Custom Channel Example for Rasa Core 0.12.3

(Stacybot123) #1


Can someone please provide an example of custom input channel on rasa core “version”: “0.12.3”. Below is the code I am using , but getting error as

agent.handle_channels(InputChannel(5004, “/chat”, input_channel)) TypeError: object() takes no parameters

Here is my

from __future__ import print_function
from __future__ import unicode_literals

import logging

from rasa_core.channels import InputChannel
from rasa_core import utils
from rasa_core.agent import Agent
from rasa_core.interpreter import RasaNLUInterpreter
from import UserMessage
from import CollectingOutputChannel
from rasa_core.utils import EndpointConfig
from flask import Blueprint, request, jsonify

logger = logging.getLogger(__name__)

class SimpleWebBot(InputChannel):

    def blueprint(self, on_new_message):
        custom_webhook = Blueprint('custom_webhook', __name__)

        @custom_webhook.route("/", methods=['GET'])
        def health():
            return jsonify({"status": "ok"})

        @custom_webhook.route("/webhook", methods=['POST'])
        def receive():
            payload = request.json
            sender_id = payload.get("sender", None)
            text = payload.get("message", None)
            out = CollectingOutputChannel()
            on_new_message(UserMessage(text, out, sender_id))
            responses = [m for _, m in out.messages]
            return jsonify(responses)

        return custom_webhook
def run(serve_forever=True):
    interpreter = RasaNLUInterpreter("projects/default/mybotnlu")
    action_endpoint = EndpointConfig(url="http://localhost:5055/webhook")
    agent = Agent.load("projects/dialogue", interpreter=interpreter , action_endpoint=action_endpoint)
    input_channel = SimpleWebBot()
    if serve_forever:
      agent.handle_channels(InputChannel(5004, "/chat", input_channel))
    return agent

if __name__ == '__main__':
(JG) #2

hey @stacybot123 let me suggest you how to connect your rasa bot with custom channel :

  1. Create credentials.yml and add the contents to the file as mentioned here : Chat & Voice platforms

  2. run your rasa core server using the below command :

python -m -d models/dialogue -u models/nlu/current --port 5002 --credentials credentials.yml

3.then you can connect your bot to your custom channel using the below api :


hope it helps :sweat_smile::smiley:

(Stacybot123) #3

@JiteshGaikwad Thanks! it worked , but as soon as I closes the terminal the command python -m -d models/dialogue -u models/nlu/current --port 5002 --credentials credentials.yml

terminates. I was trying to run the server without keep open the terminal . Is there a way/example I attach this to a flask app


(SSS) #4

Hi @JiteshGaikwad, Can you please little elaborate, because I am not getting anything in the output?

(Rohit Nair) #5

Hey, I think what you’re trying to do is keeping the process alive even after quitting the terminal? If so, check out screen, which does exactly that for you.

(王旭峰(Xufeng Wang)) #6

Hello, can you show me your credential.yml file? Thank you, @stacybot123