Hi, I would like to install spacy in production in order to use the spacyNLUTokenizer. However as we are alreay in production using Rasa X and the Quick install docker compose here.
Here is how my config.yml looks like. However it raises an error during training due to the fact that spacy is not installed.
language: "fr" # your two-letter language code
pipeline:
- name: SpacyNLP
- name: SpacyTokenizer
- name: SpacyFeaturizer
- name: RegexFeaturizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
- name: CountVectorsFeaturizer
analyzer: "char_wb"
min_ngram: 1
max_ngram: 4
- name: DIETClassifier
epochs: 100
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
policies:
- name: TEDPolicy
max_history: 10
epochs: 20
batch_size:
- 32
- 64
- max_history: 6
name: AugmentedMemoizationPolicy
- name: TwoStageFallbackPolicy
core_threshold: 0.1
nlu_threshold: 0.3
fallback_nlu_action_name: action_default_ask_affirmation
fallback_core_action_name: action_default_fallback
- name: FormPolicy
- name: MappingPolicy
- name: MemoizationPolicy
Thanks in advance for any help.
Sincerely.