I wish to make a chatbot using the two services listed in the title. Watson assistant is used to make the dialog for the chatbot while watson discovery allows for finding information in a large variety of documents such as .html, .pdf files. I want to make a chatbot that uses these two services.
The way the chatbot would work is that when a user says something into the chatbot, it will go through watson discovery and run that query which will then return results back to the user.
I currently know how to use Watson Discovery and Watson Assistant but I am unaware how to link them together. I know its possible because I have seen demos on this but the ones who have made those demos give a lack in instructions to produce the chatbot.
You could link Watson Discovery from within a dialog action of Watson Assistant. I have done that and described that method in the "5 minute barebone news chatbot". That blog post links to the full source code on GitHub.
Basically, within a dialog node I defined a client action. That action performs the call to Watson Discovery and returns the found items to the dialog node. There, it is presented as part of the chatbot response. In a similar way, you could pack that action as Cloud Function and execute it as server action.
"actions": [
{
"type": "client",
"name": "henriktest",
"parameters": {
"topic": "<? $topic ?>",
"input": "<? input ?>"
},
"result_variable": "myNews"
}
]
You might want to look at the new "Search Skill" feature in Watson Assistant. Though it is still in Beta phase, it provides a seamless integration between Assistant and Discovery out of the box.
https://cloud.ibm.com/docs/services/assistant?topic=assistant-skill-search-add
It is available to Plus or Premium plan users only.
Alternatively you can check this code out.
https://github.com/watson-developer-cloud/assistant-with-discovery
Related
I have configured an Assistant with some dialog skills. The utterances are passed through Node.JS backend of my application. As a requirement for the project is to use Discovery but in term of a search skill.
My question is: When the request is proceed to a search skill from Watson, the way of returning the result from Discovery is the same like from a dialog skill e.g. Discovery -> Watson Assistant -> Node.JS backend?
(We didn't configure the billing plan yet, that's why I'm asking this basic question.)
When you use Watson Discovery as part of a Watson Assistant search skill, access to Discovery is through Assistant. In terms of the underlying programming, take a look at the Watson Assistant API overview in the docs and at the actual V2 API for Watson Assistant. The search integration is configured is in Watson Assistant and determines how the results are displayed to the user as chatbot answer.
So, from the user view, everything is done through Watson Assistant.
I'm creating a bot using IBM Watson Assistant. I am trying to use a webhook, but don't know the format of the POST request JSON/HTML which is sent to the webhook.
My case study is a shop where user can pre-order. I want to send the order details to my back-end server and give the user a reference number for the pre-order. I found nothing in the documentation about what POST request format is sent from IBM Watson Assistant and in what format response should be returned.
I know IBM Watson Assistant does not require a particular response format. It allows the developer to manipulate the response as the developer wants.
IBM Watson Assistant has a documented API. There are the recommended V2 Assistant API which can be used to create session and then send messages. The older V1 Assistant API has more functions and is deeper into the system. Both APIs can be used to write chatbots.
If you mean a Webhook as the Watson Assistant feature to reach out from a dialog node to an external service, the process is the following:
in the global configuration, you define the URL and the header
for a dialog node, you enable webhooks, then define the key / value pairs that are sent as payload. They can differ by dialog node.
Typically, the expected result is JSON data because it is the easiest to process.
This IBM Cloud Solution tutorial on building a Slack bot with Watson Assistant uses webhooks to call out to a Db2 database. The code is available in a GitHub repo.
We have integrated IBM Watson Assistant skill/workspace with a Facebook page using the Watson features. We did this using an integrated approach from Virtual Assistants tab.
We are able to get the response in Facebook Messenger from Watson skill/workspace FAQS. Now we want to add a few more questions to skill/workspace and get the response from a database.
We know that we can use IBM Cloud Functions to get DB data and respond back with the data, but Cloud Functions action types (web_action and cloud_function or server) incur a cost, hence we are looking for another approach.
We have our own APIs developed for the DB and want use those in Watson Assistant dialogue node actions. Please let us know how we can add it in actions and get a response from the API without using client application/cloud functions.
Note: we haven't developed any application for this chatbot, we directly integrated Watson skill/workspace with the Facebook page and trying to call API calls wherever we require them from the dialogue nodes.
As you can see, IBM Watson Assistant allows to invoke three different types of actions from a dialog node.
client,
server (cloud_function),
web_action.
Because for cloud_function and web_action the action is hosted as Cloud Function on IBM Cloud, the computing resources are charged. For type client, your app would handle the API call and the charges depend on where your app is hosted. Thus, there are always costs.
What you could do is to write a wrapper function that is deployed as web_action or cloud_function. Thus, there isn't much of computing resource needed and the charges would be minimal. But again, independent of the action type, there are always costs (maybe not charges) - one way or another...
I am using IBM Watson Assisstant to create a chatbot, and created a Watson Discovery collection too in the project.
I need help in that how the dialogs works to take a response from the Discovery collection when an intent along with the entities are detected in the try section.
in the response section we have to define something or there is something else similar like text response
is the discovery response is only available in the app on which we work
There are a couple of options to link up a IBM Watson Assistant chatbot to IBM Watson Discovery.
The first and oldest is to have the application interact with Watson Assistant and, depending on the flow, context and response send a request to Watson Discovery. Basically, the integration is done in the application layer.
The second option is to use server or client dialog actions in Assistant to directly call into Discovery. See my blog on a barebone news chatbot and the related code on GitHub on how to implement such an action. My example uses client actions (basically let the app handle it again), but server actions are similar. This IBM Cloud solution tutorial covers server actions for a database-driven bot.
The newest option and currently in beta is to use the direct integration of Assistant and Discovery. See "Building a search skill" for an introduction into this direct linkage between IBM Watson Assistant and IBM Watson Discovery.
The option 2 (server action) and 3 should work from the "Try it" in the tooling, the others not because of the app-based coordination.
As usual in IT, there are different way to achieve the goal, the choice is yours... ;-)
I have created a chatbot with IBM Watson Assistant. But currently I have hardcoded all values in the dialog
e.g : When some user will ask "Who created Computer ?" then in the dialog flow I have written "XYZ created computer".
But suppose the user will ask about some other person and that value is not hardcoded in the dialogs on IBM Watson Assistant then is there any way by which I can provide Google search results?
You can make programmatic calls from within IBM Watson Assistant dialog nodes. Both server-side actions (IBM Cloud Functions) or client side calls (within the app) are supported. That way you can react to such queries as described and could call a search engine, database or somethin else.
This IBM Cloud solution tutorial on how to build a database-driven Slackbot uses server side actions to interact with a Db2 database. Instead of calling out to a database to fetch data, in your example, you would open a request to Google search.
I saw that you tagged it "facebook-apps". If you use Botkit middleware to build an integration with Facebook Messenger, then check out this blog on how to enable actions in the Botkit Middleware for Watson Assistant.