sandeep2213
December 11, 2020, 4:31pm
1
My bot is always falling back after I started including forms. Can any one help me solving that.
I tried removing the extended code but still did not work. I changed to AugemntedMemoization Policy that also did not work. Can any one help me???
check the screen shots:
This is what I am getting
This is I want
when i tried to change the threshold the this error came up:
InvalidConfigException: The pipeline configuration contains errors. The component ‘FallbackClassifier’ requires ‘IntentClassifier’ to be placed before it in the pipeline. Please add the required components to the pipeline.
please check my thread at github.com for RASAHQ:
opened 02:20AM - 12 Dec 20 UTC
closed 03:38PM - 27 Jan 21 UTC
type:bug
area:rasa-oss
<!-- THIS INFORMATION IS MANDATORY - YOUR ISSUE WILL BE CLOSED IF IT IS MISSING.… If you don't know your Rasa version, use `rasa --version`.
Please format any code or console output with three ticks ``` above and below.
If you are asking a usage question (e.g. "How do I do xyz") please post your question on https://forum.rasa.com instead -->
**Rasa version**: 2.1.3
**Rasa SDK version** (if used & relevant):
**Rasa X version** (if used & relevant):
**Python version**: 3.7.9
**Operating system** (windows, osx, ...): WIN 10
**Issue**:
I didn't why my rasa bot always fall back. Intent classification is good but the replying ones is not correct
**Error (including full traceback)**:
```
This is what I am getting
This was earlier screenshot when it is working fine
```
**Command or request that led to error**:
```
```
**Content of configuration file (config.yml)** (if relevant):
```yml
# Configuration for Rasa NLU.
# https://rasa.com/docs/rasa/nlu/components/
language: en
pipeline:
# # No configuration for the NLU pipeline was provided. The following default pipeline was used to train your model.
# # If you'd like to customize it, uncomment and adjust the pipeline.
# # See https://rasa.com/docs/rasa/tuning-your-model for more information.
# - name: WhitespaceTokenizer
# - name: RegexFeaturizer
# - name: LexicalSyntacticFeaturizer
# - name: CountVectorsFeaturizer
# - name: CountVectorsFeaturizer
# analyzer: char_wb
# min_ngram: 1
# max_ngram: 4
# - name: DIETClassifier
# epochs: 100
# - name: EntitySynonymMapper
# - name: ResponseSelector
# epochs: 100
# - name: FallbackClassifier
# threshold: 0.3
# ambiguity_threshold: 0.1
# Configuration for Rasa Core.
# https://rasa.com/docs/rasa/core/policies/
policies:
# # No configuration for policies was provided. The following default policies were used to train your model.
# # If you'd like to customize them, uncomment and adjust the policies.
# # See https://rasa.com/docs/rasa/policies for more information.
- name: MemoizationPolicy
# - name: TEDPolicy
# max_history: 5
# epochs: 100
- name: RulePolicy
```
**Content of domain file (domain.yml)** (if relevant):
```yml
session_config:
session_expiration_time: 60
carry_over_slots_to_new_session: true
intents:
- greet
- what_is_supported
- eligibility_criteria
- goodbye
- bot_challenge
- how_to_apply_supported
- fetch_can
entities:
- supported
- can_number
- email
- mobile
- name
slots:
can_number:
type: text
influence_conversation: false
email:
type: text
influence_conversation: false
mobile:
type: text
influence_conversation: false
name:
type: text
influence_conversation: false
supported:
type: text
influence_conversation: false
responses:
utter_greet:
- text: Hey! How are you?
utter_ask_can_number:
- text: Enter can bro
utter_default:
- text: Falled back
actions:
- action_what_is_supported
- action_eligibility
- action_ask_can_number
- action_ask_name
- action_ask_mobile
- action_ask_email
- action_apply_supported
- action_fetch_can
- form_fetch_can
forms:
form_fetch_can:
can_number:
- type: from_text
email:
- type: from_text
mobile:
- type: from_text
name:
- type: from_text
```
```stories
version: "2.0"
stories:
- story: stories for what is supported
steps:
- intent: what_is_supported
- action: action_what_is_supported
- story: story for eligibility criteria
steps:
- intent: eligibility_criteria
- action: action_eligibility
- story: story for applying
steps:
- intent: how_to_apply_supported
- action: action_apply_supported
- story: fetching can
steps:
- intent: fetch_can
- action: utter_ask_can_number
- action: form_fetch_can
- active_loop: form_fetch_can
```
debug message:
Your input -> what is income certificate
2020-12-12 09:21:56 DEBUG rasa.core.lock_store - Issuing ticket for conversation 'fd95b907d632406e860e44b1d917e1dd'.
2020-12-12 09:21:56 DEBUG rasa.core.lock_store - Acquiring lock for conversation 'fd95b907d632406e860e44b1d917e1dd'.
2020-12-12 09:21:56 DEBUG rasa.core.lock_store - Acquired lock for conversation 'fd95b907d632406e860e44b1d917e1dd'.
2020-12-12 09:21:56 DEBUG rasa.core.tracker_store - Could not find tracker for conversation ID 'fd95b907d632406e860e44b1d917e1dd'.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Starting a new session for conversation ID 'fd95b907d632406e860e44b1d917e1dd'.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Policy prediction ended with events '[]'.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Action 'action_session_start' ended with events '[<rasa.shared.core.events.SessionStarted object at 0x000001B49DBF6DC8>, <rasa.shared.core.events.ActionExecuted object at 0x000001B359AEB608>]'.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Current slot values:
can_number: None
email: None
mobile: None
name: None
supported: None
requested_slot: None
2020-12-12 09:21:56 DEBUG rasa.nlu.classifiers.diet_classifier - There is no trained model for 'ResponseSelector': The component is either not trained or didn't receive enough training data.
2020-12-12 09:21:56 DEBUG rasa.nlu.selectors.response_selector - Adding following selector key to message property: default
2020-12-12 09:21:56 DEBUG rasa.core.processor - Received user message 'what is income certificate' with intent '{'id': -7096267651852178878, 'name': 'what_is_supported', 'confidence': 0.9999905824661255}' and entities '[{'entity': 'supported', 'start': 8, 'end': 14, 'confidence_entity': 0.9511626958847046, 'value': 'income', 'extractor': 'DIETClassifier'}]'
2020-12-12 09:21:56 DEBUG rasa.core.processor - Current slot values:
can_number: None
email: None
mobile: None
name: None
supported: income
requested_slot: None
2020-12-12 09:21:56 DEBUG rasa.core.processor - Logged UserUtterance - tracker now has 5 events.
2020-12-12 09:21:56 DEBUG rasa.core.policies.memoization - Current tracker state:
[state 1] user intent: what_is_supported | user entities: ('supported',) | previous action name: action_listen
2020-12-12 09:21:56 DEBUG rasa.core.policies.memoization - There is no memorised next action
2020-12-12 09:21:56 DEBUG rasa.core.policies.rule_policy - Current tracker state:
[state 1] user intent: what_is_supported | user entities: ('supported',) | previous action name: action_listen
2020-12-12 09:21:56 DEBUG rasa.core.policies.rule_policy - There is no applicable rule.
2020-12-12 09:21:56 DEBUG rasa.core.policies.ensemble - Predicted next action using policy_1_RulePolicy.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Predicted next action 'action_default_fallback' with confidence 0.30.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Policy prediction ended with events '[]'.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Action 'action_default_fallback' ended with events '[BotUttered('Falled back', {"elements": null, "quick_replies": null, "buttons": null, "attachment": null, "image": null, "custom": null}, {"template_name": "utter_default"}, 1607745116.4180608), <rasa.shared.core.events.UserUtteranceReverted object at 0x000001B345C6EB48>]'.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Current slot values:
can_number: None
email: None
mobile: None
name: None
supported: None
requested_slot: None
2020-12-12 09:21:56 DEBUG rasa.core.processor - Predicted next action 'action_listen' with confidence 1.00.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Policy prediction ended with events '[]'.
2020-12-12 09:21:56 DEBUG rasa.core.processor - Action 'action_listen' ended with events '[]'.
2020-12-12 09:21:56 DEBUG rasa.core.lock_store - Deleted lock for conversation 'fd95b907d632406e860e44b1d917e1dd'.
Please help me asap I'm in a hurry
vanshkapil
December 12, 2020, 6:44am
2
Did you include form rule in rules.yml (or stories) ?
sandeep2213
December 12, 2020, 6:56am
3
vanshkapil:
o
Yes I included in stories
Any updates on this? I am facing the same issue. when i tried
rasa shell nlu
and gave the inputs, it is classifying properly. But when I run it with
rasa shell
it always prints out the fallback response. I am new to Rasa, I would appreciate the help
