- Course Overview 4:07
- What is Watson Used For? 3:13
- Trying it Out 5:10
- IBM Cloud and a Sample Chatbot 5:00
- How Conversation and Discovery Services Work Together 4:19
- How Conversation and Tone Analyzer Services Work Together 3:33
- Starting Our Project on IBM Cloud 7:12
- Starting Our Local Client 6:28
- Review: What is Watson? 6 questions
Preview
Video Player
00:00
00:00
Course Overview
4:07Treehouse has partnered with IBM to teach you how to build apps using services available from the IBM Watson APIs. In this course, we'll teach you how to build a chatbot for a car powered by Watson APIs. This video shows you what we'll build and what you need to know.
[MUSIC]
0:00
Hello, my name is Ben, and I'm teacher and
manager here at Treehouse.
0:04
I'm pleased to introduce
Armen Pischdotchain,
0:07
who's joining us from IBM to show you
the best inside advice on how to build
0:10
all sorts of cool stuff using services
available from the Watson APIs.
0:14
In this course, we'll teach you how to
build a chatbot with Watson APIs from IBM.
0:18
>> Hi,
I work at IBM as an academic tech mentor.
0:23
And I'm excited to be here
to show you specifically
0:27
how to build a chatbot that uses some
natural language processing services
0:31
available from our
IBM Watson data platform.
0:35
Imagine you have a car
with a voice assistant.
0:39
[SOUND] We are going
to build a chatbot for
0:41
the car that you can talk
to with voice commands.
0:44
For example, you can say something
like turn on the wipers [SOUND].
0:47
Or ask questions like,
how is the weather today?
0:51
Or can you find me a nice apartment in
Manhattan overlooking the Hudson River?
0:55
Our user interface will
be a simple webpage.
1:01
We will use the APIs that sends this text
to multiple services for processing.
1:04
The Watson Services will analyze the text
and then return appropriate responses.
1:11
Which we would use to craft the final
chat response that we display
1:17
back on the webpage, as if the car were
responding to questions and commands.
1:22
>> What's really cool about this
project is that you'll be able to adapt
1:28
this chatbot for other uses.
1:30
Maybe you have a site where you could use
a chatbot as a basic level of support for
1:32
your customers.
1:36
As we go along,
1:37
we'll talk about where you could change
the bot we build to do other things.
1:38
Now let's talk about what you
should know to take this course.
1:42
The Watson Services are available as
APIs that you can call from Bluemix,
1:45
IBM's premier platform as a service.
1:48
So you could build a bot like this
in JavaScript, C#, Python, or
1:51
pretty much whatever language or
framework you want.
1:55
IBM has provided a bunch of SDKs
to simplify development, and
1:58
there are even some that
the community has made available.
2:02
Armen and I are going to use JavaScript,
or specifically, Node.js.
2:06
Now it's a good idea to take the Node
courses that we link to in the teacher's
2:09
notes for this video.
2:12
You don't need to be an expert
in Node to follow along, but
2:14
that base knowledge will definitely help.
2:16
Even though we're going
to be working in Node,
2:19
the way in which we do it will transfer
pretty easily to other languages.
2:21
So even if you're not a Node developer,
you can still follow along and
2:25
use docs and samples in your own language
to work through any differences.
2:28
I personally don't know Node very well,
but
2:32
this all makes sense because of
my skills in other languages.
2:34
>> The Watson services
are available as REST APIs.
2:38
We assume you know how to interact
with API methods such as GET, PUT,
2:43
POST and so forth.
2:47
But even if you're not sure,
you can still follow along.
2:50
If you want a brief overview
of how RESTful services work,
2:53
check the teacher's note for
a link to a short course.
2:58
>> Right, you should know how to
construct a call to an API, and
3:01
how to parse its response.
3:05
We're gonna provide you with that code and
3:06
just walk through it, because the focus
of this course is how to use these APIs,
3:08
not necessarily how to make
an asynchronous API call.
3:12
We do cover that in other courses at
Treehouse for a bunch of languages, so
3:16
just let us know if you need help
finding that supporting material.
3:19
We'll put some additional
links in our notes.
3:22
All that said, we aren't going to
write very much code in this course.
3:24
Our focus is on the services, and
3:27
we're going to provide you
with a lot of working code.
3:29
So even if you aren't totally comfortable
with how you do these things,
3:31
you can still follow along and learn
a lot about how to use the Watson APIs.
3:34
I'd recommend it, and you can go back for
more training on Node, or
3:39
whatever, after this course.
3:41
>> I've been working with Watson for
3:44
four years, and I'm looking forward
to showing you how to work with it.
3:46
You can build a lot of amazing things,
3:50
with even more exciting
services coming in the future.
3:53
>> Armen, I'm so glad you're here with us.
3:56
Why don't we take a short break, and
3:57
then we can show students some of the ways
that they can experiment with Watson
3:59
right away, in their browser,
without writing any code?
4:02
>> Let's get to it.
4:06