| 1 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Amazon ECR | What is the primary purpose of Amazon ECR (Elastic Container Registry)? | Easy | 1 | A | A managed container image registry that stores Docker images | A database service for containers | A compute service for running containers | A networking service for containers | ECR is a managed container image registry that stores Docker images for applications and integrates seamlessly with EC2 and other AWS services. |
| 2 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Amazon EC2 | What does Amazon EC2 (Elastic Compute Cloud) provide? | Easy | 1 | B | Container orchestration | Virtual servers where application code runs | Object storage | Database management | EC2 provides virtual servers where your application code runs. In multi-agent systems and RAG pipelines, EC2 instances host the orchestration layer and agent runtime environments. |
| 3 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | NAT Gateway | What is the primary function of a NAT Gateway in AWS? | Medium | 1 | C | Storing data in the cloud | Managing user permissions | Allowing private VPC resources to initiate outbound internet connections while remaining unreachable from the internet | Load balancing traffic between servers | NAT Gateway allows resources inside your private VPC to initiate outbound connections to the internet while remaining unreachable from the internet. |
| 4 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | VPC | What is a VPC (Virtual Private Cloud) in AWS? | Easy | 1 | D | A storage service | A compute instance | A database | A private network in AWS where you can isolate your resources | A VPC is a private network in AWS where you can isolate your resources. All services (EC2, databases, etc.) run within a VPC, controlling who can access what. |
| 5 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Amazon DynamoDB | Which of the following best describes Amazon DynamoDB? | Easy | 1 | A | A fast, NoSQL database excellent for applications requiring quick, unpredictable access patterns | A relational database service | A file storage service | A container registry | DynamoDB is a fast, NoSQL database excellent for applications requiring quick, unpredictable access patterns. It automatically scales based on traffic. |
| 6 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Amazon RDS | What type of data is Amazon RDS best suited for? | Medium | 1 | B | Unstructured data with simple access patterns | Structured data with complex relationships and transactions | Container images | Vector embeddings only | RDS provides managed relational databases. Unlike DynamoDB, RDS is best for structured data with complex relationships and transactions. |
| 7 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Amazon S3 | What can Amazon S3 (Simple Storage Service) store? | Easy | 1 | C | Only Docker images | Only database records | Any type of data—documents, images, logs, or raw training data | Only text files | S3 is object storage that can hold any type of data—documents, images, logs, or raw training data. It's highly scalable and cost-effective for large-scale data storage. |
| 8 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Amazon Bedrock | What does Amazon Bedrock provide? | Medium | 1 | A | Serverless access to foundation models for language generation and embedding tasks | Container orchestration services | Virtual private networking | Object storage | Amazon Bedrock provides serverless access to foundation models, enabling both language generation and embedding tasks without managing infrastructure. |
| 9 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | AWS IAM | What is the primary purpose of AWS IAM (Identity and Access Management)? | Easy | 1 | D | Storing files in the cloud | Running virtual machines | Managing databases | Controlling who can access which AWS resources and what actions they can perform | IAM controls who can access which AWS resources and what actions they can perform. It's fundamental for secure multi-agent architectures. |
| 10 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | RAG Pipeline | In a typical RAG system, what is the purpose of vectorization? | Medium | 1 | B | Compressing files for storage | Converting extracted text to embeddings for semantic search | Encrypting data for security | Formatting data for display | In RAG systems, vectorization converts extracted text to embeddings using services like Bedrock Embedding (Titan v2) for semantic search and retrieval. |
| 11 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | IAM Configuration | What command is used to configure AWS CLI with your credentials? | Easy | 1 | A | aws configure | aws setup | aws init | aws credentials | The command aws configure is used to set up your access key, secret access key, region, and output format for AWS CLI. |
| 12 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | IAM Access Keys | Where can AWS credentials be stored for authentication? | Medium | 1 | C | Only in environment variables | Only in the AWS web console | In ~/.aws/credentials file, environment variables, or via aws configure | Only in the application code | AWS credentials can be stored in ~/.aws/credentials file, using export commands for environment variables, or configured via aws configure command. |
| 13 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Amazon Bedrock | Which Python library is used to interact with Amazon Bedrock for chat functionality? | Medium | 1 | B | boto3 only | ChatBedrockConverse from langchain_aws | requests | tensorflow | The ChatBedrockConverse class from langchain_aws is used to interact with Amazon Bedrock for chat functionality with foundation models. |
| 14 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Embedding Models | Which embedding model is mentioned as available in Amazon Bedrock? | Easy | 1 | D | GPT-4 | DALL-E | Claude | Cohere Embed English v3 | Embedding models available in Bedrock include Titan v2 and Cohere (cohere.embed-english-v3) for creating vector embeddings. |
| 15 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | S3 Bucket | What is a requirement when naming an S3 bucket? | Easy | 1 | A | The bucket name must be globally unique across all AWS users | The bucket name must start with a number | The bucket name must be exactly 10 characters | The bucket name must contain special characters | When creating an S3 bucket, the name must be globally unique across all AWS users. |
| 16 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | S3 Vectors | What parameters are required when creating an index in S3 Vectors? | Hard | 1 | C | Only bucket name | Only index name and dimension | vectorBucketName, indexName, dataType, dimension, and distanceMetric | Only region and bucket name | When creating an index in S3 Vectors, you need to specify vectorBucketName, indexName, dataType (e.g., float32), dimension (e.g., 1024), and distanceMetric (e.g., cosine). |
| 17 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Amazon ECR | In a CI/CD pipeline, what command is used to authenticate Docker with Amazon ECR? | Medium | 1 | B | docker login ecr | aws ecr get-login-password | aws ecr authenticate | docker ecr connect | The command aws ecr get-login-password is used to get the password and pipe it to docker login for ECR authentication. |
| 18 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | EC2 Security | What should be configured in EC2 security groups to allow web traffic? | Easy | 1 | A | Inbound rules for HTTP and HTTPS traffic | Only outbound rules | VPC peering | NAT Gateway rules | Security groups need inbound and outbound rules to allow necessary traffic such as HTTP, HTTPS, and SSH for EC2 instances. |
| 19 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | EC2 CLI | Which AWS CLI command is used to stop an EC2 instance? | Easy | 1 | D | aws ec2 terminate-instances | aws ec2 start-instances | aws ec2 describe-instances | aws ec2 stop-instances | The command aws ec2 stop-instances --instance-ids <instance-id> is used to stop an EC2 instance. |
| 20 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | S3 Upload | When using boto3 to upload a file to S3, which method of the S3 client is used? | Medium | 1 | B | put_file | upload_file | send_file | transfer_file | The s3_client.upload_file() method is used in boto3 to upload a file to an S3 bucket, taking the file path, bucket name, and object name as parameters. |
| 21 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Service Selection | A customer wants to build a chatbot that can answer questions based on their company documents. Which combination of services should they use? | Hard | 1 | A | S3 for document storage, Bedrock for embeddings and LLM, DynamoDB for conversation state | EC2 only for all processing | RDS for document storage, EC2 for LLM | VPC and NAT Gateway only | For a RAG-based chatbot, S3 stores documents, Bedrock provides embeddings and LLM capabilities, and DynamoDB maintains conversation state for multi-turn interactions. |
| 22 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Service Selection | A customer needs to store user profiles with complex relationships between users, roles, and permissions. Which service is most appropriate? | Medium | 1 | B | DynamoDB | Amazon RDS | Amazon S3 | Amazon ECR | RDS is best for structured data with complex relationships and transactions, making it ideal for user profiles with relationships between users, roles, and permissions. |
| 23 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer's agents in a private VPC need to call external LLM APIs but the agents should not be directly accessible from the internet. What should they use? | Medium | 1 | C | VPC Peering | Internet Gateway | NAT Gateway | Direct Connect | NAT Gateway allows resources inside a private VPC to initiate outbound connections to the internet while remaining unreachable from the internet. |
| 24 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Service Selection | A customer wants to deploy multiple microservices as containers and needs a place to store and version their Docker images. Which service should they use? | Medium | 1 | A | Amazon ECR | Amazon S3 | Amazon RDS | Amazon DynamoDB | ECR is a managed container image registry that stores Docker images, enables versioning of pipeline processing containers, and integrates with CI/CD for automated deployments. |
| 25 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer needs to run inference pipelines that require flexible compute resources that can scale based on demand. Which service should they choose? | Medium | 1 | D | Amazon S3 | Amazon DynamoDB | Amazon ECR | Amazon EC2 | EC2 provides virtual servers with flexible compute for varying workloads, allowing customers to scale up or down based on demand and pay only for resources used. |
| 26 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Service Selection | A customer wants to implement semantic search across their knowledge base without managing embedding infrastructure. Which service should they use? | Medium | 1 | B | Amazon RDS | Amazon Bedrock | Amazon EC2 | NAT Gateway | Amazon Bedrock provides serverless access to embedding models like Titan v2, enabling semantic similarity matching without managing infrastructure. |
| 27 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer needs to ensure each component in their multi-agent system has only the necessary permissions to access specific resources. What should they implement? | Medium | 1 | A | AWS IAM with least-privilege access principles | VPC with private subnets | NAT Gateway restrictions | S3 bucket policies only | IAM enforces least-privilege access principles, defines roles for different agent services, and controls access to all AWS resources. |
| 28 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Architecture | A customer is building a RAG system and needs to store pre-computed vector embeddings for fast retrieval. Which storage option should they consider? | Hard | 1 | C | RDS with standard tables | DynamoDB with string attributes | S3 Vectors or S3 with structured format | EC2 local storage | S3 can store pre-computed vector embeddings in a structured format, and S3 Vectors enables efficient similarity search and retrieval for RAG systems. |
| 29 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer needs low-latency access to agent metadata and conversation context during multi-turn interactions. Which database should they use? | Medium | 1 | D | Amazon RDS | Amazon S3 | Amazon ECR | Amazon DynamoDB | DynamoDB provides low-latency access to agent metadata, stores conversation state and context, and maintains session information for multi-turn interactions. |
| 30 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Architecture | A customer wants to isolate their agent infrastructure for security and compliance while enabling private communication between components. What should they set up? | Medium | 1 | B | NAT Gateway | VPC | IAM Roles | S3 Bucket Policies | VPC isolates infrastructure for security, controls network traffic between services, enables private communication, and supports compliance requirements. |
| 31 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Service Selection | A customer needs to store large amounts of training data for fine-tuning models and wants a cost-effective, highly scalable solution. Which service fits best? | Medium | 1 | A | Amazon S3 | Amazon RDS | Amazon DynamoDB | Amazon EC2 EBS | S3 is highly scalable and cost-effective for large-scale data storage, making it ideal for storing training data for fine-tuning models. |
| 32 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer's application requires ACID transactions for critical operations involving user data. Which database service should they use? | Hard | 1 | C | Amazon DynamoDB | Amazon S3 | Amazon RDS | Amazon ECR | RDS supports ACID transactions for critical operations, making it suitable for applications requiring transaction integrity. |
| 33 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Architecture | A customer is designing a data ingestion pipeline where raw documents need to be stored and later processed for text extraction. Which service should store the raw documents? | Medium | 1 | B | Amazon DynamoDB | Amazon S3 | Amazon RDS | Amazon ECR | In a typical RAG pipeline, raw documents are stored in S3 before being processed for text extraction. S3 serves as the data lake for multi-agent knowledge. |
| 34 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer needs to audit all access and actions performed on their AWS resources for compliance purposes. Which service provides this capability? | Medium | 1 | D | Amazon S3 | Amazon VPC | Amazon DynamoDB | AWS IAM | IAM audits all access and actions for compliance, providing visibility into who accessed which resources and what actions were performed. |
| 35 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Service Selection | A customer wants to use foundation models for agent reasoning and decision-making without managing GPU infrastructure. Which service should they use? | Medium | 1 | A | Amazon Bedrock | Amazon EC2 with GPU instances | Amazon SageMaker | AWS Lambda | Amazon Bedrock provides serverless access to foundation models like NOVA PRO for agent reasoning and decision-making without managing infrastructure. |
| 36 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A developer created an IAM user but cannot access S3 vectors service. The error says "Access Denied". What is the most likely issue? | Hard | 1 | C | The AWS CLI is not installed | The region is incorrect | The user lacks the required s3vectors permissions policy | The S3 bucket doesn't exist | Some policies like s3vectors are not available in the policy generator, so an inline policy with s3vectors actions must be created and attached to the user. |
| 37 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer wants to run their Python application that uses boto3 on a new machine but gets "NoCredentialsError". What should they do first? | Medium | 1 | B | Install Python | Run aws configure to set up credentials | Create an S3 bucket | Install Docker | The aws configure command sets up access key, secret access key, and region, which are required for boto3 to authenticate with AWS services. |
| 38 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Architecture | A customer wants to automate the deployment of their containerized application whenever code is pushed to GitHub. Which services should be involved? | Hard | 1 | D | S3 and DynamoDB | RDS and EC2 | VPC and NAT Gateway | ECR for image storage and EC2 for deployment via CI/CD pipeline | A CI/CD pipeline builds Docker images, pushes them to ECR, then deploys to EC2 by pulling new images and restarting services. |
| 39 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer's EC2 instance cannot be accessed via SSH from their local machine. What should they check first? | Medium | 1 | A | Security group inbound rules for SSH (port 22) | The instance type | The AMI version | The EBS volume size | Security groups must have inbound rules configured to allow SSH traffic (port 22) for remote access to EC2 instances. |
| 40 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Service Selection | A customer needs to create vector embeddings for their documents and store them for semantic search. Which combination of services should they use? | Hard | 1 | B | EC2 and RDS | Bedrock Embeddings and S3 Vectors | Lambda and DynamoDB | ECS and ElastiCache | Bedrock Embeddings (like Cohere or Titan v2) create vector representations, and S3 Vectors provides scalable vector storage with indexing for semantic search. |
| 41 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer is getting "InvalidParameterValue" when creating an S3 Vectors index. They specified dataType as "int" and dimension as 1024. What is wrong? | Hard | 1 | C | The dimension is too large | The index name is invalid | The dataType should be "float32" not "int" | The bucket doesn't exist | When creating an S3 Vectors index, the dataType parameter should be "float32" for vector embeddings, not "int". |
| 42 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Architecture | A customer wants to use temporary AWS credentials in their application. Which method should they use to set credentials? | Medium | 1 | D | Only ~/.aws/credentials file | Only aws configure | Only environment variables | Environment variables including AWS_SESSION_TOKEN | For temporary credentials, you can use export commands including AWS_SESSION_TOKEN in addition to access key and secret access key. |
| 43 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer deployed their application to EC2 but it cannot pull Docker images from ECR. What should they verify? | Hard | 1 | A | The EC2 instance has run aws ecr get-login-password and authenticated with Docker | The S3 bucket permissions | The DynamoDB table exists | The VPC has internet access only | To pull images from ECR, the EC2 instance must authenticate Docker with ECR using aws ecr get-login-password piped to docker login. |
| 44 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Service Selection | A customer wants to query similar documents based on semantic meaning from their knowledge base. What feature of S3 Vectors should they use? | Medium | 1 | B | ListVectors | QueryVectors | GetVectors | PutVectors | The QueryVectors action in S3 Vectors enables semantic similarity search across the vector index based on query embeddings. |
| 45 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer's boto3 code is connecting to the wrong AWS region. How can they specify the correct region in their code? | Medium | 1 | C | Only through aws configure | Only through environment variables | By passing region_name parameter to boto3.client() | By modifying the AWS SDK source code | The region_name parameter can be passed directly to boto3.client() to specify the AWS region, e.g., boto3.client("s3vectors", region_name="ap-southeast-1"). |
| 46 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Architecture | A customer is building a multi-agent system where agents need to cache frequently accessed embeddings for fast retrieval. Which service should they use? | Medium | 1 | A | Amazon DynamoDB | Amazon S3 | Amazon RDS | Amazon ECR | DynamoDB is ideal for caching frequently accessed embeddings due to its low-latency access and automatic scaling based on traffic. |
| 47 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer wants their backend workers to process tasks asynchronously while the main orchestration server handles user requests. Which service hosts both components? | Medium | 1 | D | Amazon S3 | Amazon DynamoDB | Amazon ECR | Amazon EC2 | EC2 runs both agent orchestration servers and hosts background workers processing tasks, providing flexible compute for varying workloads. |
| 48 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer is trying to upload a file to S3 using boto3 but gets "NoSuchBucket" error. What should they verify? | Medium | 1 | B | The file exists locally | The bucket name is correct and the bucket exists | The IAM permissions | The region setting | The "NoSuchBucket" error indicates the specified bucket doesn't exist. The customer should verify the bucket name is correct and the bucket has been created. |
| 49 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Architecture | A customer wants to tag their Docker images with both "latest" and the git commit SHA for version tracking in ECR. Why is this a good practice? | Hard | 1 | C | It reduces storage costs | It improves image pull speed | It enables rollback to specific versions while maintaining a latest reference | It is required by ECR | Tagging with both latest and git SHA allows maintaining a latest reference for convenience while enabling rollback to specific versions using the commit SHA. |
| 50 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Service Selection | A customer needs to store pgvector extensions for PostgreSQL-based vector search. Which service supports this? | Hard | 1 | A | Amazon RDS with PostgreSQL | Amazon DynamoDB | Amazon S3 | Amazon ECR | RDS with PostgreSQL can store vector extensions like pgvector, enabling vector-based similarity search within a relational database. |
| 51 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer's CI/CD pipeline fails when pushing to ECR with "denied: Your authorization token has expired". What should they do? | Medium | 1 | B | Create a new ECR repository | Re-run aws ecr get-login-password to get a fresh token | Change the Docker image tag | Restart the EC2 instance | ECR authorization tokens expire, so the pipeline needs to re-authenticate by running aws ecr get-login-password before pushing images. |
| 52 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Architecture | A customer is designing a system where agents need to track decision history for debugging and auditing. Which services should store this data? | Hard | 1 | D | S3 only | EC2 local storage | ECR | DynamoDB for quick access and RDS for audit trails | DynamoDB tracks agent decision history with low-latency access, while RDS maintains audit trails of agent actions with complex query capabilities. |
| 53 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer wants to list all available foundation models in Amazon Bedrock using Python. Which boto3 client method should they call? | Medium | 1 | A | bedrock_client.list_foundation_models() | bedrock_client.get_models() | bedrock_client.describe_models() | bedrock_client.show_models() | The list_foundation_models() method of the bedrock client returns a list of available Amazon Bedrock foundation models. |
| 54 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Architecture | A customer wants to embed multiple documents in batch for their RAG system. Which BedrockEmbeddings method should they use? | Medium | 1 | C | embed_query() | embed_single() | embed_documents() | embed_batch() | The embed_documents() method of BedrockEmbeddings accepts a list of documents and returns embeddings for all of them. |
| 55 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer's agents are making external API calls but the responses are slow due to network latency from the private subnet. What should they check? | Hard | 1 | B | The EC2 instance type | The NAT Gateway configuration and bandwidth | The S3 bucket region | The DynamoDB read capacity | NAT Gateway enables outbound connections from private subnets. Slow responses could indicate NAT Gateway bandwidth or configuration issues. |
| 56 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Service Selection | A customer wants to use cosine similarity for comparing vectors in their semantic search system. Which parameter should they set when creating an S3 Vectors index? | Medium | 1 | D | dataType | dimension | indexName | distanceMetric | The distanceMetric parameter should be set to "cosine" when creating an S3 Vectors index for cosine similarity comparisons. |
| 57 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Problem Solving | A customer's multi-agent system needs to maintain temporary working memory for complex tasks. Which service is most appropriate? | Medium | 1 | A | Amazon DynamoDB | Amazon S3 | Amazon RDS | Amazon ECR | DynamoDB manages temporary working memory for complex tasks due to its low-latency access and automatic scaling capabilities. |
| 58 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Architecture | A customer deployed their application but environment variables with AWS credentials are not persisting after EC2 restart. What is a better approach? | Hard | 1 | C | Hardcode credentials in the application | Store credentials in S3 | Use ~/.aws/credentials file or IAM roles for EC2 | Store credentials in DynamoDB | The ~/.aws/credentials file persists credentials, or better yet, use IAM roles attached to EC2 instances for automatic credential management. |
| 59 | Unit 5: Basic Cloud Essentials for Developer | Lec2 | Problem Solving | A customer is using ChatBedrockConverse and gets "ValidationException: Model not found". What should they verify? | Hard | 1 | B | The AWS CLI version | The model_id is correct and the model is available in the specified region | The temperature parameter | The max_tokens parameter | The model_id must be a valid model identifier (e.g., "amazon.nova-lite-v1:0") and the model must be available in the specified region_name. |
| 60 | Unit 5: Basic Cloud Essentials for Developer | Lec1 | Service Selection | A customer wants to enable batch processing of large datasets for their RAG knowledge base. Which service should store the datasets? | Medium | 1 | A | Amazon S3 | Amazon DynamoDB | Amazon ECR | Amazon VPC | S3 enables batch processing of large datasets and serves as a data lake for multi-agent knowledge, making it ideal for RAG knowledge bases. |