More of a question than a problem but I'm wondering if anyone has attempted or seen the use of a CMS for an Alexa Skill. I'm imagining a simple FAQ based Alexa skill. The JSON for the intent would have to be generated elsewhere or at least supplied elsewhere. The idea is that through the CMS you could supply the intent and also the response. I know this is very lose but I'm kind of feeling out if anyone has done anything with this.
Have you seen this project?
https://www.hackster.io/tom-harrigan280/alexawp-20a282
Github repo is here:
https://github.com/tomharrigan/AlexaWP
I believe it close to what you are looking for. It uses Wordpress as the source of content for responses to Alexa requests.
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 have a alexa skill live on amazon skill store. The interaction model of that skill was developed using the skill builder of alexa development portal and the lambda function was uploaded seperately. The skill is live and has many users.
Recently I felt the need of making some changes to that skill. Since now I am using ask-cli for all my alexa skill development, I decided to use the same for this skill too.
Here are the steps I followed:
cloned the skill from the alexa console using command ask clone and selecting the skill I wanted to make changes in.
made the required changes in the skill. Just changed a response, nothing special.
tried deploying the skill again to alexa console using ask deploy command
But I got the following error:
[Error]: Building skill schema failed
I thought that the changes I made might be the cause of it, so I backtracked the changes and made the code as it was when cloned. Then I tried deployig the code again but the error remained the same.
I went through some answers on amazon portal, the most common cause of the issue for others there was some mistake in URI of skill icon URIs. To be sure, I also removed that line from skill.json and tried deploying it again but nothing changed.
Does anyone has any idea of the cause of the above mentioned issue?
Make sure your lambda function has Alexa Skills Kit as trigger. I solved my problem by adding back the trigger (and entering the skill ID).
This steps might able to fix that problem.
Create a new skill in the developer portal.
Create the Lambda function for that skill then add it as an endpoint.
Download the skill via ask-cli
Copy the code in the existing skill to the new skill.
Re deploy using ask-cli.
It might be due to permission error or the appropriate profile used during deployment is configured incorrectly or missing.
If the cause of the issue is your image urls in Skill.json file try this hacky solution
Goto your Alexa skill development portal and select "distribution"
tab
In that upload both small and large icon. ( Do not press save ) if its a new skill,
right click on the image and select open image in new tab and copy
the image URL. now use this URL in the skill.json
This is what i used in my skill when s3 url are all causing issue.
Is there a way I can use voice recognition to personalize responses in an Alexa Skill? I am creating an Alexa Skill where I want Alexa to generate responses based on the user who utters the command. Currently I'm thinking of simply configuring the app such that it asks the user who they are before responding to their command/question. However, this is a very naive approach, so I was wondering if there is a way Alexa can use voice recognition to figure out who is talking to it. Couldn't find anything useful online, so it would be great if anyone here who has done something similar could share their insights.
Amazon is working on this capability, and is current accepting requests to receive more information as it is released. You can sign up with Amazon to receive information here.
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.
For my project is ideally suited Smart Home Skill from Amazon. Tell me please, can I add additional commands (eg turn left, close door, show last video etc.) or only commands which are presented on this page (link) is available to me?
I have in the lambda function my commands but Alexa only recognizes standard. I have studied the documentation, but I did not find the information about how to Smart Home Skill, can add additional commands. But also I didn't find the information that it cannot be done.
Through the Smart Home Skill, only the designated actions are available.
To create an expanded feature set, create a custom skill. It will require the user to use the skill name (e.g. Alexa, ask my service to turn left) as part of the activation.
Note, depending on your use case, you could do both to cover all needs.
Update triggered from comment:
With this approach, you are building two skills. A Smart Home skill and traditional Alexa Skill. They will each have their own entry points into your code. The Smart Home Skill is usually a subset of features in your Alexa skill.
The Home Skill requires implementation as an AWS Lambda, so it would probably be easier to build the ASK front end for both skills in AWS. My solution started as an ASK skill prior to the availability of the Home Skill so my architecture is different.
For me, I route all Home skill requests through the AWS Lambda (mostly just the sample shell code) and then to my hosted service that performs the actual function and builds the appropriate ASK response. So, the Lambda logic is mostly just a proxy/wrapper for my code hosted elsewhere.
The number of "directives" available through the Smart Home Skill API is regularly increasing. At this time only Amazon can create new directives, but, as noted this list is growing.
Three weeks ago Amazon completely revamped the developer documentation for the Alexa Smart Home Skill API (and added new directives). You can find the updated landing pages with overview info here:
https://developer.amazon.com/alexa/smart-home/build
Updated reference material is here:
https://developer.amazon.com/docs/smarthome/smart-home-skill-api-message-reference.html