All - Activity - nikamsau - Rasa Community Forum

ModuleNotFoundError: Cannot find class 'LexicalSyntacticFeaturizer' from global namespace

Hey @JiteshGaikwad, I’m facing the same issue. I’m using python 3.6 pip version: 20.1.1 yes I’m using anaconda rasa version : 1.9.4 Please do respond, asap

Tensorflow compatibility ISSUE

Which version of tensorflow is compatible with rasa 1.9.4 ??

ERROR in testing. ValueError : invalid end-to-end format for message greet

No I couldn’t solve it. Testing is failing in middle

ValueError: (‘Error in line 2: Encountered invalid end-to-end format for message greet. Please visit the documentation page on end-to-end testing at https://rasa.com/docs/rasa/user-guide/testing-your-assitant/#end-to-end-testing/’, “Invalid story file format. Failed to parse ‘/tmp/tmph0lsiph7/da1298…

How to get the value of previous slot in current form action?

Ok, got it. Thanks a lot for clarifying the concepts.

okay. So basically you want to say that I need to use 2 slots here and it won’t work with single slot, right? And in general how to do the contextual training? Like do we need to use forms every time or use different slots and then maintain the context ?

Slot gets first set when user asks for version. 1st time slot is filled: [ver1] (version_type) 2nd time : [rollback version] (version_type) So when user asks for rollback version, bot should check slot value(1st) and then respond

@IgNoRaNt23 Off-course we use this method to get slot value, but here ver1, ver2, ver3, rollback version belongs to same slot named "version_type". So in this case, how can we get the value of previous value of slot.

Hi, I am building a contextual bot. In order to answer the current question, bot needs the previous contextual data. So, how can I get the value of previously set slot in the current form action? PS: Bot has only 1 slot, so I want the previous slot value to proceed. Your help will be appreciated.

How to make training data with 1000s of features

Show me [Bios Version] (feature_type) Show me [Chassis Model] (feature_type) Can you please tell the [IP Address] (feature_type) ? Can you please tell the [DNS Rac name] (feature_type) ?

So here I’ve 1000 such feature types(entity value). How to train bot to identify and extract the correct entities?

But those entities are nothing but the normal English words. How to use regular expression to distinguish it?

Custom Action Server Failed

hey thanks!! I forgot to mention custom action in domain.yml file.

The rasa action server is stuck on starting mode, it’s not proceeding further. (Status: First 4 lines)

2020-02-17 16:20:33 INFO rasa_sdk.endpoint - Starting action endpoint server… 2020-02-17 16:20:33 INFO rasa_sdk.executor - Registered function for ‘action_feature_search’. I am unable to proceed further because rasa custom actions server is not working. Could you please help me resolve the issue?

Getting Error on training : ValueError: dictionary update sequence element #0 has length 1; 2 is required

configuration file: { "pipeline":"spacy_sklearn", "path":"./models/nlu", "data":"./data/data.json" } nlu_model.py from rasa_nlu.training_data import load_data from rasa_nlu.config import...