For example if you have IntentA and you add 2 followup intents: IntentB, IntentC, it works ok it should add a context because it doesn't have an output context yet. But here is the problem. Sometimes if you add another one, for example a FallbackIntent, it just adds another context (SOMETIMES) and if you delete it in both(IntentA and FallbackIntent), so they both have the same context, meaning they should still be connected, and the hiearchy shouldn't change,but it still does. It still works perfectly, but still this is a wierd behavior. Any ideas why this happens and how to fix it?
Intent A
Intent B
Fallback
The best way to resolve this issue and organize the structure of your dialogflow agent is to upload the intents using create_intent() function of dialogflow api.
You can give the root intent as parent_followup_intent_name, and all the intents having this root intent will fall under same intent. Note that you will need to give root intent ID not the name.
You can read more about create_intent api using python sdk.
intents_client = dialogflow.IntentsClient()
intent = dialogflow.types.Intent(
display_name=display_name,
training_phrases=training_phrases_parts,
messages=response,
input_context_names=input_contexts,
output_contexts = output_context_list,
parent_followup_intent_name=root_intent,
)
intents_client.create_intent(parent, intent)
EDIT:
As requested, here's 2nd and easier way of doing this without any prograpping knowledge.
Suppose your agent looks like below screenshot before, and you want
to group intents under how to solve intent
Go to Setting -> Export and Import -> Export as zip the agent
Once exported, unzip the files and go to intents folder. Your files will look something like below screenshot
Open how to solve.json file and copy the id of this intent
Open all the json files which you want to group under how to solve
intent (note we have to open the files which do not have
_usersays_en as they only contain user utterances
Paste the id of how to solve intent as parentId in these json
files like below screenshot (in this case intent id of how to solve intent was b2131b0e-f86d-429d-957c-65c070ddd5df)
Once all the changes have been made, then zip the directory
Again go to Setting -> Export and Import -> Restore from
zip and select the zip file you have just created
Intent will look like below screenshot once the process is complete
Hope it helps.
#sid8491 - this is absolutely ingenious :)
Thanks for that! Works like a charm and I can confirm that this is just a visual representation. No need to worry about changing your code.
Just a small addition: When you already have follow-up intents, they already carry
"id": "70a48f63-662b-48d4-9a78-dd0af3e0db87",
"parentId": "5a1b5861-fadc-480e-b03b-11bc034df8b9",
"rootParentId": "6c9cb1d6-3efb-4bac-b768-ae3265faa7b6",
Make sure to adjust rootParentId to the aforementioned id of the root-intent, leave parentId intact and you're all set. Didn't try with a follow-up/follow-up/follow-up etc. structure but I'd say it will follow the same pattern somehow.
Related
I'm writing a client-side application which should read in a file, transform its content and then export the result. To do this, I decided on Re-Frame.
Now, I'm just starting to wrap my head around Re-Frame and cloujurescipt itself and got the following thing to work:
Somewhere in my view functions, I send this whenever a new file gets selected via a simple HTML input.
[:input {:class "file-input" :type "file"
:on-change #(re-frame/dispatch
[::events/file-name-change (-> % .-target .-value)])}]
What I get is something like C:\fakepath\file-name.txt, with fakepath actually being part of it.
My event handler currently only splits the name and saves the file name to which my input above is subscribed to display the selected file.
(re-frame/reg-event-db
::file-name-change
(fn [db [_ new-name]]
(assoc db :file-name (last (split new-name #"\\")))))
Additionally I want to read in the file to later process it locally. Assuming I'd just change my on-change action and the event handler to do this instead, how would I do it?
I've searched for a while but found next to nothing. The only things that came up where other frameworks and such, but I don't want to introduce a new dependency for each and every new problem.
I'm assuming you want to do everything in the client using HTML5 APIs (eg. no actual upload to a server).
This guide from MDN may come handy: https://developer.mozilla.org/en-US/docs/Web/API/File/Using_files_from_web_applications
It seems you can subscribe to the event triggered when the user selects the file(s), then you can obtain a list of said files, and inspect the files contents through the File API: https://developer.mozilla.org/en-US/docs/Web/API/File
In your case, you'll need to save a reference to the FileList object from the event somewhere, and re-use it later.
I am having a bot set up the beginnings of a game. A human inputs the command of /startbrawl to initiate the setup of the game (creating the deck objects). But the two players need to be identified first. I have a message sent from another command that says "Player A is #[username A]. Player B is #[username B]." in the channel this game is happening in. I want the bot from this new command to look at the first message sent in the channel, which is always the "Player A is etc..." message (and is always sent by the bot) and pull both usernames from it in order to specify for this new command who is player A and who is player B. The code I have most recently (after trying multiple things) is this:
if (userInput.startsWith("!startbrawl") === true) {
message.channel.fetchMessages().then(messages => {
const botMessages = messages.filter(message => message.author.bot);
console.log(botMessages.mentions.members.first()) //this will be Player A. I'd repeat same for Player B with .last instead.
}
}
This gives me an error:
(node:15368) UnhandledPromiseRejectionWarning: TypeError: Cannot read
property 'first' of undefined.
I have made the last line be console.log(botMessages) to get all the info about the messages the filter finds. But trying to extract only part of it gives issues about not being defined, or just a result of undefined with no errors. Either way, something isn't working how I think I need it to.
The only other thing I've debated trying is exporting variables from the command prior to this new command. Player A and Player B are defined in the command used to make the channel that this new command is then used in. However, I've never had luck with exporting variables when I've used it in other instances. I use a command handler, so I'm not sure if that affects how exporting variables works... Which method would work best to set up the card game? I'm a novice in general just figuring things out as I go, so some advice (beyond take a course, look up basics, etc) is greatly appreciated. I've taken an online course for javascript and I work best figuring things out first hand.
Thanks for the help in advance!
As botMessages is a collection you wanna get a Message object out of it by doing
botMessages.first()
So try logging something like
botMessages.first().mentions.members.first()
I have a DialogFlow intent follow up that I'm having a hard time with. It's the only follow up to my main intent, and the issue I'm having is that when
the incidents.data array is empty it doesn't trigger the conv.ask statement in the else case and causes DialogFlow to throw an empty speech response error. The code looks something like this:
app.intent('metro_timetable - yes', async (conv: any) => {
const incidents = await serviceIncidents.getIncidents();
if (incidents.data.length > 0) {
conv.ask('I have incidents')
} else {
conv.ask(
`I wasn't able to understand your request, could you please say that again?`
);
}
});
incidents.data gets stored in the global scope, and is set deep within
the metro_timetable intent. It stores an incident for the follow up. Because all yes responses trigger the follow up I setup an else case so it catches it if someone says yes when metro_timetable doesn't understand their original request and asks them to repeat it. If incidents.data actually has information to share the dialog triggers correctly and I have incidents is correctly read to the user.
In DialogFlow it looks something like this. Where am I going wrong here?
Your description is a little convoluted how incidents.data actually gets set, but it sounds possible that instead of it being set to an empty array, it isn't set at all. In this case, I suspect that the following happened:
incidents.data would be undefined
Trying to evaluate incidents.data.length would cause an error
Since the program crashes, your webhook doesn't return a result. Since you probably didn't set a result in the UI for the intent, an empty result was returned.
You can probably solve this by doing a test such as (for example)
incidents && incidents.data && incidents.data.length > 0
Your other issue, however, seems to be that you have a Followup Intent set for a scenario where you don't actually want that as the followup. This is one of the reasons you probably shouldn't use Followup Intents but, instead, only set a context when you send a response where that context would make sense, and look for the "Yes" response in the context you define. Then, when metro_timetable doesn't understand the request, you don't set the context and you give an error.
To do this, you would remove the automatically generated metro_timetable-followup context from the two Intents. You'll create your own context, which I'll name timetable for purposes of this example.
In the fulfillment for the metro_timetable Intent, if you respond with something that needs confirmation (ie - when "yes" will be something the user says), you would set the timetable context with something like
conv.contexts.set('timetable',2);
conv.ask('Are you sure?');
You can then create an Intent that checks for timetable as the Incoming Context and has training phrases that are equivalent to "yes". In that Intent, you'd do what you need to and respond.
I'm trying to manage the context of my Google Assistant agent (in DialogFlow), using the ApiAi class in the npm package actions-on-google.
The problem is this:
How can I reset the lifespan / delete a context using the npm package?
I can easily set the lifespan of a new context, and it works.
However:
How do I delete a context?
Setting the context to a different number does not seem to work. That is, if I set app.setContext('myContext',10) and then, 2 intents later, when the lifespan in 8, I call app.setContext('myContext',10) again, in the next intent, the lifespan is still 7. If I could answer (1) and delete a context, I'd just delete it and set it again.
I don't think there is a way to delete or overwrite the duration of a context. Instead, if you know that a certain context must not be active at a certain point, set a context that lasts for 1 or 2 turns and do this after each turn. This will also give you more control over the conversation, so you won't have contexts that last for 10 turns that you suddenly don't need anymore.
To delete a lifespan of context you just set it to ZERO or 0 like app.setContext('your_context',0)
Make sure you do this before calling the app.ask or app.tell
or
if not using client you could write a function that simply sets
this.contexts_[your_context] = {}
The first option is definitely working for me. I have not tried the second option. Try and see if you are not setting it in the Dialogflow. Also, you can remove context setting in webhook and put lifespan as 0 in Dialogflow. That will put a line (like deprecated method) over your context.
I know this question is old, at least old enough so that we now have a v2 API and library overhaul, so I'll answer anyway with today's solution :) .
1 - To delete a context, you can use conv.contexts.delete('context1'); as specified on the Node.js library reference docs.
2- If conv.contexts.set('context1', 1); doesn't change the context's lifespan then you can easily delete it and recreate it with these two calls.
My experience is that you cannot overwrite context data.
You can create a new context though:
agent.setContext({
name: contextName,
lifespan: newLifeSpan,
// Note: Parameters are not visible until the context is passed
// console.log() won't show them now.
parameters: {
// Previously saved using getContext()
param_name : paramValue,
}
});
API.ai's prebuild packages allow you to easily get long lists of intents. Currently I'm trying to make use of their smalltalk package, which has at about 100 intents, and response to each.
I am making use of the api-ai-recognizer package to listen for intents. That works well, but now I have to match those intents, so that I can define the dialog (which is nothing more than using the fulfillment). And this is where I am having trouble.
intents = IntentDialog({recognizers: [apiairecognizer(CLIENT_TOKEN)]})
intents.matches('smalltalk', smalltalk_handler) // No luck
intents.matches(/smalltalk/, smalltalk_handler) // No luck
intents.onDefault(default_handler)
In the default_handler I capture the args:
{"score":1,
"intent":"smalltalk.greetings.how_are_you",
"entities": [
{
"entity":"Lovely, thanks.",
"type":"fulfillment",
"startIndex":-1,
"endIndex":-1,
"score":1
},
{
"entity":false,
"type":"actionIncomplete",
"startIndex":-1,
"endIndex":-1,
"score":1
}
]}
This makes sense according to the documentation of how matches works.
But that does mean that I don't know how to actually use the full list of intents, without explicitly copying every single intent in.
Just to clarify, if I use the exact intent:
intents.matches('smalltalk.greetings.how_are_you', smalltalk_handler)
I receive the nice response: Lovely, thanks.
Any suggestions?
So far, the only thing I have come up with is to modify the api-ai-recognizer such that it will return only smalltalk as intent, whenever it encounters a version of it. This way the intent dialog only needs to recognize one intent. Because they are handled in the same way, it doesn't matter at this point.