desc: | Rasa Changelog |
---|
All notable changes to this project will be documented in this file. This project adheres to `Semantic Versioning`_ starting with version 1.0.
[Unreleased 1.0.0.aX] - `master`_
- added arguments to set the file paths for interactive training
- added quick reply representation for command-line output
- added option to specify custom button type for Facebook buttons
- added tracker store persisting trackers into a SQL database
(
SQLTrackerStore
) - added rasa command line interface and API
- Rasa Stack HTTP training endpoint at
POST /jobs
. This endpoint will train a combined Rasa Core and NLU model ReminderCancelled(action_name)
event to cancel given action_name reminder for current user- Rasa Stack HTTP intent evaluation endpoint at
POST /intentEvaluation
. This endpoints performs an intent evaluation of a Rasa Stack model - option to create template for new utterance action in
interactive learning
- you can now choose actions previously created in the same session
in interactive learning
- add formatter 'black'
- renamed
rasa_core
package torasa.core
- for interactive learning only include manually annotated and ner_crf entities in nlu export
- made
message_id
an additional argument tointerpreter.parse
- changed removing punctuation logic in
WhitespaceTokenizer
training_processes
in the Rasa NLU data router have been renamed toworker_processes
- created a common utils package
rasa.utils
for nlu and core, common methods likeread_yaml
moved there - removed
--num_threads
from run command (server will be asyncronous but running in a single thread) - removed
--pre_load
from run command (Rasa NLU server will just have a maximum of one model and that model will be loaded by default) - changed file format of a stored trained model from the Rasa NLU server to
tar.gz
rasa train
uses fallback config if an invalid config is given
- removed possibility to execute
python -m rasa_core.train
etc. (e.g. scripts inrasa.core
andrasa.nlu
). Use the CLI for rasa instead, e.g.rasa train core
. - removed
_sklearn_numpy_warning_fix
from theSklearnIntentClassifier
- removed projects: the Rasa NLU server now has a maximum of one model at a time loaded.
- evaluating core stories with two stage fallback gave an error, trying to handle None for a policy
- the
/evaluate
route for the Rasa NLU server now runs evaluation in a parallel process, which prevents the currently loaded model unloading - added missing implementation of the
keys()
function for the Redis Tracker Store rasa nlu test
doesn't error anymore when a test file is passed with-u
- in interactive learning: only updates entity values if user changes annotation
rasa train core
actually uses additional arguments, such as augmentation