Problem Statement Nowadays, it’s quite common to add a “virtual assistant” (a.k.a chatbot) to your public facing website. Almost every organization, especially the ones dealing with endusers (B2C market-oriented organizations) try to add value to their websites in form of a bot. And Microsoft has done a pretty good job, making it easy to build a bot, with little effort and almost no coding. But unfortunately, there is not a complete guide provided, on how to create the bot from the very first click until it can be deployed on to a public website.
Each year Microsoft is inviting intersted people from all over the globe to a big show, called Microsoft Ignite, where nearly 30.000 (you read correctly THIRTY THOUSAND) people gather together to see what’s new for the various products and services Microsoft is offering. Me as a Conversational AI guy, I’m quite excited on the news and announcements they’ll share at the event, but du to the fact, there the amount of news is that big, one has a hard time following all the necessary news and announcements at a glance.
General Limits So as I work a lot with one of the most common used Cognitive Services when developing a bot, the QnA Maker, I wanted to share some insights in terms of limits of the QnA Maker as I detected some things by now. So if you have never seen it before, this docs article outlines the various limits you need to have in mind when working with the QnA Maker.
The Background So I had this idea already a couple of months to release or better open-source a SharePoint Framework WebPart which is capable of bringing your Bot Framework conversations (= your bot) to SharePoint (Online). Now I finally had the chance of publishing my webpart to the official SPFx samples GitHub repo to make it available for everyone. So if you want to try it out and integrate it into your SharePoint tenant, just clone the repo, and follow the instructions mentioned here and you should be able to get it up and running in a couple of minutes.
The Starting Position Nowadays, styling is a hot topic. If it looks good - I’ll use it is often the mindset of users. So it’s very important to offer something very good-looking to be successful with what you do. And so it is with bots. The Microsoft Bot Framework team did a pretty good job in styling the webchat component which is looking pretty good out of the box: But companies often have the need to apply their CI/CD guidelines on whatever they use.
Problem statement Imagine this: You are working on a Bot Framework bot and want to implement human handoff to give users the option to have a conversation with another human being if the bot is not able to answer the user’s questions. Now there are many good samples out there for channels like Microsoft Teams for example which demonstrate how to bring in a human into the loop. But I was trying to find a way to tell the webchat control (via DirectLine) that a given point in the conversation it should do something (escalate to an agent).
As I teamed up with Albert-Jan Schot, Rick Van Rousselt & Thomas Gölles to create a project called SelectedTech, where we discuss and share our knowledge on Office 365/Teams/SharePoint & Bots and record that as webinars, we had the idea of doing something which would be a cool way of helping others with one of the Cognitive Service APIs - QnA Maker. The idea was to create a Postman collection which we’ll share later on, to bundle all API endpoints for the QnA Maker to easily test and debug the API.
- NEWER POSTS
- page 1 of 8