What did I do wrong with lookup tables?

Rasa Open Source
1

domain.yml:

entities:
    - cars

nlu.yml:

- intent: what_car
  examples: |
      - Do you know [Ford](car)
      - Did you see [Honda](car)?
      - Find me please[Hyundai](car)

- lookup: car
  examples: |
    - Ford
    - Honda
    - Hyundai
    - Kia
    - Mazda
    - Mercedes Benz
    - Nissan
    - Opel

stories.yml:

- story: find car
  steps:
  - intent: greet
  - action: utter_greet
  - intent: what_car
    entities:
    - color: "Ford"
  - action: action_car

I am able to find those first 3 cars but not more, and sometimes my “Mercedes Benz” is detected as “Mercedes”. I want to have only few elements and those will be static, I do not want my rasa to learn anything new, just find those examples and know if I will write “Mercedes Benz” that those are 2 words

2

I found that my main problem whas wrong config.yml

this is my config.yml when my lookup tables are working:

pipeline:
    - name: WhitespaceTokenizer
    - name: RegexFeaturizer
    - name: RegexEntityExtractor
    - 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: FallbackClassifier
      threshold: 0.7
      ambiguity_threshold: 0.1

policies:

I still have problemst with txt but when I have them in my nlu.yml they are working:

- intent: zamówienie
  examples: |
      - What color do you know [green](color)
      - What color do you like [green](color)
      - Do you know [green](color), it is my favorite color!

- lookup: Restaurant
  examples: |
    - green
    - red
    - purple
    - yellow
    - black
    - white
    - grey
    - orange
    - pink