only use MultiProjectImporter?is there another way to do multi law court?In my rasa, there some nlu and response is common parts， and there are also different nlu and response for different courts. This is the core config: importers:
and for different court: config is imports:
I want that each folder is different court, and the nlu.yml of different court belong to respective court.but after I get the train model, it seems like that the rasa can response to each court.When court is lawbot_shushan, I want it ignore the content of other folder. how to do it? how to ignore else?
When court is lawbot_shushan, how to ignore nlu.yml of else court thoroughly?
or how to set the local si feixi for one equipment forever?
or use entity local ,the entity not change.how to set?
I think you have a couple of approaches you can take. Either (1) generate a single modle and use a slot to specify the context or court that the conversation or intent is about; or (2) create separate models for each court (you’d have separate runtime bots for each court).
It sounds like you are taking the 2nd approach. In that case, I’ve seen two approaches for generating multiple models from a single repo. One is to do this with scripts (and part of a CI/CD pipeline if you want) that creates a data directory from the combination of the common and court specific training data for each bot and trains them separately. The other approach I’ve seen is to separate git submodules for each court (still have separate build scripts).
There are 600 courts,so each court trains them separately,it will takes long time.
Use channel in Rasa? there 600 courts, some intents repeat in other court, but I can’t delete it,beacause 600 courts takes long time. so when I stand in one court, it recognize the intent is the courts,not the intent of other court, such as court A : intent :goto movie 1 ,text: see a movie; court B : intent goto movie 2 ,text: see a movie; court C : intent goto movie 3,text: see a movie; when I in court C ,it can recongize the intent is intent goto movie 3, not the similar intent intent goto movie 1 and intent goto movie 2
is there some examples about channel set,I want to include a location to message, the use the location I can recongize the intent of the court
I use the tracker.get_last_event_for(“user”, [], 2) ; tracker.current_state() ; tracker.events . but it only display 10 similar intents ,how to get all similar intents. or the numbers of intents is 600,is same with numbers of courts.
'intent_response_key': 'qitalocal/love_younn',
'utter_action': 'utter_qitalocal/love_younn'
},
'ranking': [{
'confidence': 0.38032880425453186,
'intent_response_key': 'qitalocal/love_younn'
}, {
'confidence': 0.2553354501724243,
'intent_response_key': 'qitalocal/love_youwuhan'
}, {
'confidence': 0.2462891787290573,
'intent_response_key': 'qitalocal/love_youcsha'
}, {
'confidence': 0.029368096962571144,
'intent_response_key': 'qitalocal/search_faguan'
}, {
'confidence': 0.019546102732419968,
'intent_response_key': 'qitalocal/dlove_youwuhan'
}, {
'confidence': 0.014975426718592644,
'intent_response_key': 'qitalocal/dlove_youcsha'
}, {
'confidence': 0.013231865130364895,
'intent_response_key': 'qitalocal/dlove_younn'
}, {
'confidence': 0.011796089820563793,
'intent_response_key': 'qitalocal/love_youbb'
}, {
'confidence': 0.007167272735387087,
'intent_response_key': 'qitalocal/love_you'
}, {
'confidence': 0.006238806992769241,
'intent_response_key': 'qitalocal/search_lawyer'
}]need help.Thanks
ranking_length: 100 in DIETClassifier.OK
There are 600 courts,so each court trains them separately,it will takes long time.
So, the slot based approach is worth trying.
how to calculate the similarity between two sentences in Rasa?
For example: sentence1: “I eat breakfast”
sentence2: “I eat now”
sentence3: “I eat breakfast after 10 minutes”
They are one intent.
now I have a sentence0: “I will eat later” ,
how to compare the sentence0 to one intent?
I want make its’ confidence is about 0.9 above. How to do it?
how to compare the sentence0 to one intent?
Is there some way or components or Rasa?
or input one sentence, how to know it isn’t the designative intent？