Web integration of bot

(Abhishak Varshney) #1

Hi guys, I want to deploy my chatbot on the website using REST channels using RESTInput and Chatroom. I am able to create bot server but during the conversation, it is not giving any response maybe models are not connected with it properly. Do anyone know how to resolve this issue.


(Akela Drissner) #2

Please provide some more details on what exactly you’re running, and what the logs look like when you’re running it. In any case, I don’t think that UI is compatible with rasa_core 0.11 yet

(Abhishak Varshney) #3


(Satish Kumar) #4

I’m also try to integrate with web can you tell the steps about how would you do that.

(Abhishak Varshney) #5

Everything is available in documentation Chat & Voice platforms However If you need any help regarding that just ping me here. I will be glad to help you.

(Satish Kumar) #6

I’m new to this platform i created one chatbot now i want to know how to connect the chat bot to the rasa-webchat widget can you explain how to connect. I’m already read the document but i can’t understand clearly.

(e8180kimo) #7

Hi, I just run into the issue when I wanted to deploy my bot using RestInput and Chatroom. I’m using Rasa core Master version.

I followed the steps (Usage with a standard Rasa Core project) in Chatroom, but when I run python -m rasa_utils.bot -d models/dialogue -u models/current/nlu

The terminal returns:

Traceback (most recent call last):
  File "/Users/wisionlearning/anaconda3/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/Users/wisionlearning/anaconda3/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/Users/wisionlearning/Documents/dd0926/rasa_utils/bot.py", line 21, in <module>
    from rasa_core.channels import (
ImportError: cannot import name 'RestInput'

I also followed the steps on chat & voice platform RestChannel:

I made a credentials.yml as same as it should be. Then I run python -m rasa_core.run -d models/dialogue -u models/current/nlu/
–port 5002 --credentials credentials.yml

I got:

Using TensorFlow backend.
Traceback (most recent call last):
  File "/Users/wisionlearning/anaconda3/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/Users/wisionlearning/anaconda3/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/Users/wisionlearning/rasa_core/rasa_core/run.py", line 234, in <module>
  File "/Users/wisionlearning/rasa_core/rasa_core/run.py", line 203, in main
  File "/Users/wisionlearning/rasa_core/rasa_core/agent.py", line 81, in load
    ensemble = PolicyEnsemble.load(path)
  File "/Users/wisionlearning/rasa_core/rasa_core/policies/ensemble.py", line 198, in load
    policy = policy_cls.load(policy_path)
  File "/Users/wisionlearning/rasa_core/rasa_core/policies/keras_policy.py", line 264, in load
    model_arch = cls._load_model_arch(path, meta)
  File "/Users/wisionlearning/rasa_core/rasa_core/policies/keras_policy.py", line 240, in _load_model_arch
    arch_file = os.path.join(path, meta["arch"])
KeyError: 'arch'

I did not do the basic usage from chatroom though, because I saw the step below that is for rasa core project. Do I also need to make a webpage for that as well? Thanks for the help.

(Nilesh mandge) #8

Hi abhishek,

I am trying to connect rasa chat bot with my personal website but some how i am not able to do that, can you please help with it, I also tried custom channel but it showing me URL not found error on browser window

(Abhishak Varshney) #9

You can use Chatroom or Rasa Socket.io based application described in rasa_core docs.

(SSS) #10

Hi @abhishakskilrock, Can you please provide some details, how you used it and how to implement action server?