Is there anyway to convert or import AIML files to Dialogflow or Lex for creating a chatbot? I am hoping for a way to incorporate open source AIML files into an NLP chatbot framework like Dialogflow or Lex, and so far my googling has produced no avail.
I found a way to create a Dialogflow bot using CSV, and I wonder if this is a case of converting AIML into CSV? Is it feasible or a fool's errand?
Much appreciation for your advice, guidance, and brainstorming!
Keith Sterling has a way listed on his github page using python 3. It also has a full step-by-step implementation with screenshots and was just updated a few days ago. It’s AIML 2.1 compliant as well.
Also, it is completely free. DialogFlow itself has both free and paid tiers (as you may know) but his program is open source.
Here’s the link:Program-Y github Repo
By way of background, this is an AIML Interpreter (which is to say it is a way for you to deploy your AIML files under various circumstances). So while the link in the OP is more direct, this gives you more options.
For example this allows you to use your same files in:
Google Assistant
A Web Client
Messenger
Telegram
Alexa
Cortana
DialogFlow
etc
And because this is REST you only interact with your main implementation and this in-turn updates all client bots.
This helps you keep an updated central set of AIML files and is also lower on overhead.
Set-up:
First sign in and then click Create Agent.
Give you bot a name, and ensure the language and timezone is what you need them to be, and then click:
Create Intents
First, delete the 2 existing intents:
Default Fallback
Default Welcome
Next, create the intents for integration with Program-y (the name of the Repo).
There are 4:
Launch
Quit
Help
Query
Launch Intent
Click Create Intent
Enter your training phrases
select event, and then,
under fulfillment, choose web-hook
Quit Intent
Carry out the same steps as above, this time naming it Quit, but this time do not select an Event and use the following phrases:
stop
exit
leave
quit
Help Intent
Again carry out the same steps as above, this time naming it Help. Again do not select an Event and use the following phrases:
help
what can I ask you
help me
what can you do
Query Intent
Finally carry out the same processes, but this time name it Query. Again do not select an Event, but this time we have one training phrase
query
This time, however, add a parameter as follows:
Connect Endpoint
Finally we need to set the endpoint that DialogFlow will call each time it identifies an intent.
On the left hand side menu bar, click Fulfillment link. Click Enabled and then enter the URL that should be called which Program-Y is running on as a Google client.
The API endpoint is always /api/alexa/v1.0/ask So combine this with the ngrok URL, gives you https://87e27269.ngrok.io/api/alexa/v1.0/ask
To save this click 'Save Endpoints' and you are ready to get your client up and running.
Scroll down to the bottom and click Save.
I know that’s a lot of info and it may look overwhelming however there are screenshots and a walkthrough at the link:
Program-Y github Repo
No, currently there is no way to do this. There is no straightforward way to translate AIML files to Dialogflow or Lex JSON import formats. The basic structure of how the conversation is handled is different. Although you can find the idea of Intent, Entities and Context in AIML (specially v2.0) you would need to do a lot of manual effort to adapt it.
I would recommend extracting the patterns -what the user says- and the templates -what the chatbot responds- from AIML, import it to the framework you want to use and adapt manually the context and entities.
Related
I'm new to iOS development and I'm trying to make an app that tracks my student loans. I would like to have the app simply display a balance found on the loan's website and build on that behavior. I've got my app to open up safari to the website but I'd like more of a web-crawling behavior so it's done in the background. This web-crawler needs to be able to login to the website and then find a field with the loan balance value..
I've looked up several ways on how to do this but I can't get any of them to work with my novice level of experience with swift. If anyone has a recommendation and a direction to go with this, that would be great.
Thanks in advance!
I've written an app to get my uni's schedules, payment records, and grades by bypassing the login and gain access to API used by the website.
The step you could take are probably very similar to mine
Find out how the website authenticate its users (could be by cookie, session id's etc) You need to have some knowledge on web too. You can use the network tab on Chrome/Brave/Safari or any other browser to see what the website is doing when you click on 'login' for example. You could use Charles too, 30 days of trial should be enough.
After authentication succeed, track what API route the website use to get the datas to html. See what information you need to access the API route. Postman would be very handy to see the JSON response by the API.
To parse the response, you can use URLSession or networking library like Alamofire to get the job done.
If you want to see how I did it, here's the GitHub repo.
Is there a way to get an example of implementing the 3 legged authentication process in React without using Redux?
The boiler plate is just way complicated for the majority and I guess is good to have something more simple for "the rest of us".
EDIT
To persist Redux states I can think of two options off the top of my head:
Open a new window session for the authentication and you can close the window and notify the parent window since they'd in the same domain once the callback arrives
Or persist all essential states to localStorage/sessionStorage to load back after direction
Although we don't exactly have a React sample to generate 3 legged tokens but the that very process has no more to do with your backend - you'd not want to generate a 3 legged token in your front end for security reasons.
So far as React or any front end framework is concerned it's a matter of redirecting the user to sign in to their Autodesk account and set up the callback handler in your backend properly to receive the access code - see our official tutorial for details and there's sample code for both front (albeit in vanialla JS) and back ends
Feel free to comment if you have any specific question re this process.
I am a naive user.
There is this website which is a really important source of information for my business.
To monitor the websites, I convert them to RSS feeds using page2rss service and then monitor feeds in IFTTT.
However, this particular site does not use static web pages and generates data response to API Calls:
Here is a sample API Call:
https://www.mpeproc.gov.in/ROOTAPP/GetTenderFreeView.jsp?Department=Urban%20Administration%20and%20Development%20Department&company=MPSEDC
Is there a way by which I could record the response from this call to an html page on my server? or is there any other way to monitor such dynamic pages.
There are solutions but not simple ones. The first page uses JavaScript to create a FORM which it then submits. You can simulate this with the command line tool curl; see https://superuser.com/questions/149329/what-is-the-curl-command-line-syntax-to-do-a-post-request
But take note that many sites don't like scraping; if they notice what you're doing, you may end up on a blacklist. So it's better to ask the site's owner for permission before you aim automated tools at their precious data.
Looking at: http://developers.box.com/get-started/#authenticating on step #2 I'm trying to use curl to enter the credentials (user/email/password) to get the auth_token. I'd rather do it this way instead of directing the user to their browser because I'm making a script for syncing.
Anyone have an idea how I can do this? can I just do a POST with curl? I'm using v2 of the API.
You must send the user through the web page, unfortunately. However, since you are writing a script, you should also be aware that auth_tokens under the current system, so you can manually retrieve one and include it in your script.
Just one thing to note. If you don't use the standard authentication flow that goes through the Box web ui, then Box's large customers that have all their users sign-on with SSO (Active Directory and similar) logins, won't be your customers.
So, basically, if you want your app to be picked up by enterprise-level customers, then follow the building guidelines that Box provides.
I am looking at creating a good google chrome extension for tumblr.
Now tumblr uses Oauth as it's authentication method.
So my question becomes.
Do I:
Distribute a single key with the application and hope people are nice enough to not use it for illegitimate purposes.
Put in the options the ability for a user to enter their own key, hence asking each user to register an application.
Create an intermediary on my server that makes the actual request.
Something else?
I also had to consider this for my Template extension when using OAuth to communicate with the goo.gl URL shortener service on the user's behalf.
After reading Chrome's OAuth tutorial I managed to implement this simply using the following;
ChromeExOAuth.initBackgroundPage({
access_url: 'https://www.google.com/accounts/OAuthGetAccessToken',
app_name: chrome.i18n.getMessage('app_name'),
authorize_url: 'https://www.google.com/accounts/OAuthAuthorizeToken',
consumer_key: 'anonymous',
consumer_secret: 'anonymous',
request_url: 'https://www.google.com/accounts/OAuthGetRequestToken',
scope: 'https://www.googleapis.com/auth/urlshortener'
});
This is surrounded by quite a bit of logic due to the complexity of the extension but this results in the user simply being shown a page (on a new tab) the first time they attempt to shorten a URL using my goo.gl implementation. Here the user can decide to allow/deny the authentication. Since this is only done once (unless the user later removes it from their list of authorized applications) I thought this was fine and my users seem to agree.
I did also provide an option to toggle OAuth on/off but I'm guessing this will always be required for the tumblr API. On that note I must admit I'm not familiar with that particular API so I'm afraid I can't help you further.