Rasa

Deprecations and Removals
- [261](https://github.com/rasahq/rasa/issues/261): In forms, the keyword `required_slots` should always precede the definition of slot mappings and the lack of it is deprecated.
Please see the [migration guide](migration-guide.mdx) for more information.
- [8428](https://github.com/rasahq/rasa/issues/8428): `rasa.data.get_test_directory`, `rasa.data.get_core_nlu_directories`, and
`rasa.shared.nlu.training_data.training_data.TrainingData::get_core_nlu_directories`
are deprecated and will be removed in Rasa Open Source 3.0.0.
- [8498](https://github.com/rasahq/rasa/issues/8498): Update the minimum compatible model version to "2.6.0".
This means all models trained with an earlier version will have to be retrained.

Features
- [8103](https://github.com/rasahq/rasa/issues/8103): Feature enhancement enabling JWT authentication for the Socket.IO channel. Users can define `jwt_key` and `jwt_method` as parameters in their credentials file for authentication.
- [8180](https://github.com/rasahq/rasa/issues/8180): Allows a Rasa bot to be connected to a Twilio Voice channel. More details in the [Twilio Voice docs](connectors/twilio-voice.mdx)
- [8532](https://github.com/rasahq/rasa/issues/8532): Conditional response variations are supported in the `domain.yml` without requiring users to write custom actions code.

A condition can be a list of slot-value mapping constraints.

Improvements
- [261](https://github.com/rasahq/rasa/issues/261): Added an optional `ignored_intents` parameter in forms.

- To use it, add the `ignored_intents` parameter in your `domain.yml` file after the forms name and provide a list of intents to ignore. Please see [Forms](forms.mdx) for more information.
- This can be used in case the user never wants to fill any slots of a form with the specified intent, e.g. chitchat.
- [5786](https://github.com/rasahq/rasa/issues/5786): Add function to carry `max_history` to featurizer
- [7589](https://github.com/rasahq/rasa/issues/7589): Improved the machine learning models' codebase by factoring out shared feature-processing
logic into three custom layer classes:
- `ConcatenateSparseDenseFeatures` combines multiple sparse and dense feature tensors
into one.
- `RasaFeatureCombiningLayer` additionally combines sequence-level and sentence-level
features.
- `RasaSequenceLayer` is used for attributes with sequence-level features; it
additionally embeds the combined features with a transformer and facilitates masked
language modeling.
- [7685](https://github.com/rasahq/rasa/issues/7685): Added the following usability improvements with respect to entities getting extracted multiple times:
* Added warnings for competing entity extractors at training time and for overlapping entities at inference time
* Improved docs to help users handle overlapping entity problems.
- [7999](https://github.com/rasahq/rasa/issues/7999): Replace `weight_sparsity` with `connection_density` in all transformer-based models and add guarantees about internal layers.

We rename `DenseWithSparseWeights` into `RandomlyConnectedDense`, and guarantee that even at density zero the output is dense and every input is connected to at least one output. The former `weight_sparsity` parameter of DIET, TED, and the ResponseSelector, is now roughly equivalent to `1 - connection_density`, except at very low densities (high sparsities).

All layers and components that used to have a `sparsity` argument (`Ffnn`, `TransformerRasaModel`, `MultiHeadAttention`, `TransformerEncoderLayer`, `TransformerEncoder`) now have a `density` argument instead.
- [8074](https://github.com/rasahq/rasa/issues/8074): Rasa test now prints a warning if the test stories contain bot utterances that are not part of the domain.
- [8263](https://github.com/rasahq/rasa/issues/8263): Updated `asyncio.Task.all_tasks` to `asyncio.all_tasks`, with a fallback for python 3.6, which raises an AttributeError for `asyncio.all_tasks`. This removes the deprecation warning for the `Task.all_tasks` usage.
- [8461](https://github.com/rasahq/rasa/issues/8461): Change variable name from `i` to `array_2D`
- [8560](https://github.com/rasahq/rasa/issues/8560): Implement a new interface `run_inference` inside `RasaModel` which performs batch inferencing through tensorflow models.

`rasa_predict` inside `RasaModel` has been made a private method now by changing it to `_rasa_predict`.

Bugfixes
- [7005](https://github.com/rasahq/rasa/issues/7005): Fixed a bug for plotting trackers with non-ascii texts during interactive training by enforcing utf-8 encoding
- [7589](https://github.com/rasahq/rasa/issues/7589): Fix masked language modeling in DIET to only apply masking to token-level
(sequence-level) features. Previously, masking was applied to both token-level and
sentence-level features.
- [8300](https://github.com/rasahq/rasa/issues/8300): Make it possible to use `null` entities in stories.
- [8333](https://github.com/rasahq/rasa/issues/8333): Introduce a `skip_validation` flag in order to speed up reading YAML files that were already validated.
- [8341](https://github.com/rasahq/rasa/issues/8341): Fixed a bug in interactive training that
lead to crashes for long Chinese, Japanese,
or Korean user or bot utterances.

Features
- [8892](https://github.com/rasahq/rasa/issues/8892): Added `sasl_mechanism` as an optional configurable parameters for the [Kafka Producer](event-brokers.mdx#kafka-event-broker).

Bugfixes
- [8446](https://github.com/rasahq/rasa/issues/8446): Fixed prediction for rules with multiple entities.
- [8545](https://github.com/rasahq/rasa/issues/8545): Mitigated Matplotlib backend issue using lazy configuration
and added a more explicit error message to guide users.

Deprecations and Removals
- [8141](https://github.com/rasahq/rasa/issues/8141): The following import abbreviations were removed:
* `rasa.core.train`: Please use `rasa.core.train.train` instead.
* `rasa.core.visualize`: Please use `rasa.core.visualize.visualize` instead.
* `rasa.nlu.train`: Please use `rasa.nlu.train.train` instead.
* `rasa.nlu.test`: Please use `rasa.nlu.test.run_evaluation` instead.
* `rasa.nlu.cross_validate`: Please use `rasa.nlu.test.cross_validate` instead.

Features
- [7869](https://github.com/rasahq/rasa/issues/7869): Upgraded Rasa to be compatible with spaCy 3.0.

This means that we can support more features for more languages but there are also a few changes.

SpaCy 3.0 deprecated the `spacy link <language model>` command so that means that from now on [the
full model name](https://spacy.io/models) needs to be used in the `config.yml` file.

**Before**

Before you could run `spacy link en en_core_web_md` and then we would be able
to pick up the correct model from the `language` parameter.

yaml
language: en

pipeline:
- name: SpacyNLP


**Now**

This behavior will be deprecated and instead you'll want to be explicit in `config.yml`.

yaml
language: en

pipeline:
- name: SpacyNLP
model: en_core_web_md


**Fallback**

To make the transition easier, Rasa will try to fall back to a medium spaCy model when-ever
a compatible language is configured for the entire pipeline in `config.yml` even if you don't
specify a `model`. This fallback behavior is temporary and will be deprecated in Rasa 3.0.0.

We've updated our docs to reflect these changes. All examples now show a direct link to the
correct spaCy model. We've also added a warning to the [SpaCyNLP](components.mdxspacynlp)
docs that explains the fallback behavior.

Improvements
- [4280](https://github.com/rasahq/rasa/issues/4280): Improved CLI startup time.
- [4596](https://github.com/rasahq/rasa/issues/4596): Add `augmentation` and `num_threads` arguments to API `POST /model/train`

Fix boolean casting issue for `force_training` and `save_to_default_model_directory` arguments
- [7477](https://github.com/rasahq/rasa/issues/7477): Add minimum compatible version to --version command
- [7660](https://github.com/rasahq/rasa/issues/7660): Updated warning for unexpected slot events during prediction time to Rasa Open Source
2.0 YAML training data format.
- [7701](https://github.com/rasahq/rasa/issues/7701): Hide dialogue turns predicted by `RulePolicy` in the tracker states
for ML-only policies like `TEDPolicy`
if those dialogue turns only appear as rules in the training data and do not appear in stories.

Add `set_shared_policy_states(...)` method to all policies.
This method sets `_rule_only_data` dict with keys:
- `rule_only_slots`: Slot names, which only occur in rules but not in stories.
- `rule_only_loops`: Loop names, which only occur in rules but not in stories.

This information is needed for correct featurization to hide dialogue turns that appear only in rules.
- [8208](https://github.com/rasahq/rasa/issues/8208): Faster reading of YAML NLU training data files.
- [8335](https://github.com/rasahq/rasa/issues/8335): Added partition_by_sender flag to [Kafka Producer](event-brokers.mdx#kafka-event-broker) to optionally associate events with Kafka partition based on sender_id.

Bugfixes
- [7260](https://github.com/rasahq/rasa/issues/7260): Fixed the 'loading model' message which was logged twice when using `rasa run`.
- [7379](https://github.com/rasahq/rasa/issues/7379): Change training data validation to only count nlu training examples.
- [7450](https://github.com/rasahq/rasa/issues/7450): Rule tracker states no longer include the initial value of slots.
Rules now only require slot values when explicitly stated in the rule.
- [7640](https://github.com/rasahq/rasa/issues/7640): `rasa test`, `rasa test core` and `rasa test nlu` no longer show temporary paths
in case there are issues in the test files.
- [7690](https://github.com/rasahq/rasa/issues/7690): Resolved memory problems with dense features and `CRFEntityExtractor`
- [7916](https://github.com/rasahq/rasa/issues/7916): Handle empty intent and entity mapping in the `domain`.

There is now an InvalidDomain exception raised if in the `domain.yml` file there are empty intent or entity mappings.
An example of empty intent and entity mappings is the following :
yaml-rasa
intents:
- greet:
- goodbye:

entities:
- cuisine:
- number:

- [8102](https://github.com/rasahq/rasa/issues/8102): Fixed a bug in a form where slot mapping doesn't work if the predicted intent name is substring for another intent name.
- [8114](https://github.com/rasahq/rasa/issues/8114): Fixes bug where stories could not be retrieved if entities had no start or end.
- [8178](https://github.com/rasahq/rasa/issues/8178): Catch ChannelNotFoundEntity exception coming from the pika broker and raise as ConnectionException.
- [8337](https://github.com/rasahq/rasa/issues/8337): Fix bug with NoReturn throwing an exception in Python 3.7.0 when running `rasa train`
- [8382](https://github.com/rasahq/rasa/issues/8382): Throw `RasaException` instead of `ValueError` in situations when environment variables
specified in YAML cannot be expanded.
- [8343](https://github.com/rasahq/rasa/issues/8343): Updated python-engineio version for compatibility with python-socketio

Miscellaneous internal changes
- [6511](https://github.com/rasahq/rasa/issues/6511), [#7640](https://github.com/rasahq/rasa/issues/7640), [#7827](https://github.com/rasahq/rasa/issues/7827), [#8056](https://github.com/rasahq/rasa/issues/8056), [#8117](https://github.com/rasahq/rasa/issues/8117), [#8141](https://github.com/rasahq/rasa/issues/8141), [#8240](https://github.com/rasahq/rasa/issues/8240)

Bugfixes
- [8114](https://github.com/rasahq/rasa/issues/8114): Fixes bug where stories could not be retrieved if entities had no start or end.

Bugfixes
- [7835](https://github.com/rasahq/rasa/issues/7835): Fix `UnicodeException` in `is_key_in_yaml`.
- [8258](https://github.com/rasahq/rasa/issues/8258): Fixed the bug that events from previous conversation sessions would be re-saved in the [`SQLTrackerStore`](tracker-stores.mdx#sqltrackerstore) or [`MongoTrackerStore`](tracker-stores.mdxmongotrackerstore) when `retrieve_events_from_previous_conversation_sessions` was true.