I am using one DailogFlow(DF) agent for multiple customers. The agent is used for a voice assistant. I use Voximplant as the programmable telephony environment. The agent has dynamic responses build-in using placeholders. Based on the customer using the agent I can give different answers.
I would like to offer a set on intents in DF that the customer can choose from. Means, I need to be able to disable intents (ignore) based on a sessionID or other parameter. Disabling intents for the whole agent is not an option as some customers choose to enable other intents then others.
Anyone knows if that is possible? Kind of use the "ignore" function in ES on a multi-tenant approach.
Appreciate your help
Related
I would like to implement and publish my first Google Action. The application will guide you in choosing a particular product according to the user's answers. The action will have Dialogflow as a backend. is it allowed using the same DialogFlow agent (or a clone of this) to drive an e-commerce support chat according to Google policies?
I tried to search for information with no result.
Thanks in advance
Let's say I have a desktop app that listens to a user, and leverages Dialogflow to determine intent.
In the app, we just call:
https://dialogflow.googleapis.com/v2/projects/my-project-name/agent/sessions/123456789:detectIntent
Let's also say the active user is "UserX" in our system, and we need to retrieve information specific to the account.
I understand that Dialogflow utilizes webhooks for fulfillment as described here:
https://dialogflow.com/docs/fulfillment/how-it-works
However, I'm unclear how user information can be sent to our webhook such that we'll be able to tell that "UserX" was the one who made the call to Dialogflow.
Can anyone explain if/how communication of user information is supported in fulfillment webhooks?
It is supported by fulfillment. There are a number of ways you can do it. Assuming that the user has communicated with the agent, the agent can then store the users response i.e. lets assume the agent asked the user what their name is. Since the agent can store that info (UserX) in a parameter, that parameter can then be passed to the fulfilment. The agent can also store user responses in context parameters and they can also be passed to the fulfilment. Finally even if the user does not provide info to the agent you can also use the dialog flow API to pass data to the agent which in turn can be passed to the fulfillment.
We are using Chatbase for multiple clients that we identify with a different version number.
See my previous question here: Track multiple context for the same Bot
We have a dashboard for all those clients and would like to show them their own data. A bit like Google analytics allows it.
So:
Is an API in the pipeline (I couldn't find any existing resources)
If not, in what alternative way could we get the data to present it?
We have a .csv export that is currently limited to the first 500 rows of your message variations report. It is on our roadmap to increase the scope of this report, however there is no official timeline for release.
Our recommendation for deploying an integration like you described in your message is as follows:
Have the user create a Chatbase account in order to obtain the API key
Have the user integrate their analytics on your platform by providing the API key
Send the messages from their bot to their Chatbase API
Provide the user deeplinks to the Chatbase reports from within your UI
Alternatively, you could configure your bot to send a redundant message to an internal database, or bigquery table to have access to all of your logs.
If you would like access to data you have sent to Chatbase up to this point, please contact chatbase-support#google.com and provide your bot's name and/or api key and we can provide a one-time export.
I am creating a health care chatbot. I want to use same agent for all of my clients. But i want to use same agent for all clients. I want to add intents for each client dynamically . So is there any way i can create intents for each client per session ?
I have an application that serves multiple customers. As part of my workflow, I would like to use PubNub for realtime messaging to customers, offering something like one channel per customer. I would like to just give my customers a subscription key that they can use to listen to messages on their particular channel.
Is this a supported scenario on Pubnub? What’s the right way to set this up? I assume that I will do all the setup on my side and also handle all the billing, while just handing my customers the subscription keys to their channels. But for now, on my Pubnub account, I only see one “subscribe key”. I would like all keys and customer data to be isolated from one another.
You should use the PAM access manager feature for handling this. In addition to the subscribe key you will also provide your customers an auth-token. You can grant access to an auth-token to publish/subscribe to a specific set of channels.
You can find more details here:
http://www.pubnub.com/docs/javascript/tutorial/access-manager.html