I have implemented the "tompaana" solution for bot-agent-handoff (1 to 1 conversation), but how can I establish a "1 to n" scenario (i.e. one agent handling multiple users after bot escalation)?
I have implemented as per the link given below :
Referred link : https://github.com/tompaana/intermediator-bot-sample.
The way I have implemented it was using back channel in the directline api. When agent connects pass the agent details as well as session details with the "start conversation". However any mechanism that stores conversation reference of specific chat with the session would work
https://github.com/microsoft/BotFramework-WebChat/tree/master/samples/04.api/b.piggyback-on-outgoing-activities
For the intermediate-bot-sample, here is a comment by #tompanna with regards to a call center support scenario issue:
I think the best bet to implement a call center, given that one want to use the message router, is to take the message routing component source and customize it based on one's needs. LiveEngage is one that has routing capabilities out-of-the-box, but can be enhanced with custom code. I have implemented a simple connector for LivePerson service (Node.js). Ibex Dashboard is another OSS project by Microsoft containing enablers for this kind of a scenario (but does not do the job out-of-the-box).
You can take a look at the BotFramework HandOff experimental sample. Also, there is a Node sample by TDurnford where you can message #list to get a list of users waiting to talk to an agent in the queue, and message #connect to connect to the user waiting at the top of the queue.
Hope this helps.
Related
I have a Text2SQL model (EditSQL: https://github.com/ryanzhumich/editsql) which I have configured to take a sentence as input and return a SQL query as output.
Now, I want to deploy this program as a chat bot application in Microsoft Teams.
I understand there's Microsoft bot framework that enables publishing a bot and the 3 options are described here.
https://learn.microsoft.com/en-us/learn/modules/choose-bot-building-tool/
However, I am not finding any of them suitable for my use case since I need to deploy a Question-Answering Bot where the Questions from users need to be sent to an external server like AWS and the response from AWS (could be an excel file) needs to be sent back to the user. Multiple questions can be the part of a conversation, so the chat client should be able to mark start and end of a conversation.
My problem:
What are the basic steps of exposing a ml model via a server so that it can be queried in production.
What are the tools that will allow me to make a client on Teams and a server for this model on AWS?
Please let me know if I should add more information on this.
Thanks
As you've seen, there are a bunch of tools/approaches to creating bots in the Microsoft world, for Teams or otherwise. Underneath, these all use the Bot Framework, but you can develop directly (i.e. write code), or use a higher-level tool like Bot Framework Composer - the choice is yours depending on your own internal skills. If you want to work with code directly, here are a bunch of bot samples, in multiple languages: https://github.com/microsoft/BotBuilder-Samples/tree/main/samples . For isntance, here is an example of integrating the Microsoft QnAMaker service into your bot: https://github.com/microsoft/BotBuilder-Samples/tree/main/samples/python/49.qnamaker-all-features
Basically, if you go the development approach, your bot is just a web service. Once it receives the message, it can call out to any other service behind the scenes. That means it can receive a message, call out to an AWS service, receive the response, and send a reply to the user.
For multiple questions as part of a 'set' of chats, Bot Framework provides an idea called "dialogs" that should work for you.
I am currently looking at using Microsoft Web Chat to interact with my existing Node Js application built on MS Bot Framework Core but uses DialogFlow as NLU.
Current implementation: Web Page -> Custom UI Widget -> Connects to Node.js app built on MS Botframework Core -> Queries DialogFlow NLU to identify Intent -> Node.js app constructs the Dialog -> Gives response to user.
Looking at the Web Chat component, I cannot find references using any other NLU except Azure Bot Service. Is it mandatory to use Azure Bot Service/LUIS NLU to integrate with Web Chat?
I have also looked at offline-directline npm module but the last dev on the module is more than 3 years ago.
Firstly, responding with a quick message about using offline-directline, you should feel reasonably comfortable with it. It is a few years old, but seems to stand the test of time with continued use and little in the way of issues that I have heard.
Another option would be to use a 'browser bot'. In this scenario, the bot is contained within the hosting page's html/scripts. So, there is no reliance on using Direct Line. I don't know your whole setup, so this may or may not align with your overall needs and architecture.
As for using Web Chat with something other than the Azure Bot Service, this would be an uphill battle. In theory, this is probably achievable to some degree. The issue is that Web Chat is heavily integrated with the BotFramework-DirectLineJS library. You might be able to cherry pick specific components from Web Chat, replace the Direct Line library with a make of your own, and modify the remaining code to work with your 'service'. But, I'm not certain the effort is worth it. That is something you would have to decide for yourself.
If you do go this direction, you will likely need to configure your 'service' to send messages that conform to the BotFramework schemas when communicating with Web Chat. Even without the dependency on Direct Line for connecting to the service, much of Web Chat is still oriented towards what an incoming message looks like (i.e. a BotFramework Activity) and handling it according to the properties it contains.
To start, here are a few areas you should review in order to correctly configure you service to handle inbound and outbound messages going to and coming from Web Chat:
BotFramework Activity schema
BotFramework Card schema
BotFramework Transcript schema
Web Chat's Activity, Card, Attachments, etc. Types - at present, these are loosely defined. I would expect that to change at some point in the future which may prove to be a changing break in your specific scenario.
This is not exhaustive and would require greater research as there are likely other considerations than the few I've listed above. But, again, this may not be necessary if you decide to utilize offline-directline.
I am developing a customer service chatbot, using Azure's Bot Framework in .NET, using the the Messenger channel. I wanted to know if anyone knows what the best way to handle the handoff to a human on Zendesk (which my platform already uses as its CRM platform). I'm not looking for when to do the handoff, but how to manage what happens next.
What I would love to be able to do would be that so when handoff is needed, a ticket on Zendesk would be created, sending for example a file (the transcript of the conversation so far). Then the agent would be able to solve the customer's problem in that ticket, having a conversation with him, having the bot sending messages back and forth between zendesk and messenger.
I don't know if this has been done before, or if it's at all possible. And I'm free to other solutions to the problem of handling this kind of handoff, without having to create a separate "chat" for the customer service agents to use, like it's explained on the azure documentation.
Thank you for your patience while I researched this. I found this resource that I believe will meet your needs. This functionality is built off of the Bot Framework utilizing .NET (it's also available for Nodejs). There are two available methods to connect a client to an agent.
The first (which should apply to you) aggregates different channels into one allowing an agent to pickup in the same channel where the bot handed off. The second opens a new channel when an agent joins the conversation.
Intermediator Bot
I was able to spin up a bot using this and confirmed the bot was listening for outside traffic.
Hope this helps.
Steve.
One thing that I'm about to try is this:
Bot conversation ends.
Bot service calls an Azure Function, passing the conversation content.
The Azure Function integrates with Trello API, creating an entry on a Kanban board.
So, instead of Trello as I want to do, you can make a call to the Zendesk API.
I'm writing a few articles about developing Azure bots. The next two actually are dealing with these very things. You can find out more here. sign up if you'd like to get notified over the next week or so when the new tutorials are online.
Hope that helps!
Tim
I wonder to know which technique and tools I should use to have the ability to send real time notifications to users. Specifically if I build a messaging system.
I can see that modern social networks can send notifications about new messages almost immediately. Even when the user 'A' from one country writes a message to the user 'B' in another country you can see that the user 'A' writes a message and you immediately see it (even if those users live in different continents).
I tried to figure out how it is possible and find any information about this but without success.
The only thing I found out is the technique when we use a Redis or RabbitMQ server with several servers which acts like publishers and subscribers. Our API servers receive new messages then they push a new message in the queue then subscribers receives the messages and if they have an open WebSocket with the recipient they push this message in the WebSocket and a client receives the message.
But it really won't work if you have a distributed project and your clients are connected to the nearest servers in the nearest data center.
The question is: what technologies/techniques/anything we should use to be able to build notifications in a distributed project?
If you develop your distributed app/system using web technologies, you can consider building what is referred to as a Progressive Web App. With PWAs you can add push notifications in a relatively easy way. You could start with a PWA approach, and then decide later on if developing a native app as well (i.e. iOS or Android) would be necessary.
There are many resources to learn and guide you in developing progressive web apps. Check the references I mentioned above, and you can do this codelab as a starting point.
Hi we are thinking to implement a chat feature in our web app. (MVC 3 running on Azure) like Facebook or Gmail applications.
So the idea about this question is to have your technical architecture opinion about it.
How would you design it and which services you would use (worker role, queue, blob, Sql azure etc.).
Thanks
Instant Messaging is about asynchronous delivery of messages between multiple publishers and subscribers. This sounds like a perfect recipe for Azure Queues.
If the number of users who will use this feature is small, you can create a queue per recipient. Web-app would drop a message onto the recipient's queue and would check queue of its own user.
The positive about this approach is its simplicity The downside of this approach is the frequency of checking the queues per user and the cost associated with that.
If you have 10,000 users logged into IM and the app is checking their queue's once per second, that's 1penny per second. Which translates to ~$26k/month.
Windows Azure Service Bus provides Publish-Subscribe messaging with Topics that can be used for this scenario. You can see a Silverlight based Chat sample for this: http://servicebus.codeplex.com/SourceControl/changeset/view/9715
In addition you can see a Multi-tier app sample that shows using Service Bus Topics/Subscriptions from Web/Worker roles here: http://code.msdn.microsoft.com/windowsazure/Multi-Tier-application-6c033cad