****0 6 free internet marketing ebooks, click here for download Introduction In this article, we’ll learn how to use Dialogflow to turn a FAQ document into a conversational experience.
What you learn
- What is Knowledge Connector
- How to set up Dialogflow Knowledge Connector
- How to test agent
Others readers like : Forestry management through IT
- Basic concepts and constructions of Dialogflow. Watch the Deconstructing chatbot series for introductory tutorial videos from Dialogflow that cover the basic conversation design.
- You could watch the video before you start for a visual learning experience.
Top 4 Bot Tutorials 1. How we wrote a Wirecutter-like bot with Reply.ai in just a few hours
2. How to Make a Facebook Messenger Bot with Ruby on Rails
3. DialogFlow (formerly API.AI): Let’s create a Movie ChatBot in minutes
4. Chatbot Conference in San Francisco
What is Knowledge Connector? NOTE: Knowledge Connector is a beta function, so the function and functionality can change.
Knowledge Connector complements the defined intentions by parsing documents such as frequently asked questions or articles to find questions and answers.
Questions are added when training phrases and answers are added as answers. To configure them, define one or more knowledge bases, these are collections of documents. At the time of this article, CSV and HTML files are supported for recording.
It is common for an agent that uses knowledge connectors to use defined intentions as well. Knowledge connectors offer less response precision and control than the intentions. When you use both intentions and knowledge connectors, you need to define your intentions to handle complex user requests that require special processing and precision, and let knowledge connectors process simple requests with answers that automatically get out of your documents. made. When you identify content in FAQs that you want to expand, you can transform the questions into defined intentions, giving you full control.
Steps to Setup Knowledge Connector Use an existing DialogFlow agent or create a new one. If you don’t know how to create an agent, see the third episode of the Deconstructing Chatbot series where we’re building an appointment schedule. You can also refer to this article.
Because this is a beta function, we begin by going to the gear icon and enabling the beta option.
Now we’re ready to make our knowledge connector. Select the Knowledge Beta in the left pane and click “Create Knowledge Base”
Name it and save it.
We need a knowledge document that we can use to automatically generate the FAQ chatbot. These calculator FAQs can be used as an example. You can use your own sample document here use.
Now go back to the DialoglFlow agent and create the first knowledge connector.
Create a New Knowledge Document
- Name it, I called it “Compute Engine FAQ”
- Select a knowledge type — it’s FAQ
- Select MIME type — in this case it’s an HTML file.
- And we add a URL to the document. I use this https://cloud.google.com/compute/docs/faq
- After you fill in, click Create.
And with that, the Knowledge connector has created the FAQ chatbot, click on the Compute Engine FAQ.
We see that the questions are neatly processed in requests and answers.
Click Add Comment to enable automatic replies and beat Questions from document dissected in Questions and Answers .
Turn on the chatbot before testing. Select the check box next to the name of the FAQs and click Enable.
Test your Chatbot! Now we’re ready to test! In the simulator on your right, ask your DialogFlow agent with “what’s the price for a calculator” and you will see a response from the bot. Try more examples, such as “How to Get Support”. You’ll notice that even if you don’t type the exact same question from the FAQ, it will still be assigned to the right intent. That’s the beauty of knowledge connector.
Congratulations! You created a FAQ chatbot based on an HTML or CSV file in less than 2 minutes. Try this great beta feature and create some chatbots to answer those FAQ questions automatically!! Don’t forget to share the experience here in comments.
- Check out the DialogFlow website for documentation, APIs, and more here.
- Follow the deconstructing Chatbots video series and subscribe to the YouTube cloud channel of the cloud platform
- Try Dialogflow, it’s free to build a bot! View.