I have made a bot with API.AI and I am using it with Slack. I'm trying to integrate a multi-language agent to it, however I don't know how to set the lang tag of the messages coming from Slack.
My bot supports English and French and even if the user have Slack set in french, the lang tag remains "EN" (English).
Thank you in advance
Related
I already finish the chatbot, but I have no idea of how to upload it to my website, please, help :)
I tried to look for some code to send to the IT developers, but cannot find it :( And the IT guys are too busy, so I'ld like to get the answer by myself so I can send it to them if I'm not able to apply it. Thank you. (Btw: I'm not an IT person... :( )
Where to start?
The dialog / conversation part of your Watson Assistant part chatbot is available as a REST API.
There are several deployment options available. For the more popular choices the Assistant tooling provides integrations. So if you want to access your chatbot through slack, or facebook messenger or on a word press site then look at the documentation as to how - https://cloud.ibm.com/docs/services/assistant?topic=assistant-deploy-integration-add
If you are developing your own application or web-page, then your developers will need to design the User Interface and handle the quirks of your dialog. eg. Decide how to display images, options etc., all from the API, which is essentially only message in, response out - https://cloud.ibm.com/apidocs/assistant-v2#send-user-input-to-assistant. There are samples available for them to base from - eg. https://github.com/watson-developer-cloud/assistant-intermediate
If your website is using Wordpress, there is a very easy way to deploy the chatbot to it using a wordpress plug in - https://wordpress.org/plugins/conversation-watson/
I am working on an e-commerce website and would like to integrate with Google Voice assistant or Amazon alexa. I have gone through the dialogflow on how to build a voice assistant. But how It'll be available in amazon alexa or google home that shipped to every household ?
Both Alexa and Google Assistant let you develop things that work very much like websites - Alexa calls them Skills, Google calls them Actions. These are programs that run on your (or a) web server, get HTTPS calls from Amazon or Google with JSON information about what the user has said, and are expected to return JSON information that replies to what has been said.
Amazon requires you to use the Alexa Skills Kit to do the development of these sites, but Dialogflow can export its model to Alexa. Google is a little more open, but since they own Dialogflow, integrating a Dialogflow agent with Actions on Google is very straightforward.
You will need to register your Skill/Action with the appropriate company, but once you have done so, it is available to the users. Alexa users need to "install" the Skill from the Skills directory, although that really just means that they can activate it. The Assistant doesn't require users to activate it this way, but it will be listed in the directory. In both cases, users can then trigger it by saying something like "open Skill Name" or "talk to Action Name".
When the skill is under development, I can invoke it in the development console. In the Echo or the Amazon Alexa app the skill is not invoking.
The skill is showing under the skills & games tab in the app and it is enabled.
Anybody knows how to solve this issue?
This could be because of the language you have selected in the Alexa app or Echo device. If you have developed the skill in English (India) and if you app/Echo device is configured with English (US). The skill won't work, just like what you are experiencing.
Make sure that the Alexa app, your Echo device and the skill you developed are all in same language.
I was also facing the same problem when I was trying to get it done using alexa app on mobile. To solve this problem change your device language(mobile phone language from settings) to the language of the skill which you have developed(in my case it was English(UK)) and then restart the alexa app.
I had the same issue as well, changing the device/mobile application language to the language in the development console (English (GB)) solved the issue
#johndoe answer did work for me.
Let me give the step by steps as on this date.
go to alexa developer console -> skills tab
https://developer.amazon.com/alexa/console/ask
see what is the language of your skill.
mine is english / United States
Now go to alexa app on your phone
click on more in the bottom bar of the app.
click on settings -> alexa app settings -> change language to the one in your developer console.
now again click on more in bottom bar settings -> device settings -> select device -> click on gear icon in top right side -> change language to the one in your developer console.
now it should work.
if it doesnt work -change language in your phone settings , restart alexa app , restart alexa device.
now it should most likely work.
Feel free to HMU.
cheers.
Is there any API or way to integrate the utterance generator to alexa skill developer console.
Means I want the generated utterances by generator tool to be autofilled in the alexa skills intents in develope console.
Does developer console provide any means of calling the utterance generator API and to get it included into respective intents in alexa developer console.
The developer console right now does not support any means of calling external API to autofill utterances.
However, One solution would be to write a simple program in one of your preferred languages to create a JSON file according to this format.
You can generate all the utterances into this file and copy and paste the file in the interaction model JSON editior in amazon skill developer console and it would automatically create intents and utterances according to the Interaction model Json you pasted.
A solution very useful, with nested parentheses and JSON format you'll find in this site.
This tool will help you enumerate the sample utterances that your Amazon Echo app will recognize for your intents
I have created a simple flash briefing skill that reads from a rss feed. However it is pronouncing the name of the company wrong. I have reviewed the SSML page on the amazon developer site, but i do not see a way to get to the js that runs the skill. Is there any way to edit the js behind the skill if I am using the default API? Is there another solution short of writing a standalone skill?
It's not possible to do that yet. SSML is allowed in the Feed content only.
However you can up-vote the idea, you are not the first one who faces this issue.