It appears that Dialogflow can only respond to what's tweeted at my bot. Is there anyway to get it to respond to non-# my bot tweets?
Dialogflow's built-in Twitter integration works with #-tweets and DMs.
To handle arbitrary tweets, you would have to write your own Twitter integration using the Dialogflow API and Twitter API, calling the detectIntent endpoint for each incoming tweet and posting the response via Twitter's API.
Related
I recently did some Watson Assistant integrations. Whatsapp, Telegram and Facebook Messenger and now I'm looking to do the same thing with Instagram.
I saw that Facebook (now Meta) recently published the API to do this integration. But I tried to replicate what I had done on Facebook Messenger, (set up webhoock, link page, set up test user) and Direct doesn't give me a return.
I would like to know if Watson and this API are compatible with each other.
And if not, is there any platform to do this integration?
It is currently possible.
Instagram provides an API in which you can capture a Webhook and exchange messages, while node red creates a url that will be sent and received as responses
You can also use captivate hub to connect your watson assistant on instagram
Link: https://hub.captivat.io
Manual: https://manual.captivat.io/install/channels/instagram
I have a Dialogflow agent which is integrated in an app and a web version. I want to integrate this chatbot with Chatbase to get analysis metrics of the bot. However, as of chatbase documentation we cannot integrate Dialogflow hosted bots with Chatbase but if I have a server in the middle of my app and chatbot which is saving all the data, can I integrate chatbase with it?
The typical way to integrate Chatbase is to have it called as part of fulfillment. This requires you to set each Intent to use fulfillment, but you can still set the reply as part of the Intent, if you wish. In your webhook, you would call Chatbase to record the event, but not return any response in the webhook, and Dialogflow will use the Response set in the UI.
Chatbase reports are built upon user messages and intents, however there is value in sending us the bot messages to provide context to the Transcripts feature. You can create a server to server integration to send us the JSON payloads in real time, or in batches of up to 100.
Im using fulfillment to get data from database. And I have integrated my bot with facebook.
And currently I'm customizing db response as per facebook in my api itself and sending it to the dialogflow.
And I want to integrate it with skype too.
Now my question is, can I customise my api response in dialogflow instead of in API. As I want to integrate my bot with multiple platforms so accordingly their response will be formatted as per facebook or skype.
So i will need to create another api for skype too. I want to avoid this.
So I want to get output from my api and format it in dialogflow itself using custom payload. So is it possible to work in this way?
Sure! You get the stored data using your API and then you format the response for the platforms you are going to use. In this example, the payload contains different responses for Google Assistant, Facebook and Slack.
Also, take a look at this NodeJS library which makes easier develop your fulfillment code.
I have a case where I need to create a Bot in Slack that my users can use conversational language to get information out of my web app in real time. The scenario goes something like:
User asks the bot something like: #hrbot How many employees are in the Finance department?
Bot send the string to API.AI/ diagflow to resolve into a JSON request
API.AI sends the JSON request to my Web App endpoint via webhook to get the answer
Answer is returned to user's Slack channel
Question:
1. How do I get the auth token from api.ai to send message to slack?
With Dialogflow (formerly API.AI) you provide a webhook (a HTTPS URL where your server is) and Dialogflow will send a HTTPS request to your webhook when requests come to your Dialogflow agent. You can enable the Slack integration in your Dialogflow agent through the web interface and all requests from Slack will be sent to your Dialogflow agent and (if you configure it) to your webhook with NLU information and the original request from Slack.
Information about the request that is sent to your webhook is documented here: dialogflow.com/docs/fulfillment#request if you respond to the request the response will be forwarded to the user that trigger the request. The response format is documented here: dialogflow.com/docs/fulfillment#response
I require to send messages asynchronously from my service to api.ai and then api.ai would send it to Facebook Messenger.
To achieve asynchronous messaging I have used custom events.
But on using custom events, events are getting triggered from webhook, and messages are going to api.ai but it is not further displaying anything to facebook messenger
Probably you want to add a delay before api.ai replies to user input, right? Than you need to add a delay in your Facebook integration app.
Consider the follow flow
User type a message in Facebook messenger window
Facebook sends the message to your integration app
Integration app sends the message to api.ai
Api.ai responds to the message and send the reply to the integration app
Integration app wait for a while and than sends the reply to Facebook
Regards