I am making a chat bot that requires the use of 3 external APIs to be used as responses. When wanting to call an external API from within Watson Assistant, webhooks would be required to connect to one API either locally or on the cloud (IBM functions). How would I connect more than one API to the assistant if possible ?
Unfortunately no, not at this time. The design was meant to have a middleware app that orchestrated the apis, formats the data, etc just like the video in the docs.
Related
I have been wondering if it is possible to integrate Google Cloud Services such as Cloud Text-to-Speech in Flutter. The lack of documentation makes me wonder if there's some workaround or something because I can't find a way to integrate.
As you can see in the documentation, there are only samples for different languages, no presence for Flutter:
https://cloud.google.com/text-to-speech/docs/samples/tts-synthesize-text
enter image description here
Any suggestions? Will appreciate it.
GCP TtS is available also by REST API calls, as any other GCP service. So you can write Dartcode to perform an HTTP POST request to send text or audio.
BTW you have to consider how to authenticate to TtS, and there are different options, some of them:
your users need to be authenticated in your GCP organization by your mobile app, and they also need to have the permissions to invoke that service. Then your app can invoke TtS using HTTP POST and impersonating the user.
your mobile app authenticate the users without a GCP or Firebase identity. In that case you need a backend layer (might be a REST service or a simple Cloud function) acting as a proxy between your mobile app and TtS. Your app calls your backend, the backend authenticates to TtS using a service account (GPC identity), then the backend invokes TtS and sends back the result to your mobile app.
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 have seen the tutorial for starting the cloud functions and creating a guestbook on IBM Cloud, but when trying to connect an App ID it actually requires an application and not a Cloud Functions API.
So how can I connect them? Is there some tutorial somewhere? What needs to be considered?
depending on what you want to do, take a look in https://console.bluemix.net/docs/services/appid/relatedlinks.html#secure.
Specifically one of
Securing your Cloud Functions API
Securing your serverless Cloud Functions mobile backend with App ID
Tutorial: GitHub traffic analytics with Cloud Functions and Cloud Foundry
Cloud Functions supports OAuth 2.0 user authorization out of the box and you can bound your App ID instance directly to it.
Here's a fairly recent tutorial showing the steps:
https://www.ibm.com/cloud/blog/authenticating-users-with-cloud-functions-api-gateway-and-app-id
If you're looking to automatically initiate a new authentication flow as in redirect to the an identity provider where you're user will sign in, you'll have to either add logic to your application using an OIDC SDK (For instance App ID's: https://github.com/ibm-cloud-security/appid-serversdk-nodejs/) or add it manually handle the flow from a set of actions.
If you go the action approach, you'll have to keep in mind that they are ephemeral and can't keep session state, so you'll have to keep secure cookies in the user's browser.
The documented API only allows interaction with the Watson Conversation service once it is configured. Is there any API which will allow the configuration. For example create intents, entities etc...
Good questions and we agree. We have plans shortly to expose a lower level set of APIs that will address your concerns. Brian
At this point in time the APIs for what you want to do are not publicly exposed.
Just to close out this question. The API for Watson Assistant (formerly Watson Conversation) can be seen here. The Watson Developer SDKs support that API.
To see the API in action there are several examples. I wrote a tool demonstrating some of the API calls and a so-called EgoBot that mutates during the dialog, i.e., adds objects by using that API.