While trying to use knowledge base Beta feature for Frequently Used Questions, I faced the below issue:
From Dialogflow console, the knowledge base seems to be working fine (matches with user request for every question found in the knowledge document)
From Twitter Direct Message, the knowledge base is not being matched with the user's request and Dialogflow is returning the Fallback Intent. To note, that:
Dialogflow - Twitter integration was done based on the latest release (https://github.com/GoogleCloudPlatform/dialogflow-integrations/tree/master/twitter#readme)
The rest of the intents are being matched normally
The knowledge base in enabled (all detect intent requests should find automated responses using this knowledge base as per Google Documentation)
Any help is much appreciated.
Related
I have made a query flow in dialogflow and it has four intent and in the last intent it uses a webhook to get data from server side and displays the result. It is trained automatically and works perfectly in dialogflow console returning response and query answer. The issue is it does not work when I use embedded url. It fails to recognize the name intent and asks (Can you repeat again or fallback intent). I've removed all intents and made query again, there is no similar name intents. Yet it works well in console and not in embedded url.
For the webhook part I've used node.js service.
Please help in this issue.
By 'embedded url' if you mean Dialogflow Web Demo (DWD), you should keep in mind that DWD can be used only for simple text messages. It does not support messages from webhook or even rich responses. However, if you steel need a web widget to embed your bot to your webpage you either create your own or you should use third party solutions (like Kommunicate). Here's the link regarding the limitations of DWD.
I'm really stuck at the process of auto-translation...
There is someone who can do a clear tutorial on how to automatically translate intents via Google Translate API over user request?
Searching all over the internet and haven't found anything clear...
I just need that if a Spanish user (for example) writes to my chatbot, the source language where the dialogflow agent is programmed is automatically translated to the detected one (Spanish in this case)
I have written and submitted an app via DialogFlow for Google Home which is now live. If I make use of the training facility in DialogFlow (https://dialogflow.com/docs/training-analytics/training) and match un-matched user questions to existing intents, do I need to resubmit my app to google for the training to take effect? Unfortunately the documentation is not clear on this point.
I contacted DialogFlow re the question and they confirmed that that app does need to be resubmitted to google if you use their training function as this alters the language model.
I am working on dialogflow and actions on Google for Google assistant integration. I have been working on it from last few months, I created dialogflow agent made required changes and setting in actions on Google as well. I used to test each and every day after implementing new features to my app (using Webhook) and found everything well before submitting to apha/beta approval. After completing my work with the app, I just submitted it for alpha/beta approval to Google and they approved it. At this point I just sent the opt in link(provided by actions on Google for alpha users for testing purpose) to the alpha testers. But unfortunately nothing is working as expected. After analyzing I found that all the parameters are always empty in the webhook request sent from dialogflow and intent didn't match as expected. But for me (developer or owner) it works fine, I mean to say alpha/beta versions are not working. The parameters should have the values of matched entity synonyms that have been added/loaded to dialogflow dynamically via dialogflow V2 APIs. It is working fine with owner account or developer account, But not with alpha/beta release.
While checking via postman if the entities gets loaded to dialogflow or not i found entities were loaded successfully to dialogflow with the same dialoflow V2 api, But due some reasons webhook request always sends empty strings for parameters.
Can any one have any idea why is this happening, And what is the solution for this issue?
Thanks in advance.
I have faced the same issue. And I found that my google actions are in deploying state and I have tried to test it with an opt-in link. But After a few hours, it is deployed properly and my custom google actions worked fine. And you also need to do alpha testing enabled in your mobile from an opt-in link.
In my NodeJS Dialogflow fulfillment, I want to reference an output context parameter from an intent from 2 requests ago within the session.
The queryResult of the latest request doesn't have that data. And the samples only seem to process WebhookRequest and WebhookResponse (
reference: https://dialogflow.com/docs/reference/api-v2/rest/v2beta1/WebhookResponse )
If I can access https://dialogflow.com/docs/reference/api-v2/rest/v2beta1/projects.agent.sessions.contexts/get I may be able to do it. But I don't quite understand if that implies mixing https://github.com/dialogflow/fulfillment-webhook-nodejs/blob/master/functions/index.js with this Client Library:
https://github.com/googleapis/nodejs-language .
In other words, it's not clear to me what the purpose of https://github.com/googleapis/nodejs-language is. Is nodejs-language intended to substitute actions-on-google fulfillments (in the format of https://github.com/dialogflow/fulfillment-webhook-nodejs/blob/master/functions/index.js ) ?
There is a lot going on here, and it isn't quite clear why you think things fit together the way you do.
The nodejs-language library is used to access Google's Natural Language API that runs as part of the Google Cloud Machine Learning API family. This is a completely separate product from the Google Assistant, Actions on Google, and Dialogflow systems. It is meant as an API for people who are looking for a pre-trained AI that can do things like sentiment and syntax analysis. It is not meant as a substitute for any part of the AoG or Dialogflow platform.
As long as the context set two requests ago was set with a lifetime more than 2, and wasn't cleared in between, then it still should be valid and sent to your fulfillment webhook. Since it sounds like you're using Dialogflow V2, you should be able to get all the currently valid contexts as part of the request that is sent to your fulfillment webhook by looking at the queryResult.contexts object in the request body.
If you're using the fulfillment-webhook-nodejs library that you referenced in your post, this should be available to you in the inputContexts variable.