I am using Botium to validate dialog flow Intents and Training phrases. I have 3 agents in my dialog flow account.
In which one agent only recognizing all the intents properly.others are not. Mostly the intents using fulfillment responses are not recognized.
It is always calling the default fallback intent.
Can you help me solve this issue?
Both agents’ default language code are the same.
Botium is using the Dialogflow API. You have to make sure that the Botium capability "DIALOGFLOW_LANGUAGE_CODE" exactly matches your Dialogflow workspace, otherwise you will receive no responses at all.
So, in your botium.json, you should add something like this:
...
"DIALOGFLOW_LANGUAGE_CODE": "de"
...
See this list as reference.
Related
Is there a way to preview the intent response with confidence score without actually triggering parameters to be filled, possible fulfilment web hooks to be called, etc.
I know Amazon Lex has a "preview intent" call that lets you preview what the response might be before actually doing the official call for a response/fulfillment.
I'm trying to be able to filter the the responses from multiple bots and choose the one with the highest confidence score and I don't want to trigger fulfilment for any bot that isn't going to be used in the dialog.
Dialogflow as of today, does not provide an option to predict the response of an intent before it is being triggered.
Dialogflow ES has Intent matching, and you might be able to do something like the next-best-intents solution, if that helps.
My setup:
I'm using actions-on-google to create a custom action for google assistant, every intent is a fallback in dialogflow that is then redirected to my server where I check the intent with a custom nlp engine and then respond to it, using the actions-on-google package.
The issue:
But when an intent is suicidal, for example: "I want to kill myself", google stop the action and give a response instead of letting my custom action handle it. Is there a way to avoid this?, it also happens with certain words like "Save" in that case google stop the action and ask me if I want to save an event or whatnot.
Can I override this behavior?
You're running into a "feature" that Google calls "no-match yielding". In some cases, if you're using a Fallback Intent in Dialogflow, and the Google Assistant itself can handle the question - it will do so.
To avoid this you can use regular Intents that match the #sys.any System Entity.
However, if all you're doing for everything is sending it to your NLU, then you don't need to be using Dialogflow at all. You can just use the Actions on Google v2 to send all TEXT Intents to your NLU for processing.
I have a DialogFlow agent with the default intents and also intents "Registrar" and "explicacion-funcionamiento" but none of these appears on Actions on Google. It only shows the defaults. I put some photos.
Although I'm using the Dialogflow integration, I need Actions on Google to access the basic information of the user (I need the email).
What can I do?
This is my dialogflow agent:
This is the actions builder:
If the user is not logged in, I will redirect him to the "explicacion-funcionamiento" but if he is signed in, he can access to "registrar" intent.
That 's why i need this intent.
You don't need to use the Actions Builder to use Dialogflow with Actions on Google, or even to use Account Linking. Dialogflow's integration with Actions on Google can still be done using the Actions Console, but the Actions Builder screens aren't available.
The pages for Account Linking with Dialogflow are still available, and most previous questions in StackOverflow still reference how to do this with Dialogflow.
Keep in mind that there are tradeoffs between using Dialogflow and Actions Builder - but Account Linking is supported equally well in both.
If you do wish to switch to Actions Builder (and to get new features, you'll need to do so), there is (currently) no way to automatically convert from one to the other.
My Dialogflow knowledge base intent is detected when I ask questions withing the knowledge base document while in the dialogflow console try it now and works well in facebook too. But when integrated kommunicate, if i ask a same question, it defaults to fallback intent and responds with fallback response. What could be the cause. I increased the knowledge base slider to strongest.
Screenshot of the console
Kommunicate supports the knowledgebase feature of Dialogflow. However, This feature is disabled by default because it is in the beta phase.
If you want to enable this feature you can contact to Kommunciate support team at support#kommunicate.io with the knowledgebase Ids and bot Id.
Check this answer to get the knowledgebase id from Dialogflow.
In trying to work with custom dialog I have encountered some issues. While using Virtual Agent as a testing grounds, I have been trying to redirect all input to a Conversation workspace by doing the following:
Disabling all intents other than the 3 mandated ones (Connect to Agent, Agent Settings, None of the Above).
Configure custom dialog to be invoked on the intent "None of the Above".
This should have the effect of sending all input to the "None of the Above" which essentially sends any input straight into the Conversation workspace. When testing this approach without tying in the workspace, the simple canned message does get invoked on any input as expected. However, when adding the workspace ID and Conversation credentials (checked several times for accuracy), I get the error:
Error -- Unable to create custom dialog service
So I am wondering why this might occur.
Your logic is correct but this error means there is a missing or incorrect workspace attribute.
Please use the following values:
Conversation endpoint
"https://gateway.watsonplatform.net/conversation/api"
API Version:
"2016-07-11"
CaesarOG:
The Off_Topic intent is "special" - it invokes your custom workspace without forcing the intent to be Off_Topic (unlike the other intents in Watson Virtual Agent). This design decision was done so that you could do the sort of thing you are trying to accomplish. If in your custom Conversation workspace you have custom intents, and you add your custom dialog to respond to those intents, the Watson Virtual Agent will have Conversation evaluate your utterances against the custom intent detection system and trigger your custom dialog as you would expect.