Building Chatbots with Google Dialogflow
This course is the second part of our series on building chatbots using Google Dialogflow. In this course, we'll be taking a hands-on approach to implementing a Dialogflow chatbot, specifically focusing on the graphical user interface. You'll follow along as we cover the example of building an online banking customer service chatbot using Dialogflow.
We'll also discuss the use of databases and other knowledge sources in order to provide meaningful responses that give you the option to serve real-world information to your user.
- Learn what intents are and how to train your chatbot to look for them
- Set up entities in Dialogflow
- Understand how chatbots interact with users and how to test your chatbot
- Learn how to connect your chatbot to a data source
- Understand the user interfaces available with Dialogflow
- Learn how to use the Knowledge service to build chatbots quickly and with less configuration
- Anyone looking to build chatbots using Google Dialogflow
Before taking this course, make sure you've done Part One first. To get the most out of this course, you should also have a basic understanding of:
- Computer science techniques
- REST APIs and SQL
- Google Cloud Platform
So with fulfillment handled, really the last remaining component is handling new interfaces. This is how does a person actually communicate with the agent? In every example we've tried so far, we've actually only just used the testing widget. Now this is a fantastic way to get started but unless every single user of yours is going to log on to Dialogflow and use it just for that, you need to actually get out in front of people with a method they can use.
So there's a lot of different options to start with. The Dialogflow Messenger is in beta and it's a fantastic option for embedding or Dialogflow within websites. This is by far one of the most common ways to use a chat bot. So this widget when enabled will enable you to use a code snippet they provide and put it into a website to start interacting with it right away.
If you're looking for a more commercial option, options like Twilio exist. These commercial options all require external connectivity to services which also require you to sign up and establish an account with separately. In the case of Twilio though, this enables some fantastic options around telephony, voice chat and text messages over SMS but as I noted, you have to purchase things from Twilio separately to set up this integration.
Now in the case of Twilio and a few of the other external connections, they used to have a first party integration. And this is where Google would have a toggle just to turn them on or off. But for many of these integrations now, Google supplies a get hub with some basic instructions on how to set things up, such as leveraging Google Cloud Run. And of course, there's a few other options in addition to Twilio, such as Slack and Google Assistant. But the key takeaway here is that these integration options is that you're able to use them in some combination to serve your agent over voice, text, SMS, and native web messaging.
So to actually try one of these out, Google makes it amazingly easy for many of the first party integrations. You're actually able to just flip a simple toggle on the integrations menu, which you could find on the left you'll see it right below fulfillments and when you turn it on, you can actually start playing with it immediately.
So now using this app, you can have your own pop-up in the bottom right so that you could test this layer of integration right in your web browser. And this is different than the simulator we've previously been using because this is actually using that integration as shown in the snippet to test how it would work in your website. This is really cool because this is actually very similar to a production application of the embedding and you're able to use it without having to actually launch your website.
Calculated Systems was founded by experts in Hadoop, Google Cloud and AWS. Calculated Systems enables code-free capture, mapping and transformation of data in the cloud based on Apache NiFi, an open source project originally developed within the NSA. Calculated Systems accelerates time to market for new innovations while maintaining data integrity. With cloud automation tools, deep industry expertise, and experience productionalizing workloads development cycles are cut down to a fraction of their normal time. The ability to quickly develop large scale data ingestion and processing decreases the risk companies face in long development cycles. Calculated Systems is one of the industry leaders in Big Data transformation and education of these complex technologies.