you don’t know your Rasa version, use rasa --version
.
Please format any code or console output with three ticks ``` above and below.
If you are asking a usage question (e.g. “How do I do xyz”) please post your question on http://forum.rasa.com instead -->
Rasa version: Rasa 1.1.8
Rasa X version (if used & relevant):
Python version: python3.6.7
Operating system (windows, osx, …): linux
Issue: Duckling is not working for entity extraction
I’ve done testing is done using
curl -XPOST http://0.0.0.0:8000/parse --data ‘locale=en_GB&text=“the first Tuesday of October”’
it will give o/p:
[{“body”:“the first Tuesday of October”,“start”:1,“value”:{“values”:[{“value”:“2019-10-01T00:00:00.000-07:00”,“grain”:“day”,“type”:“value”}],“value”:“2019-10-01T00:00:00.000-07:00”,“grain”:“day”,“type”:“value”},“end”:29,“dim”:“time”,“latent”:false}]
but when I will try it out in RASA than it produce empty entity , so how can I Implement it in my rasa code
Content of configuration file (config.yml) (if relevant):
pipeline: supervised_embeddings
- name: rasa_addons.nlu.components.language_setter.LanguageSetter
- name: WhitespaceTokenizer
- name: CountVectorsFeaturizer
- name: EmbeddingIntentClassifier
- BILOU_flag: true
name: CRFEntityExtractor
features:
- [low, title, upper]
- [low, bias, prefix5, prefix2, suffix5, suffix3, suffix2, upper, title, digit, pattern]
- [low, title, upper]
- name: rasa_addons.nlu.components.gazette.Gazette
- name: EntitySynonymMapper
- name: components.botfront.duckling_http_extractor.DucklingHTTPExtractor
url: http://duckling:8000
dimensions:
- "number"
- "time"
- "duration"
locale: en_US
timezone: Europe/Berlin
Content of domain file (domain.yml) (if relevant):