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?
Asked
Active
Viewed 3,418 times
3

jainmiah shaik
- 31
- 1
- 2
-
This link might be helpful: [Rasa deployment](https://rasa.com/docs/rasa-x/enterprise/deployment-environments/) – Sociopath Mar 18 '20 at 05:39
-
@Sociopath as a beginner I'm not getting those exactly, can you simply the way how it should fix the problem? – jainmiah shaik Mar 18 '20 at 05:48
-
If you have core and nlu separate then you need to upgrade soon. After >= v1.0, core and NLU server have been merged. Check this out on how to use rest APIs to create your own UI for your website: https://rasa.com/docs/rasa/user-guide/connectors/your-own-website/#id2 – lahsuk Mar 18 '20 at 12:27
-
@jainmiahshaik did you find a solution? there's no tutorial or good documentation for deployment on a live website using rasa-nlu – Dids Jun 15 '21 at 16:15
2 Answers
1
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.

Melinda
- 747
- 5
- 13
0
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

Aziz ullah
- 99
- 1
- 8