All - Activity - AndreD - Rasa Community Forum

How to pass intent with entity during "interactive" mode

Hi Abhishek, I am facing the same issue. What version do you use ? br andre

Forms, responses between questions

Hi Leo, I suggest to have a validationAction in order to a) validate the slot filling if necessary and b) to utter what ever you want to feedback to the user. best regards andre

Handling unhappy form paths: getting slot value outside the form

Hi Nicolas, I just read what you experienced and I am wondering why you need both - a rule and a story both handling the deviation. As the whole rule is 100% integrated part of your story, why is it necessary ? Wouldn’t it work without that rule? BR Andre

Failed test stories have no comments

I have exactly the same issues. I also put it here: It seems that no one seems to have an answer. As I lately also realized differences in between my CI/CD chain results and local testing I lost all my trust in that capability, which I find is crucial to have.

Failed Story in test stories

Hi jalowiec, I am hanging around with storytesting as well as you can see here: I have currently two major topic with that: Nobody seems to know how to read the failed test stories file. For my understanding the hash-tag (#) should indicate wrong predictions, which gives you a hint where the s…

End to end story testing; how to read results of failed_test_stories.yml

Hi all, I am hanging around for a while now without success regarding end to end testing. It all starts already how to interprete the results of the test run being written into failed_test_stories.yml. Currently the overall results show 3 of 30 test stories are correct, which results in having 27 i…

Failed stories

Maybe we could go back to the initial question as I am facing the same issue. Latest test results are 3 of 30 test stories are marked as correct, 27 can be found in failed_test_stories, but only 1 story has been marked with the # hashtag. What might be a good explanation for that? BR ANdre

How do I "return an ActionExecutionRejected event as part of your custom validations or slot mappings"

Hi all, I have the same question. Best Andre

Best Practice on how to efficiently update test stories from failed test stories report

Background: We have a Rasa-x installation with CI/CD Github Action doing the rasa train & test. We produce our test files continuously with rasa-x. Issue: We have already a lot of test stories and when we make a fundamental change in our approach, we must regard all the test stories. Currently w…

Ignore all intents for slot filling

Hi Chris, is intent_name a typo? I mean docs says: forms: your_form: required_slots: slot_name:

type: from_text intent: intent_name not_intent: excluded_intent

Docker Compose Deploy - Set the RASA_HOME environment variable is not working. Rasa_X_playbook won't recognize it

Hi Diogo, did you finally managed it? I do have the same issue … BR Andre

Urgent: Empty nlu.md file in Rasa X. Unable to upload new nlu file as well

Hi there, I have nearly the same isue since yesterday. The only difference I see in the server side logs is an error that says some duplicate constraint is violated … sqlalchemy.exc.IntegrityError: (psycopg2.errors.UniqueViolation) duplicate key value violates unique constraint “message_log_pkey” …

Problem while integrating rasa 2.3.4 to my website : Socketio

Thanks, maybe of relevance for others. I was coming from rasa 2.3.0 in combination with python-socketio==5.0.0 and python-engineio==3.13.2. I dated rasa up to 2.4.0 → no improvement going back to socketio==4.6.1 was the game changer…

Add pure Websockets as custom channel

Hi Adam, I am currently at the same point and would highly appreciate if you would share how you did it. All the best Andre

DIETClassifier does not generalize?

Thanks for your contribution to help me. I tried it, but I am running into a runtime error. It seems that the dependencies are not correct as I got this during training of nlu: undefined symbol: _ZN10tensorflow8OpKernel11TraceStringEPNS_15OpKernelContextEb It may help to show me your full package …

DIETClassifier does not generalize?

So basicly this was my main question… and I really have doubts believing it to be honest Why should I try to use a machine learning mechanism for something that a simple mappingtable can solve even better?

DIETClassifier does not generalize?

Hi Murali, thanks a lot, I will definetely do so…I will come back whether it works. It is anyway part of my learning process using the RASA stack But this will not help regarding the NLU topic as such, as I only can store something that I have been able to extract before. Like mentioned before in…

DIETClassifier does not generalize?

I have no code so far in my actions.py as I first wanted to understand why the extraction isn’t working …

DIETClassifier does not generalize?

I cannot see any major differences which could cause my observations… Using your Country example delivers the following in my runtime: When I utter the sentence “I am in UK and want to go to the USA” the extractor delivers two country entities like expected When I utter the sentence “I am in India and want to go to…”

DIETClassifier does not generalize?

Now I have taken your “Country” Example one-by-one. I also took the en language model. I do not see any generalization happening either

DIETClassifier does not generalize?

can you also show me your pipeline ? This is how mine is looking currently … [image]

DIETClassifier does not generalize?

no problem. How many examples do you have annotated for the country entity? Looking at the image I see only the two you mentioned before. I am asking because I am wondering whether this is enough training data for the model to generalize …

DIETClassifier does not generalize?

Murali, thank you so much helping me out here But let’s please start from the original question. So before I can dig any deeper into the customer actions I need to understand the intent/entity extraction problem…

DIETClassifier does not generalize?

Do you think it makes any difference when I use roles in addition?

DIETClassifier does not generalize?

Hi Murali, exactly, but I get good entity matches (>60%) when I take location names that are mentioned in the training data. When I take similar utterances and change only the location name - let’s say Berlin -> Pune I get no matches at all… BR Andre

DIETClassifier does not generalize?

Hi all, I am wondering whether some of you had maybe kind of similar problem with the DIETClassifier. Currently I am testing how good the generalization works with the standard scenario of flying from A to B. AND now I got stuck - there is no generalization happening at all. It looks like the class…

Entity annotation not working as expected in the nlu training data tab

Hi there, I am hanging around with rasa X currently in order to check whether it could be a good low code solution for our company offering portfolio…and coming across some obstacles… One of them is that entity types are not showing up in the rasa x console so that I can make use of them. I set th…

Rocket.chat integration causes 'NoneType' object has no attribute 'startswith'

I found this issue here, which seems to cause exactly the same server Output:

curl -XPOST http://localhost:5005/webhooks/rest/webhook -d '{"sender": "forexample", "text": "hello"}' -H "Content-type: application/json"

Rocket.chat integration causes 'NoneType' object has no attribute 'startswith'

Looking into the server log I found the following: 2019-12-06 14:53:56 DEBUG rasa_core.processor - Received user message ‘None’ 2019-12-06 14:53:56 ERROR rasa_core.server - Exception on /webhooks/rest/webhook [POST]

Rocket.chat integration causes 'NoneType' object has no attribute 'startswith'

Hi everyone, I got stuck in my integration work with rockt.chat. Following the tutorials on both sides I got the servers speak to each other but now rasa seems to miss something. Anyone experienced something similar? BR Andre

Hi all, Andre from Bonn, germany

Hi all, I am Andre. I am excited about ai and Chatbots specifically in the area of voice. After first experiments with watson and cognigy I am curious about to learn how rasa performance with regards to complex dialogs. Thanks in advance to let me learn something.