pca-main.template

AWSTemplateFormatVersion: "2010-09-09"

Description: Amazon Transcribe Post Call Analytics - PCA (v0.6.0) (uksb-1sn29lk73)

Parameters:

  AdminUsername:
    Type: String
    Default: "admin"
    Description: (Required) Username for admin user
    
  AdminEmail:
      Type: String
      Description: >-
        (Required) Email address for the admin user. Will be used for logging in and for setting the admin password. 
        This email will receive the temporary password for the admin user.
      AllowedPattern: ".+\\@.+\\..+"
      ConstraintDescription: Must be valid email address eg. johndoe@example.com

  BulkUploadBucketName:
    Type: String
    Default: ""
    Description: >-
      (Optional) Existing bucket where files can be dropped, and a secondary Step Function can be 
      manually enabled to drip feed them into the system. 
      Leave blank to automatically create new bucket.

  BulkUploadMaxDripRate:
    Type: String
    Default: "25"
    Description: Maximum number of files that the bulk uploader will move to the PCA source bucket in one pass

  BulkUploadMaxTranscribeJobs:
    Type: String
    Default: "50"
    Description: Number of concurrent Transcribe jobs (executing or queuing) where bulk upload will pause

  ComprehendLanguages:
    Type: String
    Default: de | en | es | it | pt | fr | ja | ko | hi | ar | zh | zh-TW
    Description: Languages supported by Comprehend's standard calls, separated by " | "

  ContentRedactionLanguages:
    Type: String
    Default: en-US
    Description: Languages supported by Transcribe's Content Redaction feature, separated by " | "

  ConversationLocation:
    Type: String
    AllowedPattern: "[+-_\/a-zA-Z0-9]*"
    Default: America/New_York
    Description: Name of the timezone location for the call source - this is the TZ database name from https://en.wikipedia.org/wiki/List_of_tz_database_time_zones

  EntityRecognizerEndpoint:
    Type: String
    Default: undefined
    Description: Name of the custom entity recognizer for Amazon Comprehend (not including language suffix, e.g. -en). If one cannot be found then simple entity string matching is attempted instead

  EntityStringMap:
    Type: String
    Default: sample-entities.csv
    Description: Basename of a CSV file containing item/Entity maps for when we don't have data for Comprehend Custom Entities (not including language suffix, e.g. -en)

  EntityThreshold:
    Type: String
    Default: "0.6"
    Description: Confidence threshold where we accept the custom entity detection result

  EntityTypes:
    Type: String
    Default: PERSON | LOCATION | ORGANIZATION | COMMERCIAL_ITEM | EVENT | DATE | QUANTITY | TITLE
    Description: Entity types supported by Comprehend's standard entity detection, separated by " | "

  InputBucketAudioPlayback:
    Type: String
    Default: playbackAudio
    Description: Folder that holds the audio files to playback in the browser

  InputBucketFailedTranscriptions:
    Type: String
    Default: failedAudio
    Description: Folder that holds the audio files that for some reason failed transcription

  InputBucketName:
    Type: String
    Default: ""
    Description: >-
      (Optional) Existing bucket holding all audio files for the system. 
      Leave blank to automatically create new bucket with intelligent tiering storage and automated retention policy.

  InputBucketRawAudio:
    Type: String
    Default: originalAudio
    Description: Prefix/Folder that holds the audio files to be ingested into the system

  InputBucketOrigTranscripts:
    Type: String
    Default: originalTranscripts
    Description: >
      Folder that holds Transcripts from other applications (e.g. Live Call Analytics) that are to be
      processed as if PCA had processed that audio

  MaxSpeakers:
    Type: String
    Default: "2"
    Description: Maximum number of speakers that are expected on a call

  MinSentimentNegative:
    Type: String
    Default: "2.0"
    Description: Minimum sentiment level required to declare a phrase as having negative sentiment, in the range 0.0-5.0

  MinSentimentPositive:
    Type: String
    Default: "2.0"
    Description: Minimum sentiment level required to declare a phrase as having positive sentiment, in the range 0.0-5.0

  OutputBucketName:
    Type: String
    Default: ""
    Description: >-
      (Optional) Existing bucket where Transcribe output files are delivered. 
      Leave blank to automatically create new bucket with intelligent tiering storage and automated retention policy.

  OutputBucketTranscribeResults:
    Type: String
    Default: transcribeResults
    Description: Folder within the output S3 bucket where Transcribe results are written

  OutputBucketParsedResults:
    Type: String
    Default: parsedFiles
    Description: Folder within the output S3 bucket where parsed results are written

  SpeakerNames:
    Type: String
    Default: Customer | Agent
    AllowedValues:
        - Customer | Agent
        - Agent | Customer
    Description: Speaker label assignment order

  SpeakerSeparationType:
    Type: String
    Default: channel
    AllowedValues:
        - speaker
        - channel
    Description: Separation mode diarization - typically speaker for mono files, channel for stereo files

  StepFunctionName:
    Type: String
    AllowedPattern: "[-_a-zA-Z0-9]*"
    Default: PostCallAnalyticsWorkflow
    Description: Name of Step Functions workflow that orchestrates this process
    
  BulkUploadStepFunctionName:
    Type: String
    AllowedPattern: "[-_a-zA-Z0-9]*"
    Default: BulkUploadWorkflow
    Description: Name of Step Functions workflow that orchestrates the bulk import process
    
  SupportFilesBucketName:
    Type: String
    Default: ''
    Description: >-
      (Optional) Existing bucket that hold supporting files, such as the  file-based
      entity recognition mapping files.  Leave blank to automatically create new bucket.

  TranscribeLanguages:
    Type: String
    Default: en-US
    Description: Language to be used for Transcription - multiple entries separated by " | " will trigger Language Detection

  VocabFilterMode:
    Type: String
    Default: mask
    AllowedValues:
        - mask
        - remove
    Description: The mode to use for vocabulary filtering - must be one of mask or remove (tag is not supported)

  VocabFilterName:
    Type: String
    Default: undefined
    Description: Name of the vocabulary filter to use for Transcribe (not including language suffix, e.g. -en)

  VocabularyName:
    Type: String
    Default: undefined
    Description: Name of the custom vocabulary to use for Transcribe (omit the language suffix, e.g. -en-US)

  CustomLangModelName:
    Type: String
    Default: undefined
    Description: Name of the custom language model to use for Transcribe (omit the language suffix, e.g. -en-US)

  TranscribeApiMode:
    Type: String
    Default: analytics
    AllowedValues:
        - standard
        - analytics
    Description: Set the default operational mode for Transcribe

  TelephonyCTRType:
    Type: String
    Default: none
    AllowedValues:
        - none
        - genesys
    Description: Type of telephony system that will deliver Contact Trace Record files along with the audio recordings

  TelephonyCTRFileSuffix:
    Type: String
    Default: "_metadata.json | _call_metadata.json"
    Description: >
      File name suffixes for the CTR file(s) associated with the chosen telephony type, separated by " | ".
      For Genesys, this needs two entries: one for the conversation CTR file, and one for the call-specific file.
      Other telephony systems may need fewer or additional entries, please consult the documentation.

  CallRedactionTranscript:
    Type: String
    Default: true
    AllowedValues:
        - true
        - false
    Description: Enable or disable Transcribe's redaction feature

  CallRedactionAudio:
    Type: String
    Default: true
    AllowedValues:
        - true
        - false
    Description: When transcript redaction is enabled in Call Analytics, only allow playback of the redacted audio

  ffmpegDownloadUrl:
    Type: String
    Default: https://www.johnvansickle.com/ffmpeg/old-releases/ffmpeg-4.4-amd64-static.tar.xz
    Description: URL for ffmpeg binary distribution tar file download - see https://www.johnvansickle.com/ffmpeg/

  loadSampleAudioFiles:
    Type: String
    Default: false
    AllowedValues:
        - true
        - false
    Description: Set to true to automatically ingest sample audio files.
    
  FilenameDatetimeRegex:
    Type: String
    Default: '(\d{4})-(\d{2})-(\d{2})T(\d{2})-(\d{2})-(\d{2})'
    Description: >
      Regular Expression (regex) used to parse call Date/Time from audio filenames. 
      Each datetime field (year, month, etc.) must be matched using a separate parenthesized group in the regex. 
      Example: the regex '(\d{4})-(\d{2})-(\d{2})T(\d{2})-(\d{2})-(\d{2})' parses
      the filename: CallAudioFile-2021-12-01T07-55-51.wav into a value list: [2021, 12, 01, 07, 55, 51]
      The next parameter, FilenameDatetimeFieldMap, maps the values to datetime field codes.
      If the filename doesn't match the regex pattern, the current time is used as the call timestamp.

  FilenameDatetimeFieldMap:
    Type: String
    Default: '%Y %m %d %H %M %S'
    Description: >
      Space separated ordered sequence of time field codes as used by Python's datetime.strptime() function. 
      Each field code refers to a corresponding value parsed by the regex parameter filenameTimestampRegex. 
      Example: the mapping '%Y %m %d %H %M %S' assembles the regex output values [2021, 12, 01, 07, 55, 51]
      into the full datetime: '2021-12-01 07:55:51'.  
      If the field map doesn't match the value list parsed by the regex, then the current time is used as the call timestamp.

  FilenameGUIDRegex:
    Type: String
    Default: '_GUID_(.*?)_'
    Description: >
      Regular Expression (regex) used to parse call GUID from audio filenames. 
      The GUID value must be matched using one or more parenthesized groups in the regex. 
      Example: the regex '_GUID_(.*?)_' parses
      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
      to extract the GUID value '2a602c1a-4ca3-4d37-a933-444d575c0222'.

  FilenameAgentRegex:
    Type: String
    Default: '_AGENT_(.*?)_'
    Description: >
      Regular Expression (regex) used to parse call AGENT from audio filenames. 
      The AGENT value must be matched using one or more parenthesized groups in the regex. 
      Example: the regex '_AGENT_(.*?)_' parses
      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
      to extract the AGENT value 'BobS'. 
  
  FilenameCustRegex:
    Type: String
    Default: '_CUST_(.*?)_'
    Description: >
      Regular Expression (regex) used to parse Customer from audio filenames. 
      The customer id value must be matched using one or more parenthesized groups in the regex. 
      Example: the regex '_CUST_(.*?)_' parses
      the filename: AutoRepairs1_CUST_12345_GUID_2a602c1a-4ca3-4d37-a933-444d575c0222_AGENT_BobS_DATETIME_07.55.51.067-09-16-2021.wav 
      to extract the Customer value '12345'.

  EnableTranscriptKendraSearch:
    Type: String
    Default: 'No'
    AllowedValues:
        - 'No'
        - 'Yes, create new Kendra Index (Developer Edition)'
        - 'Yes, create new Kendra Index (Enterprise Edition)'
    Description: Optionally make call transcripts searchable, using Amazon Kendra.

  RetentionDays:
    Type: Number
    Default: 365
    AllowedValues:
      - 30
      - 60
      - 90
      - 180
      - 365
      - 730
      - 1460
    Description: >
      When using auto-provisioned S3 buckets, your audio files and associated call analysis data will be 
      automatically and permanently deleted after the specified number of retention days. The application
      does not currently archive recordings or call data.

  Environment:
    Description: The type of environment to tag your infrastructure with. You can specify DEV (development), TEST (test), or PROD (production).
    Type: String
    AllowedValues:
      - DEV
      - TEST
      - PROD
    Default: PROD
    
  DatabaseName:
    Type: String
    Default: 'pca'
    Description: Glue catalog database name used to contain tables/views for SQL integration.

  EnablePcaDashboards:
    Type: String
    Default: 'No'
    AllowedValues:
        - 'No'
        - 'Yes'
    Description: >
      Optionally deploy advanced analytics pipeline and Amazon QuickSight dashboards. 
      IMPORTANT: Your Amazon QuickSight account MUST be enabled before deploying this stack. See http://www.amazon.com/pca-dashboards for additional 
      steps required in Amazon QuickSight to (1) enable S3 access to PCA OutputBucket and (2) share dashboard and analytics assets.

  CallSummarization:
    Default: 'DISABLED'
    Type: String
    AllowedValues:
      - 'DISABLED'
      - 'SAGEMAKER'
      - 'LAMBDA'
      - 'ANTHROPIC'
    Description: >
      Set to enable call summarization by a Large Language Model. The SAGEMAKER option uses a SageMaker endpoint with
      the pretrained bart-large-cnn-samsum model with a ml.m5.xlarge instance type.  The LAMBDA option requires you 
      to provide a function ARN below. The ANTHROPIC option is a third party service, and you must enter your Anthropic API key below.

  SummarizationSageMakerInitialInstanceCount:
    Type: Number
    MinValue: 0
    Default: 1
    Description: >
      (Optional) If 'CallSummarization' is SAGEMAKER, provide initial instance count. Set to '0' to enable Serverless Inference (for cold-start delay tolerant deployments only).

  SummarizationLLMThirdPartyApiKey:
    Type: String
    Description: >
      (Optional) If CallSummarization is ANTHROPIC, enter the provider API Key. ** Data will leave your AWS account **
    Default: ''
    NoEcho: true

  SummarizationLambdaFunctionArn:
    Default: ''
    Type: String
    AllowedPattern: '^(|arn:aws:lambda:.*)$'
    Description: >
      (Optional) If 'CallSummarization' is LAMBDA, provide ARN for a Lambda function.

Metadata:
    AWS::CloudFormation::Interface:
        ParameterGroups:
            - Label:
                default: Admin User
              Parameters:
                  - AdminUsername
                  - AdminEmail
            - Label:
                default: Sample Data
              Parameters:
                  - loadSampleAudioFiles
            - Label:
                default: Enable Call Transcript Search
              Parameters:
                  - EnableTranscriptKendraSearch
            - Label:
                default: Call Summarization
              Parameters:
                - CallSummarization
                - SummarizationSageMakerInitialInstanceCount
                - SummarizationLLMThirdPartyApiKey
                - SummarizationLambdaFunctionArn
            - Label:
                default: Advanced analytics and reporting
              Parameters:
                  - EnablePcaDashboards
                  - DatabaseName
            - Label:
                default: S3 Bucket Names and Retention Policy
              Parameters:
                  - InputBucketName
                  - BulkUploadBucketName
                  - OutputBucketName
                  - SupportFilesBucketName
                  - RetentionDays
            - Label:
                default: S3 bucket prefixes
              Parameters:
                  - InputBucketFailedTranscriptions
                  - InputBucketRawAudio
                  - InputBucketOrigTranscripts
                  - InputBucketAudioPlayback
                  - OutputBucketParsedResults
                  - OutputBucketTranscribeResults
            - Label:
                default: Filename metadata parsing
              Parameters:
                  - FilenameDatetimeRegex
                  - FilenameDatetimeFieldMap
                  - FilenameGUIDRegex
                  - FilenameAgentRegex
                  - FilenameCustRegex
            - Label:
                default: Transcription
              Parameters:
                  - TranscribeApiMode
                  - TranscribeLanguages
                  - VocabFilterMode
                  - VocabFilterName
                  - VocabularyName
                  - CustomLangModelName
                  - SpeakerSeparationType
                  - SpeakerNames
                  - MaxSpeakers
                  - CallRedactionTranscript
                  - CallRedactionAudio
                  - ContentRedactionLanguages
            - Label:
                default: Telephony system
              Parameters:
                  - TelephonyCTRType
                  - TelephonyCTRFileSuffix
            - Label:
                default: Entity detection
              Parameters:
                  - ComprehendLanguages
                  - EntityThreshold
                  - EntityTypes
                  - EntityRecognizerEndpoint
                  - EntityStringMap
            - Label:
                default: Sentiment detection
              Parameters:
                  - MinSentimentNegative
                  - MinSentimentPositive
            - Label:
                default: Bulk upload
              Parameters:
                - BulkUploadMaxDripRate
                - BulkUploadMaxTranscribeJobs
                - BulkUploadStepFunctionName
            - Label:
                default: Miscellaneous
              Parameters:
                - ConversationLocation
                - Environment
                - StepFunctionName
                - ffmpegDownloadUrl 

Conditions:
  ShouldCreateBulkUploadBucket: !Equals [!Ref BulkUploadBucketName, '']
  ShouldCreateInputBucket: !Equals [!Ref InputBucketName, '']
  ShouldCreateOutputBucket: !Equals [!Ref OutputBucketName, '']
  ShouldCreateSupportFilesBucket: !Equals [!Ref SupportFilesBucketName, '']
  ShouldEnableKendraSearch: !Not [!Equals [!Ref EnableTranscriptKendraSearch, 'No']]
  ShouldCreateKendraIndexDeveloperEdition: !Equals [!Ref EnableTranscriptKendraSearch, 'Yes, create new Kendra Index (Developer Edition)']
  ShouldDeployPcaDashboards: !Equals [!Ref EnablePcaDashboards, 'Yes']
  ShouldLoadSampleFiles: !Equals [!Ref loadSampleAudioFiles, 'true']

Resources:
  ########################################################
  # S3 buckets
  # TODO: Versioning? Lifecycle Policies? Access Logging?
  ########################################################

  BulkUploadBucket:
    Condition: ShouldCreateBulkUploadBucket
    Type: 'AWS::S3::Bucket'
    DeletionPolicy: Retain
    UpdateReplacePolicy: Retain 
    Properties:
      BucketEncryption:
        ServerSideEncryptionConfiguration:
          - ServerSideEncryptionByDefault:
              SSEAlgorithm: AES256

  InputBucket:
    Condition: ShouldCreateInputBucket
    Type: 'AWS::S3::Bucket'
    DeletionPolicy: Retain
    UpdateReplacePolicy: Retain 
    
    Properties:
      BucketEncryption:
        ServerSideEncryptionConfiguration:
          - ServerSideEncryptionByDefault:
              SSEAlgorithm: AES256
      LifecycleConfiguration:
        Rules:
          - Id: StorageClassAndRetention
            Status: Enabled
            ExpirationInDays: !Ref RetentionDays
            Transitions:
              - TransitionInDays: 1
                StorageClass: INTELLIGENT_TIERING

  OutputBucket:
    Condition: ShouldCreateOutputBucket
    Type: 'AWS::S3::Bucket'
    DeletionPolicy: Retain
    UpdateReplacePolicy: Retain 
    Properties:
      BucketEncryption:
        ServerSideEncryptionConfiguration:
          - ServerSideEncryptionByDefault:
              SSEAlgorithm: AES256
      LifecycleConfiguration:
        Rules:
          - Id: LifecycleRule
            Status: Enabled
            ExpirationInDays: !Ref RetentionDays
            Transitions:
              - TransitionInDays: 1
                StorageClass: INTELLIGENT_TIERING

  SupportFilesBucket:
    Condition: ShouldCreateSupportFilesBucket
    Type: 'AWS::S3::Bucket'
    DeletionPolicy: Retain
    UpdateReplacePolicy: Retain 
    Properties:
      BucketEncryption:
        ServerSideEncryptionConfiguration:
          - ServerSideEncryptionByDefault:
              SSEAlgorithm: AES256

  ########################################################
  # Kendra Index
  ########################################################
  KendraIndexRole:
    Type: 'AWS::IAM::Role'
    Condition: ShouldEnableKendraSearch
    Properties:
      AssumeRolePolicyDocument:
        Version: 2012-10-17
        Statement:
          - Sid: ''
            Effect: Allow
            Principal:
              Service: kendra.amazonaws.com
            Action: 'sts:AssumeRole'
      Policies:
        - PolicyDocument:
            Version: 2012-10-17
            Statement:
              - Effect: Allow
                Resource: '*'
                Condition:
                  StringEquals:
                    'cloudwatch:namespace': 'Kendra'
                Action:
                  - 'cloudwatch:PutMetricData'
              - Effect: Allow
                Resource: '*'
                Action: 'logs:DescribeLogGroups'
              - Effect: Allow
                Resource: !Sub
                  - 'arn:aws:logs:${region}:${account}:log-group:/aws/kendra/*'
                  - region: !Ref 'AWS::Region'
                    account: !Ref 'AWS::AccountId'
                Action: 'logs:CreateLogGroup'
              - Effect: Allow
                Resource: !Sub
                  - 'arn:aws:logs:${region}:${account}:log-group:/aws/kendra/*:log-stream:*'
                  - region: !Ref 'AWS::Region'
                    account: !Ref 'AWS::AccountId'
                Action: 
                  - 'logs:DescribeLogStreams'
                  - 'logs:CreateLogStream'
                  - 'logs:PutLogEvents'
          PolicyName: KendraMediaIndexPolicy

  KendraIndex:
    Type: 'AWS::Kendra::Index'
    Condition: ShouldEnableKendraSearch
    Properties:
      Description: PCA transcript index
      Edition:
          !If
          - ShouldCreateKendraIndexDeveloperEdition
          - 'DEVELOPER_EDITION'
          - 'ENTERPRISE_EDITION'
      Name: !Join
        - ''
        - - !Ref 'AWS::StackName'
          - '-Index'
      RoleArn: !GetAtt KendraIndexRole.Arn
      DocumentMetadataConfigurations:
        - Name: ANALYSIS_URI
          Search: 
            Displayable: true
          Type: 'STRING_VALUE'
        - Name: DATETIME
          Search: 
            Displayable: true
            Facetable: true
          Relevance:
            Freshness: true
          Type: 'DATE_VALUE'
        - Name: GUID
          Search: 
            Displayable: true
            Searchable: true
          Type: 'STRING_VALUE'
        - Name: AGENT
          Search:
            Displayable: true
            Facetable: true
          Type: 'STRING_VALUE'
        - Name: DURATION
          Search: 
            Displayable: true
            Facetable: true
          Type: 'STRING_VALUE'
        - Name: ENTITY_PERSON
          Search: 
            Displayable: true
            Facetable: true
          Type: 'STRING_LIST_VALUE'        
        - Name: ENTITY_LOCATION
          Search: 
            Displayable: true
            Facetable: true
          Type: 'STRING_LIST_VALUE'
        - Name: ENTITY_ORGANIZATION
          Search: 
            Displayable: true
            Facetable: true
          Type: 'STRING_LIST_VALUE'
        - Name: ENTITY_COMMERCIAL_ITEM
          Search: 
            Displayable: true
            Facetable: true
          Type: 'STRING_LIST_VALUE'
        - Name: ENTITY_EVENT
          Search: 
            Displayable: true
            Facetable: true
          Type: 'STRING_LIST_VALUE'
        - Name: ENTITY_DATE
          Search:
            Displayable: true
            Facetable: true
          Type: 'STRING_LIST_VALUE'
        - Name: ENTITY_QUANTITY
          Search:
            Displayable: true
            Facetable: true
          Type: 'STRING_LIST_VALUE'
        - Name: ENTITY_TITLE
          Search:
            Displayable: true
            Facetable: true
          Type: 'STRING_LIST_VALUE'


  
  ########################################################
  # SSM Stack
  ########################################################
  SSM:
    Type: AWS::CloudFormation::Stack
    Properties:
      TemplateURL: pca-ssm/cfn/ssm.template
      Parameters:
        BulkUploadBucketName:
          !If
          - ShouldCreateBulkUploadBucket
          - !Ref BulkUploadBucket
          - !Ref BulkUploadBucketName
        BulkUploadMaxDripRate: !Ref BulkUploadMaxDripRate
        BulkUploadMaxTranscribeJobs: !Ref BulkUploadMaxTranscribeJobs
        ComprehendLanguages: !Ref ComprehendLanguages
        ContentRedactionLanguages: !Ref ContentRedactionLanguages
        ConversationLocation: !Ref ConversationLocation
        EntityRecognizerEndpoint: !Ref EntityRecognizerEndpoint
        EntityStringMap: !Ref EntityStringMap
        EntityThreshold: !Ref EntityThreshold
        EntityTypes: !Ref EntityTypes
        InputBucketAudioPlayback: !Ref InputBucketAudioPlayback
        InputBucketFailedTranscriptions: !Ref InputBucketFailedTranscriptions
        InputBucketName: 
          !If
          - ShouldCreateInputBucket
          - !Ref InputBucket
          - !Ref InputBucketName        
        InputBucketRawAudio: !Ref InputBucketRawAudio
        InputBucketOrigTranscripts: !Ref InputBucketOrigTranscripts
        MaxSpeakers: !Ref MaxSpeakers
        MinSentimentNegative: !Ref MinSentimentNegative
        MinSentimentPositive: !Ref MinSentimentPositive
        OutputBucketName: 
          !If
          - ShouldCreateOutputBucket
          - !Ref OutputBucket
          - !Ref OutputBucketName 
        OutputBucketTranscribeResults: !Ref OutputBucketTranscribeResults
        OutputBucketParsedResults: !Ref OutputBucketParsedResults
        SpeakerNames: !Ref SpeakerNames
        SpeakerSeparationType: !Ref SpeakerSeparationType
        StepFunctionName: !Ref StepFunctionName
        BulkUploadStepFunctionName: !Ref BulkUploadStepFunctionName
        SupportFilesBucketName: 
          !If
          - ShouldCreateSupportFilesBucket
          - !Ref SupportFilesBucket
          - !Ref SupportFilesBucketName
        TranscribeLanguages: !Ref TranscribeLanguages
        TranscribeApiMode: !Ref TranscribeApiMode
        TelephonyCTRType: !Ref TelephonyCTRType
        TelephonyCTRFileSuffix: !Ref TelephonyCTRFileSuffix
        CallRedactionTranscript: !Ref CallRedactionTranscript
        CallRedactionAudio: !Ref CallRedactionAudio
        VocabFilterName: !Ref VocabFilterName
        VocabFilterMode: !Ref VocabFilterMode
        VocabularyName: !Ref VocabularyName
        CustomLangModelName: !Ref CustomLangModelName
        FilenameDatetimeRegex: !Ref FilenameDatetimeRegex
        FilenameDatetimeFieldMap: !Ref FilenameDatetimeFieldMap
        FilenameGUIDRegex: !Ref FilenameGUIDRegex
        FilenameAgentRegex: !Ref FilenameAgentRegex
        FilenameCustRegex: !Ref FilenameCustRegex
        KendraIndexId:
          !If
          - ShouldEnableKendraSearch
          - !Ref KendraIndex
          - 'None'
        WebUri: !GetAtt PCAUI.Outputs.WebUri
        DatabaseName: !Ref DatabaseName


  PCAServer:
    Type: AWS::CloudFormation::Stack
    DependsOn: SSM
    Properties:
      TemplateURL: pca-server/cfn/pca-server.template
      Parameters:
        ffmpegDownloadUrl: !Ref ffmpegDownloadUrl
        CallSummarization: !Ref CallSummarization
        SummarizationSageMakerInitialInstanceCount: !Ref SummarizationSageMakerInitialInstanceCount
        SummarizationLLMThirdPartyApiKey: !Ref SummarizationLLMThirdPartyApiKey
        SummarizationLambdaFunctionArn: !Ref SummarizationLambdaFunctionArn

  PCAUI:
    Type: AWS::CloudFormation::Stack
    Properties:
      TemplateURL: pca-ui/cfn/pca-ui.template
      Parameters:
        AdminUsername: !Ref AdminUsername
        AdminEmail: !Ref AdminEmail
        MainStackName: !Ref AWS::StackName
        AudioBucket:
          !If
          - ShouldCreateInputBucket
          - !Ref InputBucket
          - !Ref InputBucketName 
        DataBucket:
          !If
          - ShouldCreateOutputBucket
          - !Ref OutputBucket
          - !Ref OutputBucketName
        DataPrefix: !Ref OutputBucketParsedResults
        Environment: !Ref Environment

  MediaSearchFinder:
    Type: AWS::CloudFormation::Stack
    Condition: ShouldEnableKendraSearch
    Properties:
      TemplateURL: build/pca-mediasearch-finder.yaml
      Parameters:
        AdminEmail: !Ref AdminEmail
        KendraIndexId: !Ref KendraIndex
        MediaBucketNames:
          !If
          - ShouldCreateInputBucket
          - !Ref InputBucket
          - !Ref InputBucketName

  PcaDashboards:
    Type: AWS::CloudFormation::Stack
    Condition: ShouldDeployPcaDashboards
    DependsOn: PCAServer
    Properties:
      TemplateURL: build/pca-dashboards.yaml
      Parameters:
        PcaGlueCatalogDatabaseName: !Ref DatabaseName
        PcaOutputBucket: 
          !If
          - ShouldCreateOutputBucket
          - !Ref OutputBucket
          - !Ref OutputBucketName
        PcaWebAppCallPathPrefix: !Sub "dashboard/${OutputBucketParsedResults}/"
        PcaWebAppHostAddress: !Select [1, !Split ["//", !GetAtt PCAUI.Outputs.WebUri]]

  CopySamples:
    Type: AWS::CloudFormation::Stack
    Condition: ShouldLoadSampleFiles
    Properties:
      TemplateURL: pca-samples/copy-samples.template
      Parameters:
        DependsOnPCAServer: !Ref PCAServer
        DependsOnPCADashboards: !If
          - ShouldDeployPcaDashboards
          - !Ref PcaDashboards
          - !Ref AWS::NoValue

  # Custom resource to check that QuickSight has been enabled - if not, fail fast and prevent downstream failures  

  QuickSightEnabledCheckFunctionRole:
    Type: "AWS::IAM::Role"
    Condition: ShouldDeployPcaDashboards
    Properties:
      AssumeRolePolicyDocument:
        Statement:
          - Effect: Allow
            Principal:
              Service: lambda.amazonaws.com
            Action:
              - "sts:AssumeRole"
      ManagedPolicyArns:
        - "arn:aws:iam::aws:policy/service-role/AWSLambdaBasicExecutionRole"
      Policies:
        - PolicyName: s3-input-bucket-write-policy
          PolicyDocument:
            Statement:
              Effect: Allow
              Action:
                - quicksight:ListDashboards
              Resource: "*"

  QuickSightEnabledCheckFunction:
    Type: AWS::Lambda::Function
    Condition: ShouldDeployPcaDashboards
    Properties:
      Handler: index.handler
      Runtime: python3.8
      Role: !GetAtt QuickSightEnabledCheckFunctionRole.Arn
      Code: 
        ZipFile: !Sub |
          import cfnresponse
          import boto3
          def handler(event, context):
            print(event)
            client = boto3.client('quicksight')
            status = cfnresponse.SUCCESS
            reason = f"QuickSight is enabled - OK"
            if event['RequestType'] != "Delete":
              try:
                response = client.list_dashboards(
                    AwsAccountId='${AWS::AccountId}',
                    )
              except Exception as e:
                print(e)
                status = cfnresponse.FAILED
                reason = f"No Amazon QuickSight account. To deploy PCA with Dashboards enabled, you must first create an account in the Amazon QuickSight console => {e}"
            else:
              reason = f"Request type is {event['RequestType']} - skipping"
            cfnresponse.send(event, context, status, {}, reason=reason) 

  IsQuickSightEnabled:
    Type: Custom::QuickSightCheck
    Condition: ShouldDeployPcaDashboards
    Properties:
      ServiceToken: !GetAtt QuickSightEnabledCheckFunction.Arn

Outputs:

  BulkUploadBucket:
    Description: S3 Bucket for uploading input audio files for alternate bulk upload workflow
    Value:
          !If
          - ShouldCreateBulkUploadBucket
          - !Ref BulkUploadBucket
          - !Ref BulkUploadBucketName

  InputBucket:
    Description: S3 Bucket for uploading input audio files
    Value:
      !If
      - ShouldCreateInputBucket
      - !Ref InputBucket
      - !Ref InputBucketName  
    
  InputBucketPrefix:
    Description: S3 Bucket prefix/folder for uploading input audio files
    Value: !Ref InputBucketRawAudio

  InputBucketTranscriptPrefix:
    Description: S3 Bucket prefix/folder for uploading input transcripts
    Value: !Ref InputBucketOrigTranscripts
  
  InputBucketPlaybackAudioPrefix:
    Description: S3 Bucket prefix/folder for audio used for playboack from browser
    Value: !Ref InputBucketAudioPlayback

  OutputBucket:
    Description: S3 Bucket where Transcribe output files are delivered
    Value:
      !If
      - ShouldCreateOutputBucket
      - !Ref OutputBucket
      - !Ref OutputBucketName  
    
  OutputBucketPrefix:
    Description: S3 Bucket path where Transcribe output files are delivered
    Value: !Ref OutputBucketParsedResults

  SupportFilesBucket:
    Description: S3 Bucket bucket that hold supporting files, such as the file-based entity recognition mapping files
    Value:
      !If
      - ShouldCreateSupportFilesBucket
      - !Ref SupportFilesBucket
      - !Ref SupportFilesBucketName  
    
  TranscriptionMediaSearchFinderURL:
    Description: Transcript Search Application link
    Value:
      !If
      - ShouldEnableKendraSearch
      - !GetAtt MediaSearchFinder.Outputs.MediaSearchFinderURL
      - "Not enabled"
 
  WebAppURL:
    Description: PCA Web Application link
    Value: !GetAtt PCAUI.Outputs.WebUri  
    
  WebAdminUsername:
    Description: PCA admin user
    Value: !Ref AdminUsername

  RolesForKMSKey:
    Description: When using KMS key to encrypt S3 input/output buckets, KMS key must grant access to these roles.
    Value: !Join
      - ', '
      - - !Sub '${PCAUI.Outputs.RolesForKMSKey}'
        - !Sub '${PCAServer.Outputs.RolesForKMSKey}'
        - !If [ShouldLoadSampleFiles, !Sub '${CopySamples.Outputs.RolesForKMSKey}', !Ref AWS::NoValue]

  PcADashboards:
    Description: See PCA Dashboards nested stack outputs for additional information. Refer to blog - http://www.amazon.com/pca-dashboards.
    Value:
      !If
      - ShouldDeployPcaDashboards
      - !Sub "https://${AWS::Region}.console.aws.amazon.com/cloudformation/home?region=${AWS::Region}#/stacks/outputs?stackId=${PcaDashboards}"
      - "PCA Dashboards not enabled - stack param 'EnablePcaDashboards'"

  FetchTranscriptArn:
    Description: Lambda function arn that will generate a string of the entire transcript for custom Lambda functions to use.
    Value: !GetAtt PCAServer.Outputs.FetchTranscriptArn