I need to extract any text like Dialogflow @sys.any entity. In RASA how can I extract any text from intent?
Hi, your question is not that clear for me. For an address entity, I would use an entity extractor that can already handle this (probably Spacy?). You could also use the existing entity extractors in Rasa and train them with your examples (like any other entity you want to extract).
If you are sure that the user will provide the complete address, you can solve this issue with slot mapping. You define a mapping “from_text” (Domain). It will store your user’s utterance (e.g. via inform intent) in the specified slot. From there, you can use it in actions.
Rasa can be trained to detect the intent of an utterance, but it can also detect entities within an utterance. An entity can be any important detail that your assistant could use later in a conversation. This includes: Then we’d like to detect Sydney as an entity of type “destination” with a value of “Sydney.”.
- As open-source framework, Rasa NLU puts a special focus on full customizability. As result Rasa NLU provides you with several entity recognition components, which are able to target your custom requirements: The spaCy library offers pretrained entity extractors. As with the word embeddings, only certain languages are supported.