Bots

• Label: here you can type a brief description

• Choose an OpenAI bot: select the created bot from the list (mandatory field)

• Text: you want to send (e.g. the variable {GOOGLE_ASR_TRANSCRIPT} or {OPENAI_WHISPER_TRANSCRIPT})

• Sound to play while waiting (available from version 3.40.0): a playback sound, previously uploaded in Tools/Sound section, executed for the customer while waiting for a response from OpenAI, such as, “We are analyzing your request, we will get back to you shortly” , thus improving the user experience and avoiding audio gaps.

• In AWS Polly block set the Access Key ID and Secret Access Key. Then define the welcome message and the voiceover

• Then you configure the OpenAI Whisper ASR block

• On OpenAI ChatGPT block retrieve your OpenAI Bot configured in Tools section and in text section set the Variable {OPENAI_WHISPER_TRANSCRIPT}

• in GoToif block, set the condition '{OPENAI_CHATGPT_EXIT}' == 'true'. So the system can understand if the conversation with the bot has to continue (false condition) or it it has to end (true condition)

• If the condition is true, the call pass to the queue

• If the condition is false in TTS ASW Polly block set the variable {OPENAI_CHATGPT_RESULT} to get the text response from OpenAI.
  The text result is saved in database in square_messages table

• Label: here you can type a brief description

• Project ID: Cloud Platform project ID

• Client Email: email address associated to Service Account Key

• Private Key: private key associated to Service Account Key

• Language: the language you want use for the bot

• Text: the text you want to send

Exit Arrows

This box provides just one arrow out to the next step

• Call comes in

• A playback starts e.g. with the welcome message "Welcome, how can I help you?"

• The customer says his sentence for example:

  • "I would like to know the clinic's opening hours", or

  • "I would like to speak with an operator" or

  • "I would like to know the date of my reservation that I cannot remember"

• AWS ASR turns the voice into text and sends it to DialogflowV2 which understands customer's intent

• the call passes to switch option

  • if the request is for clinic hours, a playback will say them

  • if the request is to speak to an operator, a playback will say "please hold, we are transferring your call" and the interaction will pass to a queue

  • if the request is for a reservation time, a playback will say "Please hold for a moment, I search for the required information" and the info goes to the Database, which retrieves the data and the AWS Polly will say "the date of your reservation is Saturday, March 9 at 11 a.m."

• finally there is the Hangup of the interaction

• Label: here you can type a brief description

• Access Key ID and Secret Access Key: AWS security credentials
  (see http://docs.aws.amazon.com/sdk-for-java/v1/developer-guide/credentials.html )

• Region: AWS available regional endpoint (explore the official Amazon Lex documentation to discover supported regions → Supported AWS Lex Regions)

• Bot name: the bot name. Required: Yes

• Text: the text you want to send. Required: Yes

The Amazon Lex block saves the results in the following variables:

• AWS_LEX_INTENTNAME: The current user intent that Amazon Lex is aware of. (Read more)

• AWS_LEX_MESSAGE: The message to convey to the user. 

• AWS_LEX_MESSAGEFORMAT: The format of the response message. (Read more)

• AWS_LEX_DIALOGSTATE: Identifies the current state of the user interaction. (Read more)

• AWS_LEX_SLOTTOELICIT: If the AWS_LEX_DIALOGSTATE value is ElicitSlot, returns the name of the slot for which Amazon Lex is eliciting a value.

• AWS_LEX_SLOT_*: The intent slots that Amazon Lex detected from the user input in the conversation. (ex. AWS_LEX_SLOT_PICKUPCITY)

• Label: here you can type a brief description

• Choose a DeepSeek bot: select the created bot from the list (mandatory field)

• Text: you want to send (e.g. the variable {GOOGLE_ASR_TRANSCRIPT} or {OPENAI_WHISPER_TRANSCRIPT})

• Sound to play while waiting: a playback sound, previously uploaded in Tools/Sound section, executed for the customer while waiting for a response from DeepSeek, such as, “We are analyzing your request, we will get back to you shortly” , thus improving the user experience and avoiding audio gaps.