Rasa agent loading with rasa core

[AnikaTabassum]

Hi, I’m using rasa for a while now. I have deployed a chatbot and now I want to track conversation WITHOUT using rasa X, it is a requirement. So far I know I need to use my nlu model as nlu interpreter and to load rasa core agent I need to load the rasa core model. Correct me if I’m wrong. I need your assistance to know the proper way of loading an agent because this is my code: ** message=“hi” interpreter = NaturalLanguageInterpreter.create(’/home/anika/Desktop/RasaHost-master/src/RasaHost/sample/models/aas/nlu-20200319-120407/nlu’) endpoint = EndpointConfig(‘http://localhost:5055/webhook’) agent = Agent.load(’/home/anika/Desktop/RasaHost-master/src/RasaHost/sample/models/core-20200319-114712.tar.gz’, interpreter=interpreter, action_endpoint = endpoint) loop = asyncio.new_event_loop() asyncio.set_event_loop(loop) data = loop.run_until_complete(agent.handle_text(message))** this is my traceback:

File “/home/anika/Desktop/RasaHost-master/src/RasaHost/RasaHost/controllers/rasa_controller.py”, line 28, in rasa_respond ** output = ConversationsService().handle_text(message, sender_id=sender_id)**

** File “/home/anika/Desktop/RasaHost-master/src/RasaHost/RasaHost/services/conversations_service.py”, line 104, in handle_text** ** agent = Agent.load(’/home/anika/Desktop/RasaHost-master/src/RasaHost/sample/models/core-20200319-114712.tar.gz’, interpreter=interpreter, action_endpoint = endpoint)**

** File “/home/anika/Documents/environments/colourbot/lib/python3.6/site-packages/rasa/core/agent.py”, line 410, in load** ** path_to_model_archive=path_to_model_archive,**

** File “/home/anika/Documents/environments/colourbot/lib/python3.6/site-packages/rasa/core/agent.py”, line 318, in init** ** self.interpreter = NaturalLanguageInterpreter.create(interpreter)**

** File “/home/anika/Documents/environments/colourbot/lib/python3.6/site-packages/rasa/core/interpreter.py”, line 62, in create** ** return _create_from_endpoint_config(obj)**

** File “/home/anika/Documents/environments/colourbot/lib/python3.6/site-packages/rasa/core/interpreter.py”, line 305, in _create_from_endpoint_config** ** elif endpoint_config.type is None or endpoint_config.type.lower() == “http”:**

AttributeError: ‘RasaNLUInterpreter’ object has no attribute 'type’

[AnikaTabassum]

the issue got solved here.

Load Agent in Notebook is not working

Trying to get TeachingDataScience/rasa_nlu_exercise_TBD.ipynb at master · yogeshhk/TeachingDataScience · GitHub running with recent Rasa 1.0 (not rasa x) In notebook rasa agent had to be loaded with “await”. But then, at the usage time, it errors out Your bot is ready to talk! Type your messages here or send 'stop' Hi --------------------------------------------------------------------------- TypeError Traceback (most recent call last) <ipython-input-4-8da8be804…

[sharad_p (sharad)]

i also got the same error can you please help me. i did not understand what you wrote in second post.

[AnikaTabassum]

I just worked how the post says. And it worked

[sharad_p (sharad)]

@AnikaTabassum

NaturalLanguageInterpreter.create(’/home/anika/Desktop/RasaHost-master/src/RasaHost/sample/models/aas/nlu-20200319-120407/nlu’)

from rasa_core.channels.channel import RestInput from rasa_core.channels.facebook import FacebookInput from rasa_core.agent import Agent from rasa_core.interpreter import RegexInterpreter from rasa_core.interpreter import RasaNLUInterpreter from rasa_core.channels.slack import SlackInput from rasa_core.utils import EndpointConfig

#load your agent

nlu_interpreter = RasaNLUInterpreter(‘models/nlu/current’) action_endpoint = EndpointConfig(url=“http://localhost:5055/webhook”) agent = Agent.load(“models/20200325-120411.tar.gz”, interpreter=nlu_interpreter, action_endpoint = action_endpoint)

input_channel = SlackInput( ‘’, #slack_dev_token ‘’, #slack_client_token ‘’, #verification_token for interactive messages, events True)

agent.handle_channel(RestInput(5004, “/”, input_channel))

This is my code