Is it possible to train multiple projects at a time in RASA NLU using single config file?
Or how can I configure one rasa core domain with multiple RASA NLU projects and access them?
If anybody needs any extra info Please comment will update my question.
Regards
There is currently no option for Rasa Core to route between various Rasa NLU instances. You would have to run multiple Rasa Core instances and connect these to different Rasa NLU instances.
In Rasa 1.0 Rasa Core and Rasa NLU were merged into the rasa package, which means both components are trained as one model.
Related
I have installed Rasa Core and NLU in my computer and after training
and build the models now my chatbot is ready but I'm not getting clear
documentation or way to deploy or integrate with a website.
I have 'Rasa' named folder and 'venv' virtual environment. I tried to
put it into a website but they are blocking the files. So what is the
method to put the Rasa chatbot into the website for 24/7 live chat?
For connecting your chatbot to a website, try using https://github.com/botfront/rasa-webchat i.e. "A chat widget to deploy virtual assistants made with Rasa or Botfront on any website." You'll need to add something like
socketio:
user_message_evt: user_uttered
bot_message_evt: bot_uttered
session_persistence: true/false
to your credentials.yml. See https://rasa.com/docs/rasa/user-guide/connectors/your-own-website/ for further details on connecting to your own website.
In terms of deployment, the recommended way to deploy a rasa chatbot is using Rasa X using either docker-compose or kubernetes/openshift. The easiest way would be to use the one line deploy script.
https://rasa.com/docs/rasa/connectors/your-own-website/#id2
after training your bot run the command
rasa run --enable-api --cors "*"
Add the REST channel to your credentials.yml:
rest:
# you don't need to provide anything here - this channel doesn't
# require any credentials
The bot we have created uses DialogFlow as NLU Engine and uses MS BotFramework core as a dialog manager that creates dialogs as steps.
The preview version of Bot Composer looks powerful and intuitive way to create the Dialogs and manage them. But none of the documentation or Ignite Videos give a clear view whether it can be used for other NLU's(for obvious reasons, they wanted to promote LUIS).
So, curious to know if some integrated the composed with other NLU's apart from LUIS. If so, what are the caveats.
Though LUIS provides a builtin way of managing intents in Bot Framework Composer, you can still access external API's like any NLU endpoints you want to use by incorporating an HTTP step into your dialog.
I'm trying to develop a centralized rasa stack for different Facebook pages. All fb pages are of different schools and all schools are using a same software for storing data which is resides in a server. All schools' data are separated by different mysql database. The bot will be used to fetch data for different schools from the respective school's fb page. All the conversation flow will be same, just the db will be different according to the schools. I'm new to rasa. Is there any way to connect all the fb bot to a single rasa stack and differentiate the db according to fb bots when performing the data retrieval from db in custom actions? Any help will be highly appreciated.
Unfortunately this is currently not possible. You can have only one of each output channel. This mean, you would currently need to deploy one Core instance per facebook channel.
I added an issue for that to Rasa Core since I think this would be a cool feature for Rasa Core.
Requirement: I need to enable bot to handle QnAs, talk to SharePoint list for dynamic form flows and return custom designed cards/actions, preconfigured troubleshooting services with common questions and integration of Service Now etc.
Question: Since the bot is doing more than one, should I consider designing individual LUIS models and use dispatcher service? or could I build it using multiple intends with single LUIS model?
Reference: https://learn.microsoft.com/en-us/azure/bot-service/bot-builder-tutorial-dispatch?view=azure-bot-service-4.0&tabs=csharp
I want to train an ANN model for each individual, in azure ml. For example, there is an application which wants to learn the behavior of each individual separately. How is this possible in azure-ml? Any suggestion?
As I know, I can create a model and train it with some data, but I don't know how can I train it specifically for each user. I should mention that I am seeking for a scalable idea which is applicable for a real situation (might be for 100 thousands users).
I highly recommend the Create many Machine Learning models and web service endpoints from one experiment using PowerShell article on this topic. It uses Azure ML PowerShell to automate creation of web services that have identical structure but user-specific trained models. Your application would need to keep track of the correspondence between web service and user.