Skip to main content

Know the rasa ecosystem and train your model effectively

Hope you have read the previous blog to create chatbot using Rasa. I would recommend to read it before starting this blog.

This blog will help you understand insights of rasa ecosystem and explain how to train your model effectively.

Rasa is an open source framework for creating chatbot with natural language undertsanding. There are few important files of rasa project -

✪ domain.yml
This file contain information about intent and respective actions. For instance- basis on intent of a user, appropriate action gets triggered and response is sent back to user. '-utter' is plain text without any logic behind it, however we can create custom action which we will discuss further in the blog.
- greet
- goodbye
- affirm

- utter_greet
- utter_cheer_up
- utter_did_that_help

- text: Hey! How are you?
- text: 'Great, carry on!'
- text: Did that help you?

✪ endpoints.yml
Custom action can be triggered by exposing it on some URL which you define in this file. One such example of action endpoint is shown here. This file also contains information about connecting to channels like facebook

url: "http://localhost:5055/webhook"

✪ config.yml
This file contains information about nlu and core models.

✪ credentials.yml
Here details about connecting to other services is defined. For instance - slack, facebook and so on. For exposing chatbot as API, we have to uncomment 'rest' based settings. Read the previous blog to know more about how to expose chatbot as API and integrate it with website.

This file is used for defining user stories. One can define happy path or sad and link the appropriate action which needes to be triggered. We can define our own stories as well in this file.
## happy path
* greet
 - utter_greet
* mood_great
 - utter_happy

## sad path 1
* greet
 - utter_greet
* mood_unhappy
 - utter_cheer_up
 - utter_did_that_help
* affirm
 - utter_happy

## sad path 2
* greet
 - utter_greet
* mood_unhappy
 - utter_cheer_up
 - utter_did_that_help
* deny
 - utter_goodbye

This file help to train your bot. If any response is incorrectly tagged, you can put it in right intent and retrain the model by using > rasa train command.
## intent:greet
- hey
- hello
- hi
- good morning
- good evening
- hey there

## intent:goodbye
- bye
- goodbye
- see you around
- see you later
- i love you

## intent:affirm
- yes
- indeed
- of course
- that sounds good
- correct

Custom action is defined in this file. You can put the logic to decide what response should be returned. Infact, you can call an API in this file, perform action and return appropriate response.
from typing import Any, Text, Dict, List

#import the rasa dependencies
from rasa_sdk import Action, Tracker
from rasa_sdk.executor import CollectingDispatcher

class ActionFetchForm(Action):
def name(self) -> Text:
return "action_fetch_form"

Flow of chatbot messages and model training

If you are comfortable using commands, you can open the file on local machin, make the modifications, retrain the model and test it using CLI. If thats not the case, Rasa X library can make your life easy by providing a nice user interface.

How to install Rasa X?
1. Goto rasa_project directory
    > pip install rasa-x --extra-index-url
2. Once installed, run this command -
    > rasa x
It will open a nice website on local browser, see screenshot -
You can modify all required files(described above) and train the model as per your requirement using Rasa X user interface.

Hope the above blog helped you understande Rasa ecosystem and easy way to train the model. 


Popular posts from this blog

Could not load file or assembly 'Microsoft.Web.Infrastructure'

Could not load file or assembly 'Microsoft.Web.Infrastructure, Version=, Culture=neutral, PublicKeyToken=31bf3856ad364e35' or one of its dependencies. The system cannot find the file specified. What 'Micorosoft.Web.Infrastructure' does? This dll lets HTTP modules register at run time. Solution to above problem: Copy 'Micorosoft.Web.Infrastructure' dll in bin folder of your project and this problem should be resolved. If you have .Net framework installed on machine, this dll should be present on it. You can search for this dll and copy it in your active project folder.   Alternatively,  you can install this dll using nuget package manager PM> Install-Package Microsoft.Web.Infrastructure -Version 1.0.0 Happy coding!!

Create chatbot in 20 minutes using RASA

This blog will help you create a working chatbot with in 20 minutes. For creating chatbot we need following libraries to be installed- >> Python3 >> Pip3 >> Rasa Lets start installing all libraries & dependencies which are need for creating chatbot. Note: I have used MAC, therefore sharing commands related to it. You can install it on Windows, Linux or any other operating system using respective commands. 1. Install Python3 > brew install python3 > python --version #make sure you have python3 installed 2. Install Pip3 > curl -O > sudo python3 If you get issue related to Frameoworks while installing pip, follow below steps -  > cd /usr/local/lib > mkdir Frameworks > sudo chown -R $(whoami) $(brew --prefix)/* Once installed check pip3 version > pip3 --version After python3 and pip3 is succeffully installed, proceed to next steps. 3. Install Rasa > pip

Running dotnet on Linux

Server: Linux, version SUSE 12 To run dotnet code on Linux, the first and foremost task is to "Install Mono package on linux". Note: Mono is an open implementation of Microsoft's .Net framework, including compilers. It uses the same development libraries on Linux which are being used on Windows. Therefore, if you code and compiled some mono code on Linux,  it will work for Windows as well.       zypper is a package installation tool which is used in this scenario. If zypper is not available, check which package manager tool is installed on server. Furthermore, to verify if zypper is installed or not, type zypper on command line which will show all options if zypper is available on server else it will show 'command not found'. zypper ar -r The above command will download from mentioned URL in a new repository. Here 'ar' stands for 'add repo'. After adding it to repos