# Sample config for the GAIA GenAI platform module.
# Deploys a conversational AI chatbot with Bedrock foundation models,
# RAG engines (SageMaker, Aurora, Kendra, Knowledge Base), Cognito auth,
# VPC networking, and API Gateway endpoints.
#
# This comprehensive config uses email/password authentication and
# exercises every compatible optional property at full depth.

# Complete GAIA generative AI platform configuration including RAG
# engines, LLM models, authentication, VPC networking, and chatbot
# API setup.
gaia:
  # See CONFIGURATION.md for role reference options (name, arn, id).
  # Admin roles granted access to GAIA app resources (like
  # KMS/Bucket). Roles can be referenced by name, arn, or id.
  dataAdminRoles:
    - name: Admin
    - arn: 'arn:{{partition}}:iam::{{account}}:role/test-admin-role'
  # Prefix for GAIA resource naming
  prefix: testing
  # (Optional) Enable Powertools dev logging
  # (enum: "true", "false")
  powertoolsDevLogging: 'true'
  # (Optional) Main domain for the GAIA platform
  mainDomain: test-domain.example.com
  # (Optional) Amazon Bedrock integration configuration for
  # foundation model access
  bedrock:
    # Enables or disables Amazon Bedrock foundation model
    # integration
    enabled: true
    # AWS region for Bedrock foundation model access
    # (enum: SupportedRegion values)
    region: 'ca-central-1'
    # (Optional) IAM role ARN for cross-account or custom Bedrock
    # access
    roleArn: 'arn:{{partition}}:iam::{{account}}:role/test-bedrock-role'
  # LLM model configurations
  llms:
    # (Optional) HuggingFace API token for model access
    huggingFaceApiToken: 'hf_test_token_placeholder'
    # SageMaker-hosted LLM model configurations
    sagemaker:
      - # SageMaker LLM model to deploy
        # (enum: FalconLite, Llama2_13b_Chat, Mistral7b_Instruct2)
        model: FalconLite
        # (Optional) SageMaker instance type for LLM hosting
        instanceType: ml.g5.2xlarge
        # (Optional) Initial number of instances for the LLM
        # endpoint
        initialInstanceCount: 1
        # (Optional) Minimum instance count for auto-scaling
        minimumInstanceCount: 1
        # (Optional) Maximum instance count for auto-scaling
        maximumInstanceCount: 2
      - # SageMaker LLM model to deploy
        # (enum: FalconLite, Llama2_13b_Chat, Mistral7b_Instruct2)
        model: Llama2_13b_Chat
      - # SageMaker LLM model to deploy
        # (enum: FalconLite, Llama2_13b_Chat, Mistral7b_Instruct2)
        model: Mistral7b_Instruct2
  # (Optional) RAG engine and embedding model configuration
  rag:
    # Retrieval engine configuration
    engines:
      # (Optional) SageMaker RAG engine
      sagemaker:
        # (Optional) SageMaker instance type for RAG
        instanceType: ml.inf1.xlarge
        # (Optional) Initial instance count
        initialInstanceCount: 1
        # (Optional) Minimum instance count for auto-scaling
        minInstanceCount: 1
        # (Optional) Maximum instance count for auto-scaling
        maxInstanceCount: 2
      # (Optional) Aurora RAG engine
      aurora:
        # (Optional) Minimum Aurora Serverless capacity units
        minCapacity: 0.5
        # (Optional) Maximum Aurora Serverless capacity units
        maxCapacity: 4
        # (Optional) Create separate security group for Aurora
        createSeparateSecurityGroup: true
      # (Optional) Kendra RAG engine
      kendra:
        # Whether to create a new Kendra index
        createIndex: true
        # (Optional) S3 data source configuration for Kendra index
        s3DataSourceConfig:
          # S3 bucket name for Kendra data source
          bucketName: test-kendra-bucket
          # Directories to include in the Kendra index
          includedDirectories:
            - documents/
          # KMS key ARN for encrypting Kendra data
          kmsKeyArn: 'arn:{{partition}}:kms:{{region}}:{{account}}:key/test-kendra-key'
          # (Optional) Metadata directory for Kendra documents
          metadataDirectory: metadata/
        # (Optional) External Kendra index configurations
        external:
          - # Kendra index ID
            kendraId: test-kendra-index-id
            # Name for the external Kendra index
            name: test-external-kendra
            # (Optional) AWS region for the external Kendra index
            # (enum: SupportedRegion values)
            region: ca-central-1
            # (Optional) IAM role ARN for cross-account Kendra
            # access
            roleArn: 'arn:{{partition}}:iam::{{account}}:role/test-kendra-role'
      # (Optional) Bedrock Knowledge Base RAG engine
      knowledgeBase:
        # (Optional) External Knowledge Base configurations
        external:
          - # Knowledge Base ID
            kbId: test-kb-id
            # Name for the external Knowledge Base
            name: test-external-kb
            # (Optional) AWS region for the external Knowledge Base
            # (enum: SupportedRegion values)
            region: ca-central-1
            # (Optional) IAM role ARN for cross-account KB access
            roleArn: 'arn:{{partition}}:iam::{{account}}:role/test-kb-role'
    # Embedding models for vector processing
    embeddingsModels:
      - # Model provider (enum: bedrock, openai, sagemaker)
        provider: 'bedrock'
        # Model name identifier
        name: 'amazon.titan-embed-text-v2:0'
        # Vector embedding dimensions
        dimensions: 1024
        # (Optional) Whether this is the default model
        isDefault: true
      - # Model provider (enum: bedrock, openai, sagemaker)
        provider: 'sagemaker'
        # Model name identifier
        name: 'test-sagemaker-embedding-model'
        # Vector embedding dimensions
        dimensions: 768
      - # Model provider (enum: bedrock, openai, sagemaker)
        provider: 'openai'
        # Model name identifier
        name: 'text-embedding-3-large'
        # Vector embedding dimensions
        dimensions: 3072
    # Cross-encoder models for document ranking
    crossEncoderModels:
      - # Model provider (enum: bedrock, openai, sagemaker)
        provider: 'bedrock'
        # Model name identifier
        name: 'test-cross-encoder-model'
        # (Optional) Whether this is the default model
        isDefault: true
      - # Model provider (enum: bedrock, openai, sagemaker)
        provider: 'sagemaker'
        # Model name identifier
        name: 'test-sagemaker-cross-encoder'
  # (Optional) Lambda concurrency settings
  concurrency:
    # (Optional) Concurrent Lambda executions for model interface
    modelInterfaceConcurrentLambdas: 10
    # (Optional) Concurrent Lambda executions for REST API
    restApiConcurrentLambdas: 10
    # (Optional) Concurrent Lambda executions for WebSocket
    websocketConcurrentLambdas: 10
  # Authentication configuration for user access.
  # This config uses email/password authentication.
  auth:
    # Authentication method for the GAIA platform
    # (enum: email_pass, ad, existing)
    authType: 'email_pass'
    # (Optional) Custom Cognito User Pool domain for branded
    # authentication URLs. Must be globally unique.
    cognitoDomain: 'some-unique-pool-domain-name'
  # (Optional) Set API Gateway account CloudWatch role
  setApiGateWayAccountCloudwatchRole: true
  # (Optional) Skip default WAF for API Gateway
  skipApiGatewayDefaultWaf: true
  # (Optional) Custom code override paths for GAIA Lambda
  # functions, layers, and batch jobs. Allows replacing default
  # implementations with custom code. Requires actual code
  # directories/files to exist at the specified paths.
  # Cannot be exercised in synth tests without real code assets.
  # codeOverwrites:
  #   # (Optional) Custom code path for the REST API handler
  #   # Lambda replacing default CRUD operations.
  #   restApiHandlerCodePath: ./custom/rest-api-handler
  #   # (Optional) Custom code path for LangChain interface
  #   # handler Lambda for AI chain orchestration.
  #   langchainInterfaceHandlerCodePath: ./custom/langchain
  #   # (Optional) Custom code path for WebSocket connection
  #   # handler Lambda for real-time connection management.
  #   webSocketConnectionHandlerCodePath: ./custom/ws-conn
  #   # (Optional) Custom code path for WebSocket incoming
  #   # message handler Lambda for message routing.
  #   webSocketIncomingMessageHandlerCodePath: ./custom/ws-in
  #   # (Optional) Custom code path for WebSocket outgoing
  #   # message handler Lambda for response delivery.
  #   webSocketOutgoingMessageHandlerCodePath: ./custom/ws-out
  #   # (Optional) Custom code path for WebSocket authorizer
  #   # Lambda for authentication and authorization.
  #   webSocketAuthorizerFunctionCodePath: ./custom/ws-auth
  #   # (Optional) Custom code path for RAG engines inference
  #   # Lambda for document retrieval and AI response generation.
  #   ragEnginesInferenceCodePath: ./custom/rag-inference
  #   # (Optional) Custom code path for data import upload
  #   # handler Lambda for data ingestion orchestration.
  #   dataImportUploadHandlerCodePath: ./custom/data-import
  #   # (Optional) Custom code path for Aurora workspace
  #   # creation Lambda for workspace provisioning.
  #   createAuroraWorkspaceCodePath: ./custom/aurora-workspace
  #   # (Optional) Custom code path for workspace deletion
  #   # handler Lambda for cleanup and resource management.
  #   deleteWorkspaceHandlerCodePath: ./custom/delete-workspace
  #   # (Optional) Custom code path for Aurora pgVector database
  #   # setup Lambda for vector store initialization.
  #   pgVectorDbSetupCodePath: ./custom/pgvector-setup
  #   # (Optional) Custom code path for GenAI core Lambda layer
  #   # containing shared AI clients and service functionality.
  #   genAiCoreLayerCodePath: ./custom/genai-core-layer
  #   # (Optional) Custom ZIP path for common libraries Lambda
  #   # layer shared across multiple GAIA Lambda functions.
  #   commonLibsLayerCodeZipPath: ./custom/common-libs.zip
  #   # (Optional) Custom Dockerfile path for file import AWS
  #   # Batch job container for batch processing.
  #   fileImportBatchJobDockerFilePath: ./custom/Dockerfile
  #   # (Optional) Custom code path for website parser Lambda
  #   # for web crawling and content extraction.
  #   websiteParserCodePath: ./custom/website-parser
  # (Optional) Backend API configuration for custom REST and
  # WebSocket domains with Route53 DNS. Requires account/region
  # to be specified in the stack environment for hosted zone
  # lookup. Cannot be exercised in synth tests without a real
  # AWS environment.
  # api:
  #   # Route53 hosted zone name for DNS
  #   hostedZoneName: example.com
  #   # Custom domain name for REST API
  #   restApiDomainName: api.example.com
  #   # Custom domain name for WebSocket API
  #   socketApiDomainName: ws.example.com
  # VPC networking configuration for GAIA infrastructure
  vpc:
    # VPC identifier for hosting GAIA application components
    # Often created by your VPC/networking stack.
    # Example SSM: ssm:/path/to/vpc/id
    vpcId: XXXXXXXX
    # Security group ID for application tier components
    # Often created by your VPC/networking stack.
    # Example SSM: ssm:/path/to/security-group/id
    appSecurityGroupId: 'sg-12345351356'
    # Subnet IDs for the application tier
    # Often created by your VPC/networking stack.
    # Example SSM: ssm:/path/to/subnet/id
    appSubnets:
      - subnet1
      - subnet1b
    # Security group ID for data tier components
    # Often created by your VPC/networking stack.
    # Example SSM: ssm:/path/to/security-group/id
    dataSecurityGroupId: 'sg-46576878787'
    # Subnet IDs for the data tier
    # Often created by your VPC/networking stack.
    # Example SSM: ssm:/path/to/subnet/id
    dataSubnets:
      - subnet2
      - subnet2b