Case insensitive search and chatbot not recognizing the coding language not mentioned in nlu.yaml examples

Rasa Open Source
1

I have written the nlu,stories,domain.yaml file to find the number of students working in python,whose data need to be extracted after connecting to mongodb

nlu.yaml

version: "3.1"

nlu:

- intent: get_employee_count
  examples: |
    - How many employees know [Python](skill)?
    - How many employees are skilled in [Java](skill)?
    - How many employees are working in [Ruby](skill)?
    - How many employees are proficient in [C++](skill)?
    - How many employees have experience in [JavaScript](skill)?
    - How many employees are there with [Go](skill) skills?
    - How many employees know [Swift](skill)?
    - How many employees are skilled in [PHP](skill)?
    - How many employees are proficient in [Perl](skill)?
    - How many employees have experience in [Kotlin](skill)?
    - How many employees are there with [Scala](skill) skills?

stories.yaml

version: "3.1"

stories:





- story: get employee count
  steps:
    - intent: get_employee_count
    - action: action_get_employee_count

domIN.yaml

version: "3.1"

intents:
  - change_my_manager
 

entities:
  - skill

actions:
  - action_get_employee_count
session_config:
  session_expiration_time: 60
  carry_over_slots_to_new_session: true

Issues i am facing: In spite of keeping WhitespaceTokenizer case_sensitive as False.I am not able to carry on case_insensitive search. for example: if i ask employees working in python ,it returns only 1 employee inspite of having 2 employees working in python bcos of case sensitive search.below is config.yaml config.yaml

- name: WhitespaceTokenizer
     case_sensitive: False
   - name: RegexFeaturizer
     "case_sensitive": False
   - 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

2.inspite of training with many examples in nlu.yml,when iask how many are trained in C,i dont get the entity extracted as C language not mentioned in examples of nlu.yaml

How do i solve these?