1

Apologies for posting a basic question and not a detailed programming problem! Alas, IBM send people here for BlueMix support.

We're evaluating different AI Bots, and with Watson what we want to do, I think, is use Alchemy to analyze our web site, and have a chat bot that can answer random questions using general knowledge as well as what Alchemy has learnt from our site.

But, I can't find an example of how to hook up Alchemy to a chat bot. Could any of you point me in the right direction? I'll try to come back with more difficult questions another day!

Richard
  • 6,812
  • 5
  • 45
  • 60
Colin Holgate
  • 131
  • 3
  • IBM sends people to 3 different locations for Bluemix support - Stack Overflow for programming questions, https://developer.ibm.com/answers/ for offering questions and getting started, or you can open a support ticket at https://support.ng.bluemix.net/technicalsupport/. I've retagged your question so that the IBM Watson AlchemyAPI team sees it. – ralphearle Jun 02 '16 at 14:24
  • Thank you, I'm sure that will help! – Colin Holgate Jun 02 '16 at 14:55

1 Answers1

0

I think, is use Alchemy to analyze our web site, and have a chat bot that can answer random questions using general knowledge as well as what Alchemy has learnt from our site.

There is two ways to do this.

  1. You can create a controller that sits in front of Alchemy API + Dialog. The user talks to the controller and it sends the information to Dialog. Dialog can then request a lookup to the controller. This option is only useful if you don't expect Dialog to be maintained at a later date (or you are using earlier versions of WEA).

  2. The better option is to use the FUNCTION call within Dialog. This will allow you to talk to a third party system and get information back to work with.

Once you have your data returned, you can use your tags or keywords within the returned data to activate a particular process flow using SEARCH.

One thing to be aware of is that depending on the answer you need to determine how to present it.

If your corpus is stored as conversational, then you can use the content as-is. If it is stored from documentation, then you should have Dialog talk as if it is reviewing the content and coming back with an answer. The latter should be visible in a way that distinguishes it as separate from the conversation.

Simon O'Doherty
  • 9,259
  • 3
  • 26
  • 54