even after adding our new data in the original files but after running rasa shell it is not showing and recognising the updated intents and the relevant responses. But rasa train and all other commands are running fine and resolved all the error. Please suggest what to do next
Hi @Aneri, can you share your config file?
The config recipe.
Model Configuration
recipe: default.v1
Configuration for 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 Tuning Your NLU 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
constrain_similarities: true
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
constrain_similarities: true
- name: FallbackClassifier
threshold: 0.3
ambiguity_threshold: 0.1
Configuration for 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 Policies for more information.
- name: MemoizationPolicy
- name: RulePolicy
- name: UnexpecTEDIntentPolicy
max_history: 5
epochs: 100
- name: TEDPolicy
max_history: 5
epochs: 100
constrain_similarities: true[quote=“Aneri, post:3, topic:57540, full:true”]
The config recipe.
Model Configuration
recipe: default.v1
Configuration for 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 Tuning Your NLU 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
constrain_similarities: true
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
constrain_similarities: true
- name: FallbackClassifier
threshold: 0.3
ambiguity_threshold: 0.1
Configuration for 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 Policies for more information.
- name: MemoizationPolicy
- name: RulePolicy
- name: UnexpecTEDIntentPolicy
max_history: 5
epochs: 100
- name: TEDPolicy
max_history: 5
epochs: 100
constrain_similarities: true
[/quote]
strong text
Currently, I am using google collab to implement rasa version 3.3.3 but still facing the issues above. I am not able to identify whether the model is actually trained or not as it says the model is trained but still it is not giving responses to the new intents added to the original file. Could anyone pls suggest what should be performed in order to resolve this.