Every time I run “rasa shell” , it runs as if I type “rasa shell nlu”

when I am

run shell

instead of starting the regular bot chat I am getting this

UserWarning: constrain_similarities is set to `False`. It is recommended to set it to `True` when using cross-entropy loss. It will be set to `True` by default, Rasa Open Source 3.0.0 onwards.
  category=UserWarning,
NLU model loaded. Type a message and press enter to parse it.
Next message:

Anyone can help

@Avi1 in config.yml file change the constrain_similarities: true and it just a warning, nothing serious, till the time chat conversation is not effected.

not sure where exactly?

version: "2.0"
language: en_core_web_md
pipeline:
  - name: WhitespaceTokenizer
  - name: RegexFeaturizer
  - name: LexicalSyntacticFeaturizer
  - name: CountVectorsFeaturizer
  - name: CountVectorsFeaturizer
    analyzer: "char_wb"
    min_ngram: 1
    max_ngram: 4
  - name: DIETClassifier
    epochs: 100
  - name: FallbackClassifier
    threshold: 0.7
  - name: DucklingEntityExtractor
    url: http://duckling.rasa.com:8000
    dimensions:
    - amount-of-money
    - time
    - number
  - name: EntitySynonymMapper
policies:
- name: AugmentedMemoizationPolicy
- name: TEDPolicy
  epochs: 40
- name: RulePolicy
  core_fallback_threshold: 0.4
  core_fallback_action_name: "action_default_fallback"
  enable_fallback_prediction: True

all i need is to have a regular bot and not

{
  "text": "f",
  "intent": {
    "name": "nlu_fallback",
    "confidence": 0.7
  },
  "entities": [],
  "intent_ranking": [
    {
      "name": "nlu_fallback",
      "confidence": 0.7
    },
    {
      "id": 7748421168436467797,
      "name": "affirm",
      "confidence": 0.24085870385169983
    },
    {
      "id": 4841344135390005071,
      "name": "thankyou",
      "confidence": 0.24049021303653717
    },
    {
      "id": -1730515636925318311,
      "name": "check_human",
      "confidence": 0.19560882449150085
    },
    {
      "id": -5576533850659942059,
      "name": "goodbye",
      "confidence": 0.14323635399341583
    },
    {
      "id": -8924127937850757928,
      "name": "help",
      "confidence": 0.10245376825332642
    },
    {
      "id": 2061313916548079614,
      "name": "deny",
      "confidence": 0.06273943930864334
    },
    {
      "id": -6045355792617815955,
      "name": "out_of_scope",
      "confidence": 0.0064697423949837685
    },
    {
      "id": -8187359604249169926,
      "name": "pay_cc",
      "confidence": 0.0030626873485744
    },
    {
      "id": 207121872864938887,
      "name": "search_transactions",
      "confidence": 0.0028173900209367275
    },
    {
      "id": 3159377704296179703,
      "name": "greet",
      "confidence": 0.002262921305373311
    }
  ]
}
Next message:

@Avi1 I’m sharing the demo config.yml file

# Configuration for Rasa NLU.
# https://rasa.com/docs/rasa/nlu/components/
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
    ranking_length: 5
    constrain_similarities: true
    model_confidence: linear_norm
  - name: EntitySynonymMapper
  - name: ResponseSelector
    epochs: 100
    constrain_similarities: true
    model_confidence: linear_norm

  # - name: DucklingHTTPExtractor
  #   url: http://localhost:9000
  #   dimensions:
  #   - question
  #   - answer
  #   timezone: UK/London
  #   timeout: 3

# Configuration for Rasa Core.
# https://rasa.com/docs/rasa/core/policies/
policies:
  - name: MemoizationPolicy
  - name: TEDPolicy
    max_history: 5
    epochs: 100
  - name: RulePolicy
    nlu_threshold: 0.4
    core_threshold: 0.4
    fallback_action_name: "action_default_fallback"

I don’t think it’s the warning he’s worries about - you can safely ignore it.

The problem is:

But @Avi1, try rasa shell instead of run shell.