I’m having trouble with rasa in a couple of ways. I’ve been trying to figure out why it is not following the paths I’ve set for it. But running rasa interactive, it seems to have invented its own action that it wants to run a lot. Any suggestions would be appreciated. @akelad?
? The bot wants to run '...', correct? (Y/n) n
? What is the next action of the bot? (Use arrow keys)
» <create new action>
0.00 ...
0.00 action_add_to_reflection
0.00 action_back
0.00 action_check_analysis
0.00 action_deactivate_loop
0.00 action_default_ask_affirmation
0.00 action_default_ask_rephrase
0.00 action_default_fallback
0.00 action_email_post
0.00 action_get_calendar
0.00 action_get_date
0.00 action_get_reflection
0.00 action_listen
0.00 action_look_up
0.00 action_process_reflections
There is no action called “…” defined in the domain.
here are the action defined in the domain
actions:
- action_add_to_reflection
- action_check_analysis
- action_default_fallback
- action_email_post
- action_get_calendar
- action_get_date
- action_get_reflection
- action_look_up
- action_process_reflections
- action_purge_done
- action_r_reflection
- action_reflection_continue
- action_reset_reflection_form
- action_session_start
- action_show_outstanding_reflections
- action_start_outstanding_reflection
- action_wait
- utter_anything_else
- utter_articleanalysis
- utter_ask_email_form_email
- utter_greet
- utter_reflection_submit
- utter_submit_as_is
- utter_wait_continue
- validate_email_form
- validate_reflection_form
In case its important here’s the configuration file:
language: en
pipeline:
- 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
model_confidence: linear_norm
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
constrain_similarities: true
model_confidence: linear_norm
- name: FallbackClassifier
threshold: 0.19
ambiguity_threshold: 0.1
- name: RegexEntityExtractor
case_sensitive: false
use_lookup_tables: true
use_regexes: true
use_word_boundaries: true
policies:
- name: RulePolicy
core_fallback_threshold: 0.1
core_fallback_action_name: action_default_fallback
enable_fallback_prediction: false
restrict_rules: true
check_for_contradictions: true