Table of Contents

1. Challenge

   Enable APIs

   1. Enable DialogFlow API.
   2. Enable Cloud Functions API.
   3. Enable Cloud Build API.
2. Challenge

   Retrieve Working Files

   1. Activate Cloud Shell.
   2. Retrieve the working files:

   git clone https://github.com/linuxacademy/content-google-cloud-certified-professional-machine-learning-engineer
   

   4. Change to the establish-dialogflow-webhook directory.
   5. Download the exported Dialogflow agent:

   cloudshell download exported_agent_acg-apparel.blob
   

3. Challenge

   Import the Dialogflow Agent

   1. Go to the Dialogflow CX console at https://dialogflow.cloud.google.com/cx/projects.
   2. Select the project starting with establishing….
   3. Create Agent with the following parameters:

   • Name: ACG Apparel
   • Region: us-east1

   4. Restore the previously downloaded agent.
4. Challenge

   Create the Cloud Function

   1. Navigate to Cloud Functions.
   2. Apply the following parameters:

   • Function name: hoodie-dialogflow-webhook
   • Region: us-east1
   • Trigger type: HTTP
   • URL: Copy and save the value. (You will need this URL when configuring the webhook.)
   • Authentication: Require authentication
   • Require HTTPS
   • In the Runtime, build, connections and security settings section, go under RUNTIME and set the Maximum number of instances to 1.
   • Select Go 1.16 for the Runtime.

   3. Copy the contents of the function.go file and paste to the function.go field.
   4. Name the entry point HandleWebhookRequest.
   5. Deploy.

   Note: This process can take up to two minutes to complete.

5. Challenge

   Insert the Webhook

   1. Switch to the Dialogflow CX Console.
   2. Create the webhook with the following details:

   • Display name: hoodie-agent-webhook
   • Webhook URL: Paste the previously copied webhook URL
   • All other fields use default values

   3. Apply the webhook.
   4. Delete the existing text response under the Agent says heading. When you hover the text, the delete button appears.
   5. Enable webhook.
   6. Use the hoodie-agent-webhook.
   7. Set up the parameter.
   8. Add the following text response in the Agent Says field, You can cancel your order within $session.params.cancel-period business days. Thanks for your order. Have a great day!.
6. Challenge

   Test the Webhook

   1. Test agent by using the following responses:

   Hello
   I would like to buy a hoodie
   Green please
   Large I think