Hello, I created a working knowledge base english bot based on the example on github and would like an assist how to configure my pipeline with spacy instead of supervised_embeddings. I don’t know if is possible. Anyone can help me with this? My current config is below: language: en pipeline: supervised_embeddings policies: name: MemoizationPolicy name: KerasPolicy name: MappingPolicy I tried with pipeline: pretrained_embeddings_spacy but my bot seems to not understand the user. I also get this error: \lib\site-packages\rasa\nlu\extractors\crf_entity_extractor.py:590: UserWarning: Number of features (1) for attribute ‘text_dense_features’ does not match number of tokens (6). Set ‘return_sequence’ to true in the corresponding featurizer in order to make use of the features in ‘CRFEntityExtractor’. f"Number of features ({len(features)}) for attribute "

@sterpapi did you create a custom policy? because in rasa docs there is 3 policies based on ML (TEDPolicy, Memoization Policy, Augmented Memoization Policy) and one rule based policy. so what is KerasPolicy and MappingPolicy?

Rasa Knowledge Base bot with spacy pipeline

Rasa Open Source

sterpapi (Ster Papi) February 22, 2020, 7:51pm 2

any help with this?

Topic		Replies	Views
SpacyNLP and supervised_embeddings in the same pipeline Rasa Open Source	0	462	May 21, 2019
spaCy pretrained models break chatbot NLU capacities Rasa Open Source	6	845	October 16, 2019
Need help in choosing the pipeline Rasa Open Source	4	680	September 16, 2019
Financial-demo bot following the course steps: Getting Started with Rasa	29	570	November 27, 2021
Which pipeline and poilicies to select Rasa Open Source	1	495	November 21, 2019

Rasa Knowledge Base bot with spacy pipeline

Related topics