@Baval in this blog it’s not describing how to train a model in custom component. He makes his is trained = False., I have implemented a custom component of sentiment analyzer, but I am confused that in which category I should mentioned it like in Tokenizer or classifier where should I put this component in config.yml pipeline.
Use
replace your training_data to training_data.intent_examples
with open(‘labels.txt’, ‘r’) as f: labels = f.read().splitlines() texts = [e.get(TEXT) for e in training_data.intent_examples if e.get(TEXT)]
Is your custom component build in Rasa 3.0? If so, can you share your sentiment analyzer?
Yeah I have build custom component in Rasa 3.0 only
visit this link for more help.