Hi,
I started to test different NLU pipelines to figure out the best for the use case. When I just test one configuration, the test runs to completion. But when I test multiple configuration, it throws the below error
NLG responses not found during NLU pipeline comparison
Test command
rasa test nlu --nlu data/nlu.md --config config #config folder contains all different configurations
Python version: 3.7.4 Rasa version: 1.10.16
config.yml
language: en
pipeline:
- name: ConveRTTokenizer
- name: RegexFeaturizer
- name: ConveRTFeaturizer
- name: CRFEntityExtractor
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
- name: CountVectorsFeaturizer
analyzer: "char_wb"
min_ngram: 1
max_ngram: 4
- name: DIETClassifier
batch_strategy: sequence
epochs: 100
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
retrieval_intent: chitchat
policies:
- name: AugmentedMemoizationPolicy
- name: TEDPolicy
max_history: 8
epochs: 100
- name: MappingPolicy
- name: FormPolicy
- name: FallbackPolicy
nlu_threshold: 0.3
fallback_action_name: 'action_default_fallback'
Could someone help me to find where I am going wrong? Thanks in advance