Getting Confidence of 0.0

Rasa Open Source
1

My “Error”: { “intent”: { “name”: null, “confidence”: 0.0 }, “entities”: , “text”: “hallo du” }

this is my code:

image
image1824×799 72.7 KB

2

it seems you don’t have a classifier in your pipeline, just the spacy model and the tokenizer. you need to feed the features to a classifier in order to classfy intents.

3

Im really new to this, so what does that mean?
there are classes or not?

4

This is a more complete looking pipeline. Please download and point the appropriate language for your configuration. You need to add a classifier like DIET or sklearn after spaCy so spaCy features can be taken into consideration by the classifier. Please go through documentation or try rasa init for a starter configuration.

pipeline:
  - name: "SpacyNLP"
    # language model to load
    model: "en_core_web_md"

    # when retrieving word vectors, this will decide if the casing
    # of the word is relevant. E.g. `hello` and `Hello` will
    # retrieve the same vector, if set to `False`. For some
    # applications and models it makes sense to differentiate
    # between these two words, therefore setting this to `True`.
    case_sensitive: False
  - name: SpacyTokenizer
  - name: SpacyFeaturizer
    pooling: mean
  - name: RegexFeaturizer
  - name: LexicalSyntacticFeaturizer
  - name: DIETClassifier
    epochs: 100
    constrain_similarities: true
  - name: ResponseSelector
    epochs: 100
policies:
# # No configuration for policies was provided. The following default policies were used to train your model.
# # If you'd like to customize them, uncomment and adjust the policies.
# # See https://rasa.com/docs/rasa/policies for more information.
#   - name: MemoizationPolicy
#   - name: RulePolicy
#   - name: UnexpecTEDIntentPolicy
#     max_history: 5
#     epochs: 100
#   - name: TEDPolicy
#     max_history: 5
#     epochs: 100
#     constrain_similarities: true
5

@R6xDesigns - Also i just noticed your Rasa version which is quite old so some of the components may not work.

Please upgrade your Rasa version to a more recent one.

6

i dont want to annoy you with my problem but maybe im just stupid.

Im getting an error now i changed the model to the one i have installed:

image
image1190×795 88.2 KB

but i get this error:

image
image1019×541 21.8 KB

any ideas?

7

when i use pip install --upgrade rasa_nlu i get the version 0.15.1 is there a newer one i cant get via pip?

8

there is no longer rasa_nlu, you have to install rasa

do it in a separate folder,

create a virtual environment then pip install rasa

please follow installation docs https://rasa.com/docs/rasa/installation/

Regarding your error you are missing SpacyNLP as name and your yaml has indentation error. please lint your yaml

9

are you aviable to answer a question to rasa as well or do i have to make another topic for that?

10

Preferably create another topic or search the forums first. your answers might already exist. I always advise to go through the documentation for any project, there are also plenty of resources in youtube about Rasa from Rasa as well…

Checkout the learning center

1 Like