. 使用客户拥有的特定数据从头开始构建和训练一个生成式人工智能模型。

A company is using the Generative Al Security Scoping Matrix to assesssecurity responsibilities for its solutions. The company has identified fopur different solution scopes based on the matrix.

Which solution scope gives the company the MOST ownership of seciurity responsibilities?

A. Using a third-party enterprise application that has embedded generative Al features

B. Building an application by using an existing third-party generative Al undation model (FM).

C. Refining an existing third-party generative Al foundation model (FM) byfine-tuning the model by using data specific to the business.

D. Building and training a generative Al model from scratch by using specific data that a customer owns.

A. 目标检测 

B. 异常检测 

C. 命名实体识别 

D. 图像修复

An Al practitioner has a database of animal photos. The Al practitioner wants to automatically identify and categorize the animals in the photos without manual human effort.

Which strategy meets these requirements?

A. Object detection

B. Anomaly detection

C. Named entity recognition

D. Inpainting

B. 模型定制模式 

C. 预留吞吐量模式 

D. 竞价实例模式

A company wants to create an application by using Amazon Bedrock. Thecompany has a limited budget and prefers flexibility without long-term commitment.

Which Amazon Bedrock pricing model meets these requirements?

A. On-Demand

B. Model customization

C. Provisioned Throughput

D. Spot Instance

一家公司希望使用亚马逊 Bedrock 创建一个应用程序。该公司预算有限，并且希望具有灵活性，无需长期承诺。 哪种亚马逊 Bedrock 定价模式能满足这些要求？ 

A. Amazon Personalize 

B. Amazon SageMaker Jump Start 

C. PartyRock（亚马逊 Bedrock 的一个实验平台） 

D. Amazon SageMaker 端点

Which AWS service or feature can help an Al development team quickly deploy and consume a foundation model (FM) within the team's VPC?

A. Amazon Personalize

B. Amazon SageMaker Jump Start

C. PartyRock, an Amazon Bedrock Playground

D. Amazon SageMaker endpoints

A. 设计清晰且具体的提示。使用最小权限访问原则配置 AWS 身份与访问管理（IAM）角色和策略。 

B. 启用 AWS 审计管理器以执行自动模型评估作业。 

C. 启用亚马逊 Bedrock 自动模型评估作业。 

D. 使用亚马逊 CloudWatch 日志使模型具有可解释性并监控偏差。

How can companies use large language models (LLMs) securelyon Amazon Bedrock?

A. Design clear and specific prompts. Configure AWS Identity and Acccess Management (IAM) roles and policies by using least privilege access.

B. Enable AWS Audit Manager for automatic model evaluation jobs.

C. Enable Amazon Bedrock automatic model evaluation jobs.

D. Use Amazon CloudWatch Logs to make models explainable and tomonitor for bias.

哪种解决方案能满足这些要求？ 

A. 生成式预训练变换器（GPT） 

B. 残差神经网络 

C. 支持向量机 

D. WaveNet

A company has terabytes of data in a database that the company can usefor business analysis. The company wants to build an Al-based application that can build a SQL query from input text that employees provvide. The employees have minimal experience with technology.

Which solution meets these requirements?

A. Generative pre-trained transformers (GPT)

B. Residual neural network

C. Support vector machine

D. WaveNet

当该模型分析一张新图像以识别其中的目标时，会发生以下哪种人工智能流程呢？ 

A. 训练 

B. 推理 

C. 模型部署 

D. 偏差修正

A company built a deep learning model for object detection and deployedthe model to production

Which Al process occurs when the model analyzes a new image to identify objects?

A. Training

B. Inference

C. Model deployment

D. Bias correction

哪种技术可以解决这个问题？ 

A. 对不平衡类别进行数据增强 

B. 对类别分布进行模型监控 

C. 检索增强生成（RAG） 

D. 图像水印检测

An Al practitioner is building a model to generate images of humans in various professions. The Al practitioner discovered that the input data is

biased and that specific attributes affect the image generation and create bias in the mode!

Which technique will solve the problem?

A. Data augmentation for imbalanced classes

B. Model monitoring for class distribution

C. Retrieval Augmented Generation (RAG)

D. Watermark detection for images

以下哪个解决方案能够满足这一需求呢？ 

A. 使用不同的基础模型。 

B. 选择较低的温度值。 

C. 创建一个亚马逊 Bedrock 知识库。 

D. 启用模型调用日志记录。

A company is implementing the Amazon Titan foundation model (FM) by using Amazon Bedrock. The company needs to supplement the modelby using relevant data from the company's private data sources.

Which solution will meet this requirement?

A. Use a different FM.

B. Choose a lower temperature value.

C. Create an Amazon Bedrock knowledge base.

D. Enable model invocation logging.

哪种解决方案能满足这些要求呢？ 

A. 使用亚马逊 Inspector 来配置安全和合规性。

B. 使用亚马逊 SageMaker Clarify 生成简单的指标、报告和示例。 

C. 使用亚马逊 Macie 对训练数据进行加密和保护。 

D. 收集更多数据，使用亚马逊 Rekognition 为数据添加自定义标签。

A medical company is customizing a foundation model (FM) fordiagnostic purposes. The company needs the model to be transparent and explainable to meet regulatory requirements.

Which solution will meet these requirements?

A. Configure the security and compliance by using Amazon Inspeector

B. Generate simple metrics, reports, and examples by using Amazon SageMaker Clarify

C. Encrypt and secure training data by using Amazon Macie.

D. Gather more data. Use Amazon Rekognition to add custom labelsto the data.

哪种解决方案能满足这些要求呢？ 

A. 减小批量大小（batch size）。

B. 增加训练轮数（epochs）。 

C. 减少训练轮数（epochs）。 

D. 增加温度参数（temperature parameter）。

A company is training a foundation model (FM). The company wants tto increase the accuracy of the model up to a specific acceptance leveel.

Which solution will meet these requirements?

A. Decrease the batch size.

B. Increase the epochs.

C. Decrease the epochs.

D. Increase the temperature parameter.