All - Activity - taimoor-ahmed - Rasa Community Forum

Config File Errors

Hi, not so long ago I built a chatbot in RASA v.1.9.0 and it was working fine on my older system. I was trying to set it up on another system but failed to do so. When I run rasa train I get the following error: rasa.core.policies.ensemble.InvalidPolicyConfig: Module for policy 'MemoizationPolicy' …

Forms not working on failure

@saurabh-m523 I mistakenly did not copy the whole file:

from typing import Dict, Text, Any, List, Union, Optional
from datetime import datetime
from rasa_sdk import Tracker
from rasa_sdk.executor import CollectingDispatcher
from rasa_sdk.forms import FormAction
class EmergencyForm(FormAction):
    """Example of a custom form action"""
    def name(self) -> Text:
        """Unique identifier of the form"""
        return "emergency_form"

@staticmethod
    def required_slots(tracker: Tracker) -> List[Text]:
        """A list of required slots that the form has to fill"""
        re…

I was using the form to fill out different slots. The problem i am facing is that when an intent isn’t successfully recognized, the entity is not extracted and thus, the slot is not filled. I read in the docs that if a slot is not filled, the user asked to fill the slot again. For example, location …

Using Custom SpaCy model

They do not work for most times. Did you get them to work ?

@Talhag958 I didn’t end up using the SpaCy model for Urdu because I was unable to integrate it in RASA. Here is my config.yml file which I am using. Configuration for Rasa NLU.

language: ur
pipeline:
  - name: WhitespaceTokenizer
  - name: RegexFeaturizer
  - name: LexicalSyntacticFeaturizer

Yes, it’s still in development but I have developed a prototype. What do you need help with?

Pipeline for Urdu Language

Hi, I am building a chatbot in Urdu language. I wanted to know which pipeline would be the most suitable for such a language that does not have a SpaCy model? Thanks in advance.

Is it possible to be used in other languages?

Hi thank you for this. I’m building a chatbot in Urdu language. How do I check if Urdu is supported?

Hi @athenasaurav, can you share the pipeline from your config.yml.

Training data format for Urdu

I have training data in Urdu language and since Urdu is written from right-to-left. I am having trouble in labeling the entity names that are in English. For example.

intent: inform
چک شہزاد میں حادثہ ہوا ہے

I want the substring چک شہزاد to be labelled like this میں حادثہ ہوا ہے (location)

Entity Extraction In Urdu

I don’t think it overfits. I gave 20 examples for the entity location. Only those examples are correctly recognized and not new ones. Is there something that I might be doing wrong.

I am building a chatbot in Urdu language and I was working on my entity extraction. The problem that I have is that when an entity e.g. 'location' has a value in the training data, the slot is filled correctly. But when the entity value is not in the training set, I get the error: Failed to extract...

Integrating RASA server with Python app

Hi, I was trying to write a python script to communicate with my rasa chatbot. I am using requests library to send a post request. However, I do not know the url and the payload format. I ran the rasa server using the following command:

rasa run actions

Any help would be appreciated. Thanks in advance.

Domain File Configuration

I changed it to templates. Now, it is working fine. Should I update my rasa version? Thanks in advance.

I’m using RASA 1.1.6

Hello, @matthiask. I added the actions list as follows:

actions:
  - utter_greet
  - utter_ask_etype
  - utter_ask_people
  - utter_ask_location
  - utter_default
  - utter_confirmation
  - utter_slots_values

but when I run rasa shell and input greet, it throws me this error: ERROR rasa.core.actions.action - Couldn't…

Hello, I was following the formbot example to build my own chatbot. However, I get the following error when I run

rasa train
Error:
Cannot access action ‘utter_greet’, as that name is not a registered action for this domain. Available actions are: action_listen

Hi @mloubser thanks for helping me out. I’ve set these in the config file now but I have another issue regarding linking the model. The first command I ran was:

pip install dist/ur_model-0.0.0.tar.gz

Then, when I try to link the SpaCy model (ur-model-0.0.0.tar.gz) from terminal using the command ...

Hi, I was developing a chatbot in Urdu language and I wanted to know if there is an existing pipeline that I could use for Urdu language. Moreover, I found a custom SpaCy model, could that be used for training my chatbot? Thank you in advance.

Entity Extraction in Stories

@BrunoRoth95 thank you for your response. I’ll try to implement your solution and let you know if I got it right.

@hajoura thank you for your response. I tried slots but i don’t want to hardcode key-value pairs. I want the slot in tell_location regardless of the value.

The below example works fine but I do not want to define the value and fire utter_affirm_location.

tell_location {"location": "pakistan"}

I am new to Rasa NLU and I wanted to know how do we extract entities in stories regardless of their value. For example, I want to ask the user his location and then extract the entity "location" from their reply and pass it to a custom action/template.