Post has attachment
"@sys.given-name" sometimes does not recognize.

I pre-defined and also trained over 30 examples to get the name. Phrases like "My name is Luis" or just "Luis". (In Portuguese from Brazil)

But some names like "Matheus" simply can not recover the entity, arriving at the right intention.

What can I do?

-

Remembering that I did the pre-workout using that name. And I also accepted training under that name. Even so does not recognize.

Several other random names that I have tested, they work. Even short names.

Photo

my webhook is sending 3 blocks of texts, but in the example webpage the return is empty. Because?

Follow:
{
"responseId": "xxxxxxx",
"queryResult": {
"queryText": "oi",
"parameters": {},
"allRequiredParamsPresent": true,
"fulfillmentMessages": [
{
"text": {
"text": [
"texto 1"
]
}
},
{
"text": {
"text": [
"texto 2"
]
}
},
{
"text": {
"text": [
"texto 3"
]
}
}
],
"webhookSource": "xxxxxx",
"intent": {
"name": "projects/xxxx-2b0c7/agent/intents/xxxxxx",
"displayName": "smalltalk.hello"
},
"intentDetectionConfidence": 1,
"diagnosticInfo": {
"webhook_latency_ms": 276
},
"languageCode": "pt-br"
},
"webhookStatus": {
"message": "Webhook execution successful"
}
}

Hi! I'm moving my first steps with Dialogflow; I followed and completed the V1 tutorial about agent creation and webhook fullfillment (https://dialogflow.com/docs/getting-started/building-your-first-agent and https://dialogflow.com/docs/getting-started/basic-fulfillment-conversation). So, my question is: is there a new tutorial for V2 ? Or the old one is still valid?

Hi everyone,

I want to integrate dialogflow with intercom chatting platform. I could not find any integration steps in dialogflow documentation. If anyone has done this in the past, please let me know.

Post has shared content
Introducing a different kind of library

If you're developing in node.js, and primarily for Actions on Google, I've created a library that takes a different approach. Instead of peppering your code with the phrases to reply with, your code focuses on getting the values you want to reply to the user with. The responses are templates (with logic!) that you set in a configuration file and are based on the Dialogflow Intent, Action, or a new value we call an "Outent". This takes the Dialogflow design and expands it in ways that allow for easy configuration and flexible responses to the user.

We'd like to expand the support to the other platforms supported by Dialogflow, so please check it out and provide feedback.
Introducing Multivocal

I'm pleased to announce that Multivocal 0.6.0 is released. (More like a pre-release.)

What is multivocal?

Multivocal is a node.js library that takes a new approach to help you build for Actions on Google and Dialogflow (both v1 and v2). It is largely configuration driven - the phrases, cards, lists and so forth that you intend to send back to the user are stored as templates in a configuration file. Your handler functions primarily focus on loading the values that you'll use in the templates. Using Firebase Cloud Functions, Google Cloud Functions, your own Express server, or AWS Lambda is as simple as changing one line.

Multivocal handles most of the boilerplate for you as well, letting you focus on what you want to say. It handles things like unknown input, no input, and the different ways users can quit for you. It keeps track of how many times a user has visited, or even run a particular Intent in the session or ever and lets you send different messages based on this criteria.

Follow this page to hear about further updates and check us out at https://multivocal.info/ which contains links to the npm entry and the github repository, as well as some initial documentation and examples. (More documentation and examples are forthcoming - targeting feature and documentation completeness with version 1.0.0.) We also have plans to support the Action SDK, chat platforms supported by Dialogflow, and even Alexa.

Multivocal is open source - check it out, try it, and provide feedback and patches!
Photo

I have an intent "A". The intent A is using web hook to respond the query. I have a follow-up intent "A1", the is of yes type. When I get response from intent A, I type "yes", but instead of executing A1 intent, it executes web hook.

Any pointer to solve this issue?

Greetings... I hope I am in the right place for my purpose. I help individuals who have nano-businesses and need to track appt and client data. The handful of people I help either use gmail and Google Calendar, or I tell them to switch to it because I run a print out of their schedule and format it for import to a spreadsheet or database. I'd like to help more people, but I do this for love/support of others and not money, so I need it to be easier. Is there a way to program a more consistent csv type output of calendar data with Dialogflow? Is there anyone who would be willing to work with me on this project?

Hello everybody!
I'm a newbie in Dialogflow and reading the documentantion, I'm a bit confused.
My goal is developing a chatbot, that potentially could be integrated in many platftorm APIs like Telegram, Messenger, etc... Is it possible, or Dialogflow is tied with the use of Google Actions? Also, is the use of Google Cloud Project compulsory?

hello every body ! I so happy to meet you.
I want to build an amazing combined AI,chat,autonomous car system an much software in futur .So i hope you will help me understanding a lot of thing in these area .
Thank!!!

Post has attachment
Loading, please wait...
Animated Photo
Wait while more posts are being loaded