Everything was working fine when my pipeline was: language: en pipeline: supervised_embeddings Since I wanted to use lookup tables, I changed it to: language: en pipeline: - name: "SpacyNLP" model: "en_core_web_md" - name: "SpacyTokenizer" - name: "RegexFeaturizer" - name: "CRFEntityExtractor" features: [ ["low", "title", "upper"], ["bias", "low", "prefix5", "prefix2", "suffix5", "suffix3", "suffix2", "upper", "title", "digit", "pattern"], ["low", "title", "upper"] ] Now, no intent is being recognized. What’s happening? Thank you

You forgot to add a component to detect the intent like SklearnIntentClassifier, among others, check the documentation .

Pipeline change - not recognizing intents anymore

teresalazar13 (Teresa Salazar) October 9, 2019, 4:00pm 3

Topic		Replies	Views
RASA Spacy sklearn pipe line Rasa Open Source	2	1532	September 9, 2018
How should be pipeline on New Version [Deprecated] Rasa X Community Edition	4	1128	May 27, 2019
RASA NLU pretrained embeddings not detecting intent even if the input is straight forward Rasa Open Source	8	993	September 23, 2019
How to confirm lookup table is being used Rasa Open Source	1	547	March 15, 2019
Look up tables are not working on unseen data samples Rasa Open Source	2	606	May 27, 2019