You are viewing documentation for our open source project which is maintained by the community. If you want to get started building assistants with Rasa please check out our latest [documentation here](/content/docs/index.html). × SearchK This page contains information about changes between major versions and how you can migrate from one version to another. ## Rasa 3.0 to 3.1 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-30-to-31 "Direct link to heading") ### Machine Learning Components [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#machine-learning-components "Direct link to heading") #### TensorFlow Upgrade [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#tensorflow-upgrade "Direct link to heading") Due to the TensorFlow upgrade, we can't guarantee the exact same output and hence model performance if your configuration uses `LanguageModelFeaturizer`. This applies to the case where the model is re-trained with the new Rasa version without changing the configuration, random seeds, and data as well as to the case where a model trained with a previous version of Rasa is loaded with this new version for inference. Please check whether your trained model still performs as expected and retrain if needed. ### NLU JSON Format [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#nlu-json-format "Direct link to heading") [NLU training data](https://legacy-docs-oss.rasa.com/docs/rasa/nlu-training-data) in JSON format is deprecated and will be removed in Rasa 4.0. Please use `rasa data convert nlu -f yaml --data ` to convert your NLU JSON data to YAML format before support for NLU JSON data is removed. ## Rasa 2.x to 3.0 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-2x-to-30 "Direct link to heading") ### Markdown Data [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#markdown-data "Direct link to heading") Markdown is no longer supported — all the supporting code that was previously deprecated is now removed, and the convertors are removed as well. The related CLI commands `rasa data convert responses` and `rasa data convert config` were removed. If you still have training data in Markdown format then the recommended approach is to use Rasa 2.x to convert your data from Markdown to YAML. Please use the commands described [here](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide#training-data-files). ### Model Configuration [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#model-configuration "Direct link to heading") It is required to specify the used `recipe` within the [model configuration](https://legacy-docs-oss.rasa.com/docs/rasa/model-configuration). As of now Rasa only supports the `default.v1` recipe and will continue using it even if you don't specify a recipe in the model configuration. To avoid breaking changes in the future you should to specify `recipe: "default.v1"` at the top of your model configuration: - Rasa 2.0 (old) - Rasa 3.0 (new) Copy recipe: default.v1 language: en pipeline: ... policies: ... ### Custom Policies and Custom Components [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#custom-policies-and-custom-components "Direct link to heading") Rasa 3.0 changed the way [NLU components](https://legacy-docs-oss.rasa.com/docs/rasa/components) and [policies](https://legacy-docs-oss.rasa.com/docs/rasa/policies) are trained and run during inference. As part of these changes the interfaces for NLU components and policies have been unified and adapted. The next sections outline which adaptions are required to run your custom NLU components and policies with Rasa 3.0. ##### caution Please read the updated guide on custom graph components [here](https://legacy-docs-oss.rasa.com/docs/rasa/custom-graph-components) before continuing to follow the step-by-step guide to migrate your own custom graph components. **Type Annotations** Until Rasa 3.0 [type annotations](https://docs.python.org/3/library/typing.html) were not required in custom policies or custom NLU components. It is now required to use [type annotations](https://docs.python.org/3/library/typing.html) in custom NLU components and policies. Rasa uses these type annotations to validate that your graph components are compatible and correctly configured. As outlined in the custom [components guide](https://legacy-docs-oss.rasa.com/docs/rasa/custom-graph-components) it is not allowed to use [forward references](https://www.python.org/dev/peps/pep-0484/#forward-references). ##### Forward References with Python 3.7 Use the [`from __future__ import annotations`](https://www.python.org/dev/peps/pep-0563/#enabling-the-future-behavior-in-python-3-7) import to avoid using forward references with Python 3.7. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from \_\_future\_\_ import annotations from typing import List, Any from rasa.core.policies.policy import Policy from rasa.engine.storage.resource import Resource from rasa.shared.core.domain import Domain from rasa.shared.core.generator import TrackerWithCachedStates classMyPolicy(Policy): deftrain( self, training\_trackers: List\[TrackerWithCachedStates\], domain: Domain, \*\*kwargs: Any, )-> Resource: ... #### Changes to Custom NLU Components [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#changes-to-custom-nlu-components "Direct link to heading") **Inheriting from `GraphComponent`** NLU components which previously inherited from one of the following classes additionally need to inherit from the [`GraphComponent` interface](https://legacy-docs-oss.rasa.com/docs/rasa/custom-graph-components#the-graphcomponent-interface): - `SparseFeaturizer` - `DenseFeaturizer` - `IntentClassifier` - `EntityExtractor` - `Component` This snippet shows the required changes: - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from rasa.engine.graph import GraphComponent from rasa.nlu.featurizers.sparse\_featurizer.sparse\_featurizer import SparseFeaturizer classMyNLUComponent(GraphComponent, SparseFeaturizer): ... **Inheriting from `EntityExtractorMixin` instead of `EntityExtractor`** The `EntityExtractor` class was renamed to `EntityExtractorMixin`: - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from rasa.engine.graph import GraphComponent from rasa.nlu.extractors.extractor import EntityExtractorMixin classMyNLUComponent(GraphComponent, EntityExtractorMixin): ... **Instantiating a NLU Component for Training** NLU components are no longer instantiated via their constructor. Instead, all NLU components have to override the `create` method of the [`GraphComponent` interface](https://legacy-docs-oss.rasa.com/docs/rasa/custom-graph-components#the-graphcomponent-interface). The passed in configuration is your NLU component's default configuration including any updates from your model configuration file. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import Dict, Text, Any from rasa.engine.graph import GraphComponent, ExecutionContext from rasa.engine.storage.resource import Resource from rasa.engine.storage.storage import ModelStorage from rasa.nlu.classifiers.classifier import IntentClassifier classMyNLUComponent(GraphComponent, IntentClassifier): def\_\_init\_\_(self, component\_config: Dict\[Text, Any\])->None: self.component\_config = component\_config ... @classmethod defcreate( cls, config: Dict\[Text, Any\], model\_storage: ModelStorage, resource: Resource, execution\_context: ExecutionContext, )-> GraphComponent: return cls(config) **Persisting a Trained NLU Component** NLU components used to be persisted by a call to the NLU component's `persist` method from outside the NLU component itself. With Rasa 3.0 NLU components are responsible for persisting themselves. Use the provided `model_storage` and `resource` parameters to persist your NLU component at the end of the training and then return the `resource` as result of your NLU component's `train` method. See [component persistence](https://legacy-docs-oss.rasa.com/docs/rasa/custom-graph-components#model-persistence) for more details. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from rasa.engine.graph import GraphComponent from rasa.engine.storage.resource import Resource from rasa.nlu.classifiers.classifier import IntentClassifier from rasa.shared.nlu.training\_data.training\_data import TrainingData classMyNLUComponent(GraphComponent, IntentClassifier): deftrain(self, training\_data: TrainingData)-> Resource: ... self.persist() return self.\_resource defpersist(self)->None: with self.\_model\_storage.write\_to(self.\_resource)as directory: model\_data\_file = directory /"model\_data.json" rasa.shared.utils.io.dump\_obj\_as\_json\_to\_file(model\_data\_file, self.get\_model\_data()) ... **Instantiating a Trained NLU Component** Previously NLU components had to persist their own configuration. Now the config passed into `load` will automatically contain the configuration which your model was trained with. To instantiate a persisted NLU component, you need to use `model_storage` and `resource` in your NLU component's `load` method. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from \_\_future\_\_ import annotations import json from typing import Any, Text, Dict from rasa.engine.graph import GraphComponent, ExecutionContext from rasa.engine.storage.resource import Resource from rasa.engine.storage.storage import ModelStorage from rasa.nlu.classifiers.classifier import IntentClassifier from rasa.shared.exceptions import FileIOException classMyNLUComponent(GraphComponent, IntentClassifier): @classmethod defload( cls, config: Dict\[Text, Any\], model\_storage: ModelStorage, resource: Resource, execution\_context: ExecutionContext, \*\*kwargs: Any, )-> MyNLUComponent: model\_data ={} try: with model\_storage.read\_from(resource)as path: model\_data\_file = path /"model\_data.json" model\_data = json.loads(rasa.shared.utils.io.read\_file(model\_data\_file)) except(ValueError, FileNotFoundError, FileIOException): logger.debug( f"Couldn't load metadata for component '{cls.\_\_name\_\_}' as the persisted " f"model data couldn't be loaded." ) return cls( config, model\_data=model\_data ) **Providing a Default Configuration for an NLU Component** The default configuration is no longer a static class property but instead returned by the static method `get_default_config`: - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import Text, Any, Dict from rasa.engine.graph import GraphComponent from rasa.nlu.classifiers.classifier import IntentClassifier classMyNLUComponent(GraphComponent, IntentClassifier): ... @staticmethod defget\_default\_config()-> Dict\[Text, Any\]: return{"key1":"value1"} **Augmenting Training Data in an NLU Component** NLU Components like [tokenizers](https://legacy-docs-oss.rasa.com/docs/rasa/components#tokenizers) or [featurizers](https://legacy-docs-oss.rasa.com/docs/rasa/components#featurizers) augment the training data with their output during the model training. Their output is required by NLU components later in the pipeline. Typically, featurizers require _tokenized_ messages and intent classifiers require _featurized_ training data to train themselves. Rasa 3.0 makes these different purposes explicit. Previously both NLU component training and training data augmentation were done as part of the `train` method. In Rasa 3.0 they are split into `train` and `process_training_data`: - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from rasa.engine.graph import GraphComponent from rasa.engine.storage.resource import Resource from rasa.nlu.featurizers.sparse\_featurizer.sparse\_featurizer import SparseFeaturizer from rasa.shared.nlu.training\_data.training\_data import TrainingData classMyNLUComponent(GraphComponent, SparseFeaturizer): deftrain(self, training\_data: TrainingData)-> Resource: self.train\_featurizer(training\_data) self.persist() return self.\_resource defprocess\_training\_data(self, training\_data: TrainingData)-> TrainingData: for message in training\_data.training\_examples: self.add\_features(message) return training\_data **Handling Lists of Messages During Inference in an NLU Component** NLU components used to receive a single `Message` object during inference. Starting with Rasa 3.0 all NLU components have to support a list of messages during inference. Unless your component supports batch predictions the easiest way to handle this is to loop over the messages. It is also required to return the message objects at the end of the `process` method. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import List from rasa.engine.graph import GraphComponent from rasa.nlu.classifiers.classifier import IntentClassifier from rasa.shared.nlu.training\_data.message import Message classMyNLUComponent(GraphComponent, IntentClassifier): defprocess(self, messages: List\[Message\])-> List\[Message\]: for message in messages: self.predict(message) return messages **Registering your NLU Component** Before you can use your custom NLU component you have to register your NLU component using the `DefaultV1Recipe.register` decorator. The NLU component types correspond to the existing parent classes: - `Tokenizer`: `ComponentType.MESSAGE_TOKENIZER` - `SparseFeaturizer` / `DenseFeaturizer`: `ComponentType.MESSAGE_FEATURIZER` - `IntentClassifier`: `ComponentType.INTENT_CLASSIFIER` - `EntityExtractor`: `ComponentType.ENTITY_EXTRACTOR` - If your NLU component provides a pretrained model which should be used by other NLU components during training and inference use `ComponentType.MODEL_LOADER` Specify `is_trainable=True` if the `train` method of your component should be called during training. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from rasa.engine.recipes.default\_recipe import DefaultV1Recipe from rasa.nlu.classifiers.classifier import IntentClassifier from rasa.engine.graph import GraphComponent @DefaultV1Recipe.register( DefaultV1Recipe.ComponentType.INTENT\_CLASSIFIER, is\_trainable=True ) classMyNLUComponent(GraphComponent, IntentClassifier): ... **Using a Model Provider with your NLU Component** If your NLU component requires a pretrained model such as a [Spacy](https://legacy-docs-oss.rasa.com/docs/rasa/components#spacynlp) or [Mitie](https://legacy-docs-oss.rasa.com/docs/rasa/components#mitienlp) language model you have to specify the NLU component which provides this model in your model's pipeline before the NLU component which requires the model. In addition to this you now also need to specify the model loading component in the `model_from` parameter in the `register` decorator. The model will then be passed to your model's `train`, `process_training_data` and `process` methods: - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import List from rasa.engine.graph import GraphComponent from rasa.engine.recipes.default\_recipe import DefaultV1Recipe from rasa.engine.storage.resource import Resource from rasa.nlu.classifiers.classifier import IntentClassifier from rasa.nlu.utils.spacy\_utils import SpacyModel from rasa.shared.nlu.training\_data.message import Message from rasa.shared.nlu.training\_data.training\_data import TrainingData @DefaultV1Recipe.register( DefaultV1Recipe.ComponentType.INTENT\_CLASSIFIER, is\_trainable=True, model\_from="SpacyNLP" ) classMyNLUComponent(GraphComponent, IntentClassifier): deftrain( self, training\_data: TrainingData, model: SpacyModel)-> Resource: spacy\_nlp = model.model ... defprocess(self, messages: List\[Message\], model: SpacyModel)-> List\[Message\]: spacy\_nlp = model.model ... #### Changes to Custom Policies [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#changes-to-custom-policies "Direct link to heading") This guide leads you through the migration of a custom policy step by step. **Instantiating a Policy for Training** Policies are no longer instantiated via their constructor. Instead, all policies have to implement a `create` method. During the policy instantiation the configuration from the [model configuration](https://legacy-docs-oss.rasa.com/docs/rasa/model-configuration) is passed in as a dictionary instead of as separate parameters. Similarly, the`featurizers` are no longer instantiated outside of policies. Instead, the super class `rasa.core.policies.policy.Policy` instantiates the featurizers itself. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import Optional, Dict, Text, Any from rasa.core.featurizers.tracker\_featurizers import TrackerFeaturizer from rasa.core.policies.policy import Policy from rasa.engine.graph import ExecutionContext from rasa.engine.storage.resource import Resource from rasa.engine.storage.storage import ModelStorage classMyPolicy(Policy): def\_\_init\_\_( self, config: Dict\[Text, Any\], model\_storage: ModelStorage, resource: Resource, execution\_context: ExecutionContext, featurizer: Optional\[TrackerFeaturizer\]=None, )->None: super().\_\_init\_\_( config, model\_storage, resource, execution\_context, featurizer ) ... ... @classmethod defcreate( cls, config: Dict\[Text, Any\], model\_storage: ModelStorage, resource: Resource, execution\_context: ExecutionContext, )-> MyPolicy: return cls(config, model\_storage, resource, execution\_context) **Persisting a Trained Policy** Policies used to be persisted by a call to the policy's `persist` method from outside the policy itself. With Rasa 3.0 policies are responsible for persisting themselves. Use the provided `model_storage` and `resource` parameters to persist your graph component at the end of the training and then return the `resource` as result of your policy's `train` method. See [graph component persistence](https://legacy-docs-oss.rasa.com/docs/rasa/custom-graph-components#model-persistence) for more details. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import List, Any from rasa.core.policies.policy import Policy from rasa.engine.storage.resource import Resource from rasa.shared.core.domain import Domain from rasa.shared.core.generator import TrackerWithCachedStates classMyPolicy(Policy): deftrain( self, training\_trackers: List\[TrackerWithCachedStates\], domain: Domain, \*\*kwargs: Any, )-> Resource: ... self.persist() return self.\_resource defpersist(self)->None: with self.\_model\_storage.write\_to(self.\_resource)as directory: if self.featurizer isnotNone: self.featurizer.persist(directory) file\_path = directory /"model\_data.json" rasa.shared.utils.io.dump\_obj\_as\_json\_to\_file(file\_path, self.get\_model\_data()) ... **Instantiating a Trained Policy** Previously policies had to persist their own configuration. Now the config passed into `load` will automatically contain the configuration which your model was trained with. To instantiate a persisted policy, you need to use `model_storage` and `resource` in your policy's `load` method. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy import json from typing import Dict, Text, Any from rasa.core.featurizers.tracker\_featurizers import TrackerFeaturizer from rasa.core.policies.policy import Policy from rasa.engine.graph import ExecutionContext from rasa.engine.storage.resource import Resource from rasa.engine.storage.storage import ModelStorage from rasa.shared.exceptions import FileIOException classMyPolicy(Policy): @classmethod defload( cls, config: Dict\[Text, Any\], model\_storage: ModelStorage, resource: Resource, execution\_context: ExecutionContext, \*\*kwargs: Any, )-> MyPolicy: featurizer =None model\_data ={} try: with model\_storage.read\_from(resource)as path: if(Path(path)/ FEATURIZER\_FILE).is\_file(): featurizer = TrackerFeaturizer.load(path) model\_data\_file = path /"model\_data.json" model\_data = json.loads(rasa.shared.utils.io.read\_file(model\_data\_file)) except(ValueError, FileNotFoundError, FileIOException): logger.debug( f"Couldn't load metadata for policy '{cls.\_\_name\_\_}' as the persisted " f"metadata couldn't be loaded." ) return cls( config, model\_storage, resource, execution\_context, featurizer=featurizer, model\_data=model\_data ) **Providing a Default Configuration for a Policy** The default configuration is no longer provided via default values in your policy's constructor but instead returned by the static method `get_default_config`: - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import Dict, Text, Any from rasa.core.policies.policy import Policy classMyPolicy(Policy): def\_\_init\_\_(self, config: Dict\[Text, Any\])->None: ... @staticmethod defget\_default\_config()-> Dict\[Text, Any\]: return{"key1":"value1"} **Using End-To-End Features in a Policy** To use a custom [end-to-end policy](https://legacy-docs-oss.rasa.com/docs/rasa/stories#end-to-end-training) in Rasa Open Source 2, you had to use the `interpreter` parameter to featurize the tracker events manually. In Rasa 3.0, you need to [register](https://legacy-docs-oss.rasa.com/docs/rasa/custom-graph-components#registering-graph-components-with-the-model-configuration) a policy that requires end-to-end features with type `ComponentType.POLICY_WITH_END_TO_END_SUPPORT`. The features will be precomputed and passed into your policy during training and inference. ##### caution End-To-End features will only be computed and provided to your policy if your training data actually contains [end-to-end training data](https://legacy-docs-oss.rasa.com/docs/rasa/stories#end-to-end-training). - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import List, Optional, Dict, Text, Any from rasa.core.featurizers.precomputation import MessageContainerForCoreFeaturization from rasa.core.policies.policy import PolicyPrediction, Policy from rasa.engine.recipes.default\_recipe import DefaultV1Recipe from rasa.engine.storage.resource import Resource from rasa.shared.core.domain import Domain from rasa.shared.core.generator import TrackerWithCachedStates from rasa.shared.core.trackers import DialogueStateTracker @DefaultV1Recipe.register( DefaultV1Recipe.ComponentType.POLICY\_WITH\_END\_TO\_END\_SUPPORT, is\_trainable=True ) classMyPolicy(Policy): deftrain( self, training\_trackers: List\[TrackerWithCachedStates\], domain: Domain, precomputations: Optional\[MessageContainerForCoreFeaturization\]=None, )-> Resource: ... model\_data, label\_ids = self.\_prepare\_for\_training( training\_trackers, domain, precomputations, ) ... defpredict\_action\_probabilities( self, tracker: DialogueStateTracker, domain: Domain, precomputations: Optional\[MessageContainerForCoreFeaturization\]=None, rule\_only\_data: Optional\[Dict\[Text, Any\]\]=None, \*\*kwargs: Any, )-> PolicyPrediction: ... tracker\_state\_features = self.\_featurize\_tracker( tracker, domain, precomputations, rule\_only\_data=rule\_only\_data ) ... **Registering a Policy** Before you can use your custom policy you have to register your policy using the `DefaultV1Recipe.register` decorator. If your policy requires end-to-end features specify the graph component type `POLICY_WITH_END_TO_END_SUPPORT`. Otherwise, use `POLICY_WITHOUT_END_TO_END_SUPPORT`. Specify `is_trainable=True` if the `train` method of your policy should be called during the training. If your policy is only used during inference use `is_trainable=False`. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from rasa.core.policies.policy import Policy from rasa.engine.recipes.default\_recipe import DefaultV1Recipe @DefaultV1Recipe.register( DefaultV1Recipe.ComponentType.POLICY\_WITH\_END\_TO\_END\_SUPPORT, is\_trainable=True ) classMyPolicy(Policy): ... **Providing Rule-only Data to a Policy** Rasa allows excluding [forms](https://legacy-docs-oss.rasa.com/docs/rasa/forms) or [slots](https://legacy-docs-oss.rasa.com/docs/rasa/domain#slots) which are completely handled by [rules](https://legacy-docs-oss.rasa.com/docs/rasa/rules) from becoming features in other policies. In Rasa 2 this information was passed onto the policies using the `set_shared_policy_states` method which set the policy attribute `_rule_only_data`. Rasa passes the names of rule-only slots and forms via the `predict_action_probabilities` method. The passed `rule_only_data` can be `None` in case the [`RulePolicy`](https://legacy-docs-oss.rasa.com/docs/rasa/policies#rule-policy) is not part of your model configuration. - Rasa 2.0 (old) - Rasa 3.0 (new) Copy from typing import Optional, Dict, Text, Any from rasa.core.policies.policy import Policy, PolicyPrediction from rasa.shared.core.domain import Domain from rasa.shared.core.trackers import DialogueStateTracker classMyPolicy(Policy): defpredict\_action\_probabilities( self, tracker: DialogueStateTracker, domain: Domain, rule\_only\_data: Optional\[Dict\[Text, Any\]\]=None, )-> PolicyPrediction: ... ### Training data [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#training-data "Direct link to heading") #### Upgrading `version` from `2.0` to `3.0` [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#upgrading-version-from-20-to-30 "Direct link to heading") At the top of your training data files, you need to change `version: "2.0"` to `version: "3.1"`. We follow semantic versioning for training data versions. This means breaking changes result in a new major version, while new features result in a new minor version. The latest training data version is 3.1. The improvements to `slot mappings` in Rasa 3.0 were breaking changes, so we needed to upgrade from major version `2.0` to major version `3.0`. #### `TrainingDataImporter` [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#trainingdataimporter "Direct link to heading") `TrainingDataImporter` and all its implementations are updated to contain only synchronous methods. If you have a custom data importer or rely on some functions provided by `TrainingDataImporter`, you need to update your implementation and function calls. For example, this is how data loading should look like in Rasa 3.0: Copy from typing import Text from rasa.shared.importers.importer import TrainingDataImporter defload\_data(domain\_path: Text, config\_path: Text): file\_importer = TrainingDataImporter.load\_from\_config( config\_path, domain\_path ) \# note that all the functions below were async before: config = file\_importer.get\_config() domain = file\_importer.get\_domain() stories = file\_importer.get\_stories() nlu\_data = file\_importer.get\_nlu\_data() Since any custom importer implements `TrainingDataImporter`, you should update your custom importer to contain only sync methods as well: Copy from typing import Dict from rasa.shared.core.domain import Domain from rasa.shared.importers.importer import TrainingDataImporter classMyImporter(TrainingDataImporter): """Example partial implementation of a custom importer component.""" \# this function was async before defget\_domain(self)-> Domain: pass \# this function was also async before defget\_config(self)-> Dict: pass \# ... `template_variables` and `e2e` arguments also got removed from `get_stories` method of `TrainingDataImporter`. Its new signature looks this way: Copy from typing import Optional from rasa.shared.nlu.interpreter import RegexInterpreter from rasa.shared.core.training\_data.structures import StoryGraph classTrainingDataImporter: \# ... defget\_stories( self, interpreter:"NaturalLanguageInterpreter"= RegexInterpreter(), exclusion\_percentage: Optional\[int\]=None, )-> StoryGraph: pass \# ... ### Training [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#training "Direct link to heading") #### `rasa train --dry-run` [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-train---dry-run "Direct link to heading") Due to changes in the model architecture the behavior of `rasa train --dry-run` changed. The exit codes now have the following meaning: - `0` means that the model does not require an expensive retraining. However, the responses might still require updating by running `rasa train` - `1` means that one or multiple components require to be retrained. - `8` means that the `--force` flag was used and hence any cached results are ignored and the entire model is retrained. ### Machine Learning Components [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#machine-learning-components-1 "Direct link to heading") #### Normalization of Confidences in `DIETClassifier` and `ResponseSelector` [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#normalization-of-confidences-in-dietclassifier-and-responseselector "Direct link to heading") `DIETClassifier` and `ResponseSelector` will no longer automatically report re-normalized confidences when `ranking_length` is set to a value greater than `0`. This change affects the reported confidences but does not influence the final predicted intent, which might be used by policies. However, since the reported confidences are affected you might have to tune the thresholds for fallback mechanisms again. The previous behavior can still be enforced by setting `renormalize_confidences=True` when using `model_confidence=softmax`. #### Normalization of confidences in `TEDPolicy` [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#normalization-of-confidences-in-tedpolicy "Direct link to heading") Predictions of `TEDPolicy` will no longer be modified by masking and renormalizing confidences. This change can affect the maximum confidence predicted by the `TEDPolicy` and thereby affect the final result of the policy ensemble. However, the previous behavior can still be enforced by setting `ranking_length=10` and `renormalize_confidences=True`. #### Removed Policies [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#removed-policies "Direct link to heading") Several dialogue policies that were deprecated in Rasa 2.x have been removed in Rasa 3.0. If you are migrating a config file with a removed policy, consult the following migration guides for the individual policies: - `FallbackPolicy` [migration guide](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/#manually-migrating-from-the-fallback-policy) - `TwoStageFallbackPolicy` [migration guide](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/#manually-migrating-from-the-two-stage-fallback-policy) - `MappingPolicy` [migration guide](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/#manually-migrating-from-the-mapping-policy) - `FormPolicy` [migration guide](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/#forms) - `SklearnPolicy` should be replaced with [TEDPolicy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#ted-policy). It is recommended to use the [default TEDPolicy config](https://legacy-docs-oss.rasa.com/docs/rasa/model-configuration#suggested-config) as a starting point. #### Removed Tokenizers and Featurizers [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#removed-tokenizers-and-featurizers "Direct link to heading") The `ConveRTTokenizer`, `LanguageModelTokenizer`, and `HFTransformersNLP` featurizer components were deprecated in Rasa 2.x and have been removed in Rasa 3.0. See the [migration guide for Rasa 2.x](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/#deprecations-2) for replacing these components in your pipeline. ### Slot Mappings [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#slot-mappings "Direct link to heading") As of version 3.0, there is a single explicit mechanism for slot filling enabled by defining slot mappings for each slot in the `slots` section of the domain file. This approach keeps slots up to date over the course of a conversation, and removes duplicated effort in mapping the same slots in multiple forms. It is still possible to fill slots from arbitrary custom actions and not update them on every turn of the conversation if that behavior is desired. This new mechanism replaces the implicit slot setting via auto-fill of slots with entities of the same name. The `auto_fill` key in the domain is no longer available, as well as the `auto_fill` parameter in the constructor of the `Slot` class. While forms continue to request the next slot, slot extraction is now delegated to the default action [`action_extract_slots`](https://legacy-docs-oss.rasa.com/docs/rasa/default-actions#action_extract_slots). This action runs in the background automatically after each user turn. Like `action_listen`, it should not be included in stories. Each slot in the `slots` section must include the `mappings` key. The same keys used for predefined mappings in 2.0 are available in 3.0. Additionally, you can define slots with custom mappings implemented in a custom action which will be run on every user turn, for example: Copy slots: is\_existing\_customer: type: bool mappings: -type: custom action: action\_verify\_customer\_status You can use [slot validation actions](https://legacy-docs-oss.rasa.com/docs/rasa/slot-validation-actions) to either validate slots with predefined mappings, or to both extract and validate slots with custom mappings. Slots which will be filled by arbitrary custom actions in the course of the conversation, and which should not be updated on every user turn, should be listed with mappings of type `custom` and no action. For example: Copy slots: handoff\_completed: type: bool initial\_value:false mappings: -type: custom This slot's value will only change when a custom action is predicted that sets it. This mapping maintains the behavior from 2.x for a slot which was not filled by an entity or by slot mappings in a form. ##### note The `required_slots` of a form used to be a list of slot mappings. Since slot mappings are relocated to the `slots` section of the domain, `required_slots` has been converted to a list of slot names only. #### Automatic migration from 2.0 domain format to the 3.0 format [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#automatic-migration-from-20-domain-format-to-the-30-format "Direct link to heading") The only data file that has changed in format is the domain file. To migrate automatically to the 3.0 domain format, you can run the following command: Copy rasa data migrate -d DOMAIN --out OUT\_PATH In addition to creating a valid 3.0 domain in the indicated out path, this command will automatically backup your original domain file(s) in a file labeled `original_domain.yml` or `original_domain` directory if a directory was provided instead. To maintain the behavior of forms in the 2.0 format, all migrated slot mappings will include mapping conditions for each form. This can be changed manually according to your use case. See the docs on [mapping conditions](https://legacy-docs-oss.rasa.com/docs/rasa/domain#mapping-conditions) for more information. #### Manually migrating from 2.0 domain format to the 3.0 format [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#manually-migrating-from-20-domain-format-to-the-30-format "Direct link to heading") Each slot in the `slots` section of the domain will need a new key `mappings`. This key is a list of mappings moved from forms, while the `required_slots` field collapses to a list of slot names. Let's consider the following 2.0 domain file: Copy entities: - cuisine - number slots: cuisine: type: text num\_people: type: float outdoor\_seating: type: bool forms: restaurant\_form: required\_slots: cuisine: -type: from\_entity entity: cuisine num\_people: -type: from\_entity entity: number outdoor\_seating: -type: from\_intent intent: affirm value:true -type: from\_intent intent: deny value:false The initial result of migrating this domain to 3.0 format would look like this: Copy entities: - cuisine - number slots: cuisine: type: text mappings: -type: from\_entity entity: cuisine num\_people: type: float mappings: -type: from\_entity entity: number outdoor\_seating: type: bool mappings: -type: from\_intent intent: affirm value:true -type: from\_intent intent: deny value:false forms: restaurant\_form: required\_slots: - cuisine - num\_people - outdoor\_seating For slots that should be filled only in the context of a form, add [mapping conditions](https://legacy-docs-oss.rasa.com/docs/rasa/domain#mapping-conditions) to specify which form(s) should be active, as well as indicate if the `requested_slot` should be the same slot. Adding `conditions` is required to preserve the behavior of slot mappings from 2.0, since without them the mappings will be applied on each user turn regardless of whether a form is active or not. Copy slots: outdoor\_seating: type: bool mappings: -type: from\_intent intent: affirm value:true conditions: -active\_loop: restaurant\_form requested\_slot: outdoor\_seating -type: from\_intent intent: deny value:false conditions: -active\_loop: restaurant\_form requested\_slot: outdoor\_seating #### Rasa-SDK Modifications [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-sdk-modifications "Direct link to heading") If you have used `FormValidationAction` to define custom extraction and validation code in which you override the `required_slots` method, note that `slots_mapped_in_domain` argument has been replaced by the `domain_slots` argument. You must make this replacement to continue using your custom code. If you have been dynamically filling slots not present in the form's `required_slots` defined in the `domain.yml` file, note that this behaviour is no longer supported in 3.x. Any dynamic slots with custom mappings, which are set in the last user turn, will be filled **only if** they are returned by the `required_slots` method of the custom action inheriting from `FormValidationAction`. To maintain the 2.x behaviour, you must now override the `required_slots` method of this custom action as per the strong recommendation listed in the [dynamic form documentation](https://legacy-docs-oss.rasa.com/docs/rasa/forms#dynamic-form-behavior). To extract custom slots that are not defined in any form's `required_slots`, you should now use a global [custom slot mapping](https://legacy-docs-oss.rasa.com/docs/rasa/domain#custom-slot-mappings) and extend the [ValidationAction class](https://legacy-docs-oss.rasa.com/docs/rasa/action-server/validation-action#validationaction-class). ##### note If you have custom validation actions extending `FormValidationAction` which override `required_slots` method, you should double-check the dynamic form behavior of your migrated assistant. Slots set by the default action [`action_extract_slots`](https://legacy-docs-oss.rasa.com/docs/rasa/default-actions#action_extract_slots) may need to be reset within the context of your form by the custom validation actions for the form's required slots. For example, if your form dynamically adds a required slot after the first slot is filled, you may want to reset the potential required slot as part of the first required slot's validation method to ensure it will be empty when added. ## Rasa 2.7 to 2.8 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-27-to-28 "Direct link to heading") ##### caution This release **breaks backward compatibility of machine learning models**. It is not possible to load models trained with previous versions of Rasa. Please re-train your assistant before using this version. ### Deprecations [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#deprecations "Direct link to heading") #### Tracker Featurizers [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#tracker-featurizers "Direct link to heading") `training_states_actions_and_entities` method of `TrackerFeaturizer`, `FullDialogueTrackerFeaturizer` and `MaxHistoryTrackerFeaturizer` classes is deprecated and will be removed in Rasa 3.0 . If you had a custom tracker featurizer which relied on this method from any of the above classes, please use `training_states_labels_and_entities` instead. `training_states_and_actions` method of `TrackerFeaturizer`, `FullDialogueTrackerFeaturizer` and `MaxHistoryTrackerFeaturizer` classes is deprecated and will be removed in Rasa 3.0 . If you had a custom tracker featurizer which relied on this method from any of the above classes, please use `training_states_and_labels` instead. #### State Featurizer [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#state-featurizer "Direct link to heading") `encode_all_actions` method of `SingleStateFeaturizer` class is deprecated and will be removed in Rasa 3.0 . It is recommended to use the method `encode_all_labels` instead. ### Incremental Training [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#incremental-training "Direct link to heading") Users don't need to specify an additional buffer size for sparse featurizers anymore during incremental training. Space for new sparse features are created dynamically inside the downstream machine learning models - `DIETClassifier`, `ResponseSelector`. In other words, no extra buffer is created in advance for additional vocabulary items and space will be dynamically allocated for them inside the model. This means there's no need to specify `additional_vocabulary_size` for [`CountVectorsFeaturizer`](https://legacy-docs-oss.rasa.com/docs/rasa/components#countvectorsfeaturizer) or `number_additional_patterns` for [`RegexFeaturizer`](https://legacy-docs-oss.rasa.com/docs/rasa/components#regexfeaturizer). These parameters are now deprecated. **Before** Copy pipeline: -name:"WhitespaceTokenizer" -name:"RegexFeaturizer" number\_additional\_patterns:100 -name:"CountVectorsFeaturizer" additional\_vocabulary\_size:{text:100,response:20} **Now** Copy pipeline: -name:"WhitespaceTokenizer" -name:"RegexFeaturizer" -name:"CountVectorsFeaturizer" ### Machine Learning Components [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#machine-learning-components-2 "Direct link to heading") The option `model_confidence=linear_norm` is deprecated and will be removed in Rasa `3.0.0`. Rasa `2.3.0` introduced `linear_norm` as a possible value for `model_confidence` parameter in machine learning components such as `DIETClassifier`, `ResponseSelector` and `TEDPolicy`. Based on user feedback, we have identified multiple problems with this option. Therefore, `model_confidence=linear_norm` is now deprecated and will be removed in Rasa `3.0.0`. If you were using `model_confidence=linear_norm` for any of the mentioned components, we recommend to revert it back to `model_confidence=softmax` and re-train the assistant. After re-training, we also recommend to [re-tune the thresholds for fallback components](https://legacy-docs-oss.rasa.com/docs/rasa/fallback-handoff#fallbacks). ## Rasa 2.5 to 2.6 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-25-to-26 "Direct link to heading") ### Forms [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#forms "Direct link to heading") #### New `ignored_intents` parameter in Forms [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#new-ignored_intents-parameter-in-forms "Direct link to heading") There is a new parameter under Forms called `ignored_intents`. This parameter can be used to prevent any required slots in a form from being filled with the specified intent or intents. Please see the [Forms documentation](https://legacy-docs-oss.rasa.com/docs/rasa/forms) for examples and more information on how to use it in your `domain.yml` file. Before, if a user did not want to fill any slots of a form with a specified intent they would have to define it under the `not_intent` parameter for every slot mapping as shown in the following example : domain.yml Copy forms: restaurant\_form: cuisine: -type: from\_entity entity: cuisine not\_intent: chitchat num\_people: -type: from\_entity entity: number intent:\[inform, request\_restaurant\] not\_intent: chitchat feedback: -type: from\_entity entity: feedback not\_intent: chitchat By introducing the `ignored_intents` parameter, we now only need to define it in one place and it will affect all the slots of the form : domain.yml Copy forms: restaurant\_form: ignored\_intents: chitchat required\_slots: cuisine: -type: from\_entity entity: cuisine num\_people: -type: from\_entity entity: number intent:\[inform, request\_restaurant\] feedback: -type: from\_entity entity: feedback -type: from\_text ## Rasa 2.4 to 2.5 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-24-to-25 "Direct link to heading") ### Machine Learning Components [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#machine-learning-components-3 "Direct link to heading") #### `DIET`, `TED`, and `ResponseSelector` [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#diet-ted-and-responseselector "Direct link to heading") The former `weight_sparsity` parameter of the `DIETClassifier`, `TEDPolicy`, and the `ResponseSelector`, is now deprecated and superseded by the new `connection_density` parameter. The old `weight_sparsity` is roughly equivalent to `1 - connection_density`, except at very low densities (high sparsities). To avoid deprecation issues, you should set `connection_density` to `1 - your former weight_sparsity setting` throughout the config file. (If you left `weight_sparsity` at its default setting, you don't need to do anything.) #### SpaCy 3.0 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#spacy-30 "Direct link to heading") Rasa now supports spaCy 3.0. This means that we can support more features for more languages but this also introduced a breaking change. SpaCy 3.0 deprecated the `spacy link ` command. So from now on you need to use the [the full model name](https://spacy.io/models) 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. Copy language: en pipeline: -name: SpacyNLP **Now** This behavior will be deprecated and instead you'll want to be explicit in `config.yml`. Copy 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 whenever 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](https://legacy-docs-oss.rasa.com/docs/rasa/components#spacynlp) docs that explains the fallback behavior. ## Rasa 2.3 to Rasa 2.4 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-23-to-rasa-24 "Direct link to heading") ### Deprecating `template` for `response` [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#deprecating-template-for-response "Direct link to heading") NLG Server - Changed request format to send `response` as well as `template` as a field. The `template` field will be removed in Rasa 3.0.0. `rasa.core.agent` - The terminology `template` is deprecated and replaced by `response`. Support for `template` from the NLG response will be removed in Rasa 3.0.0. Please see [here](https://legacy-docs-oss.rasa.com/docs/rasa/nlg) for more details. `rasa.core.nlg.generator` - `generate()` now takes in `utter_action` as a parameter. - The terminology `template` is deprecated and replaced by `response`. Support for `template` in the `NaturalLanguageGenerator` will be removed in Rasa 3.0.0. `rasa.shared.core.domain` - The property `templates` is deprecated. Use `responses` instead. It will be removed in Rasa 3.0.0. - `retrieval_intent_templates` will be removed in Rasa 3.0.0. Please use `retrieval_intent_responses` instead. - `is_retrieval_intent_template` will be removed in Rasa 3.0.0. Please use `is_retrieval_intent_response` instead. - `check_missing_templates` will be removed in Rasa 3.0.0. Please use `check_missing_responses` instead. Response Selector - The field `template_name` will be deprecated in Rasa 3.0.0. Please use `utter_action` instead. Please see [here](https://legacy-docs-oss.rasa.com/docs/rasa/components#selectors) for more details. - The field `response_templates` will be deprecated in Rasa 3.0.0. Please use `responses` instead. Please see [here](https://legacy-docs-oss.rasa.com/docs/rasa/components#selectors) for more details. ## Rasa 2.3.3 to Rasa 2.3.4 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-233-to-rasa-234 "Direct link to heading") ##### caution This is a release **breaking backwards compatibility of machine learning models**. It is not possible to load previously trained models if they were trained with `model_confidence=cosine` or `model_confidence=inner` setting. Please make sure to re-train the assistant before trying to use it with this improved version. ### Machine Learning Components [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#machine-learning-components-4 "Direct link to heading") Rasa `2.3.0` introduced the option of using cosine similarities for model confidences by setting `model_confidence=cosine`. Some post-release experiments revealed that using `model_confidence=cosine` is wrong as it can change the order of predicted labels. That's why this option was removed in Rasa version `2.3.4`. `model_confidence=inner` is deprecated as it produces an unbounded range of confidences which can break the logic of assistants in various other places. We encourage you to try `model_confidence=linear_norm` which will produce a linearly normalized version of dot product similarities with each value in the range `[0,1]`. This can be done with the following config: Copy \- name: DIETClassifier model\_confidence: linear\_norm constrain\_similarities: True If you trained a model with `model_confidence=cosine` or `model_confidence=inner` setting using previous versions of Rasa, please re-train by either removing the `model_confidence` option from the configuration or setting it to `linear_norm`. ## Rasa 2.2 to Rasa 2.3 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-22-to-rasa-23 "Direct link to heading") ### General [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#general "Direct link to heading") If you want to use Tensorboard for `DIETClassifier`, `ResponseSelector`, or `TEDPolicy` and log metrics after every (mini)batch, please use 'batch' instead of 'minibatch' as 'tensorboard\_log\_level'. ### Machine Learning Components [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#machine-learning-components-5 "Direct link to heading") A few changes have been made to the loss function inside machine learning (ML) components `DIETClassifier`, `ResponseSelector` and `TEDPolicy`. These include: 1. Configuration option `loss_type=softmax` is now deprecated and will be removed in Rasa 3.0.0. Use `loss_type=cross_entropy` instead. 2. The default loss function (`loss_type=cross_entropy`) can add an optional sigmoid cross-entropy loss of all similarity values to constrain them to an approximate range. You can turn on this option by setting `constrain_similarities=True`. This should help the models to perform better on real world test sets. A new option `model_confidence` has been added to each ML component. It affects how the model's confidence for each label is computed during inference. It can take one of three values: 1. `softmax` \- Dot product similarities between input and label embeddings are post-processed with a softmax function, as a result of which confidence for all labels sum up to 1. 2. `cosine` \- Cosine similarity between input and label embeddings. Confidence for each label will be in the range `[-1,1]`. 3. `linear_norm` \- Dot product similarities between input and label embeddings are post-processed with a linear normalization function. Confidence for each label will be in the range `[0,1]`. The default value is `softmax`, but we recommend trying `linear_norm`. This should make it easier to [tune thresholds for triggering fallback](https://legacy-docs-oss.rasa.com/docs/rasa/fallback-handoff#fallbacks). The value of this option does not affect how confidences are computed for entity predictions in `DIETClassifier`. We encourage you to try both the above recommendations. This can be done with the following config: Copy \- name: DIETClassifier model\_confidence: linear\_norm constrain\_similarities: True ... Once the assistant is re-trained with the above configuration, users should also [tune fallback confidence thresholds](https://legacy-docs-oss.rasa.com/docs/rasa/fallback-handoff#fallbacks). **EDIT**: Some post-release experiments revealed that using `model_confidence=cosine` is wrong as it can change the order of predicted labels. That's why this option was removed in Rasa version `2.3.4`. ## Rasa 2.1 to Rasa 2.2 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-21-to-rasa-22 "Direct link to heading") ### General [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#general-1 "Direct link to heading") `TEDPolicy`'s `transformer_size`, `number_of_transformer_layers`, and `dense_dimensions` parameters have been renamed. Please update your configuration files using the following mapping: | Old Model Parameter | New Model Parameter | | --- | --- | | `transformer_size` | dictionary `transformer_size` with keys | | | `text`, `action_text`, `label_action_text`, `dialogue` | | `number_of_transformer_layers` | dictionary `number_of_transformer_layers` with keys | | | `text`, `action_text`, `label_action_text`, `dialogue` | | `dense_dimension` | dictionary `dense_dimension` with keys | | | `text`, `action_text`, `label_action_text`, `intent`, | | | `action_name`, `label_action_name`, `entities`, `slots`, | | | `active_loop` | For example: config.yml Copy policies: -name: TEDPolicy transformer\_size: text:128 action\_text:128 label\_action\_text:128 dialogue:128 number\_of\_transformer\_layers: text:1 action\_text:1 label\_action\_text:1 dialogue:1 dense\_dimension: text:128 action\_text:128 label\_action\_text:128 intent:20 action\_name:20 label\_action\_name:20 entities:20 slots:20 active\_loop:20 ### Deprecations [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#deprecations-1 "Direct link to heading") #### Markdown Data [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#markdown-data-1 "Direct link to heading") Training and test data in Markdown format is now deprecated. This includes: - reading and writing of story files in Markdown format - reading and writing of NLU data in Markdown format - reading and writing of retrieval intent data in Markdown format Support for Markdown data will be removed entirely in Rasa 3.0.0. Please convert your existing Markdown data by using the commands described [here](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide#training-data-files). ### Policies [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#policies "Direct link to heading") [Policies](https://legacy-docs-oss.rasa.com/docs/rasa/policies) now require a `**kwargs` argument in their constructor and `load` method. Policies without `**kwargs` will be supported until Rasa version `3.0.0`. However when using [incremental training](https://legacy-docs-oss.rasa.com/docs/rasa/command-line-interface#incremental-training)`**kwargs` **must** be included. #### Other [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#other "Direct link to heading") - `Domain.random_template_for` is deprecated and will be removed in Rasa 3.0.0. You can alternatively use the `TemplatedNaturalLanguageGenerator`. - `Domain.action_names` is deprecated and will be removed in Rasa 3.0.0. Please use `Domain.action_names_or_texts` instead. ## Rasa 2.0 to Rasa 2.1 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-20-to-rasa-21 "Direct link to heading") ### Deprecations [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#deprecations-2 "Direct link to heading") `ConveRTTokenizer` is now deprecated. [ConveRTFeaturizer](https://legacy-docs-oss.rasa.com/docs/rasa/components#convertfeaturizer) now implements its behaviour. To migrate, replace `ConveRTTokenizer` with any other tokenizer, for e.g.: Copy pipeline: -name: WhitespaceTokenizer -name: ConveRTFeaturizer model\_url: ... `HFTransformersNLP` and `LanguageModelTokenizer` components are now deprecated. [LanguageModelFeaturizer](https://legacy-docs-oss.rasa.com/docs/rasa/components#languagemodelfeaturizer) now implements their behaviour. To migrate, replace both the above components with any tokenizer and specify the model architecture and model weights as part of `LanguageModelFeaturizer`, for e.g.: Copy pipeline: -name: WhitespaceTokenizer -name: LanguageModelFeaturizer model\_name:"bert" model\_weights:"rasa/LaBSE" ... ## Rasa 1.10 to Rasa 2.0 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-110-to-rasa-20 "Direct link to heading") ### General [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#general-2 "Direct link to heading") A lot has changed in version 2.0. Make sure you read through this guide thoroughly, to make sure all parts of your bot are updated. A lot of updates can be done automatically with inbuilt commands, others will need some manual conversion. If you have any feedback about these updates or the migration process, please post it in the [forum](https://forum.rasa.com/t/rasa-open-source-2-0-is-out-now-internal-draft/35577). ### Training data files [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#training-data-files "Direct link to heading") As of version 2.0, the new default training data format is yaml. Markdown is still supported, but this will be deprecated in Rasa 3.0.0. You can convert existing NLU, Stories, and NLG (i.e. `responses.md`) training data files in the Markdown format to the new YAML format using following commands: Copy rasa data convert nlu -f yaml --data={SOURCE\_DIR} --out={TARGET\_DIR} rasa data convert nlg -f yaml --data={SOURCE\_DIR} --out={TARGET\_DIR} rasa data convert core -f yaml --data={SOURCE\_DIR} --out={TARGET\_DIR} Converted files will have the same names as the original ones but with a `_converted.yml` suffix. If you are using [forms](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide#forms) or [response selectors](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide#response-selectors), some additional changes will need to be made as described in their respective sections. ### Policies [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#policies-1 "Direct link to heading") With the introduction of [rules](https://legacy-docs-oss.rasa.com/docs/rasa/rules) and the [RulePolicy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#rule-policy), the following policies are deprecated: - [Mapping Policy](/content/docs/rasa/2.x/policies#mapping-policy/index.html) - [Fallback Policy](/content/docs/rasa/2.x/policies#fallback-policy/index.html) - [Two-Stage Fallback Policy](/content/docs/rasa/2.x/policies#two-stage-fallback-policy/index.html) - [Form Policy](/content/docs/rasa/2.x/policies#form-policy/index.html) To migrate the policies automatically, you can run the following command: Copy rasa data convert config This command will take care of updating your `config.yml` and `domain.yml`, while making backups of your existing files using the `.bak` suffix. It will also add a `rules.yml` if necessary. Your forms will still function as normal in the old format after this update, but this command does not convert them into the new format automatically. This should be done manually, as described in the section on [forms](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide#forms). You can also migrate the individual policies manually, if you don't want to use the automatic conversion command. #### Manually migrating from the Mapping Policy [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#manually-migrating-from-the-mapping-policy "Direct link to heading") If you previously used the [Mapping Policy](/content/docs/rasa/2.x/policies#mapping-policy/index.html), you can follow the documentation on [FAQs](https://legacy-docs-oss.rasa.com/docs/rasa/chitchat-faqs) to convert your mapped intents to rules. Suppose you previously mapped an intent `ask_is_bot` as follows: domain.yml Copy intents: -ask\_is\_bot: triggers: action\_is\_bot This becomes the following rule: rules.yml Copy rules: -rule: Rule to map \`ask\_is\_bot\` intent steps: -intent: ask\_is\_bot -action: action\_is\_bot And you can safely remove any `triggers:` from your domain: domain.yml Copy intents: - ask\_is\_bot Finally, you can replace the Mapping Policy with the [Rule Policy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#rule-policy) in your model configuration: config.yml Copy policies: \# Other policies -name: RulePolicy #### Manually migrating from the Fallback Policy [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#manually-migrating-from-the-fallback-policy "Direct link to heading") If you previously used the [Fallback Policy](/content/docs/rasa/2.x/policies#fallback-policy/index.html), the following model configuration would translate as follows given a previous configuration like this: config.yml Copy policies: -name:"FallbackPolicy" nlu\_threshold:0.4 core\_threshold:0.3 fallback\_action\_name:"action\_default\_fallback" ambiguity\_threshold:0.1 The new configuration would then look like: config.yml Copy recipe: default.v1 pipeline: \# Other components -name: FallbackClassifier threshold:0.4 ambiguity\_threshold:0.1 policies: \# Other policies -name: RulePolicy core\_fallback\_threshold:0.3 core\_fallback\_action\_name:"action\_default\_fallback" In addition, you need to add a [rule](https://legacy-docs-oss.rasa.com/docs/rasa/rules) to specify which action to run in case of low NLU confidence: rules.yml Copy rules: -rule: Ask the user to rephrase whenever they send a message with low NLU confidence steps: -intent: nlu\_fallback -action: utter\_please\_rephrase See the documentation on [fallback](https://legacy-docs-oss.rasa.com/docs/rasa/fallback-handoff#fallbacks) for more information. #### Manually migrating from the Two-Stage-Fallback Policy [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#manually-migrating-from-the-two-stage-fallback-policy "Direct link to heading") If you previously used the [Two-Stage Fallback Policy](/content/docs/rasa/2.x/policies#two-stage-fallback-policy/index.html), with a configuration like this for example: config.yml Copy policies: -name: TwoStageFallbackPolicy nlu\_threshold:0.4 ambiguity\_threshold:0.1 core\_threshold:0.3 fallback\_core\_action\_name:"action\_default\_fallback" fallback\_nlu\_action\_name:"action\_default\_fallback" deny\_suggestion\_intent\_name:"out\_of\_scope" The new configuration would look like this: config.yml Copy recipe: default.v1 pipeline: \# Other components -name: FallbackClassifier threshold:0.4 ambiguity\_threshold:0.1 policies: \# Other policies -name: RulePolicy core\_fallback\_threshold:0.3 core\_fallback\_action\_name:"action\_default\_fallback" In addition you need to add a [rule](https://legacy-docs-oss.rasa.com/docs/rasa/rules) to activate the Two-Stage Fallback for messages with low NLU confidence. rules.yml Copy rules: -rule: Implementation of the TwoStageFallbackPolicy steps: \# This intent is automatically triggered by the \`FallbackClassifier\` in the NLU \# pipeline in case the intent confidence was below the specified threshold. -intent: nlu\_fallback \# The Fallback is now implemented as a form. -action: action\_two\_stage\_fallback -active\_loop: action\_two\_stage\_fallback Note that the previous parameters `fallback_nlu_action_name` and `deny_suggestion_intent_name` are no longer configurable and have the fixed values `action_default_fallback` and `out_of_scope`. See the [fallback](https://legacy-docs-oss.rasa.com/docs/rasa/fallback-handoff#fallbacks) documentation for more information. ### Forms [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#forms-1 "Direct link to heading") As of version 2.0 the logic for [forms](https://legacy-docs-oss.rasa.com/docs/rasa/forms) has been moved from the Rasa SDK to Rasa to simplify implementation and make it easier to write action servers in other languages. This means that forms are no longer implemented using a `FormAction`, but instead defined in the domain. Any customizations around requesting slots or [slot validation](https://legacy-docs-oss.rasa.com/docs/rasa/forms#validating-form-input) can be handled with a `FormValidationAction`. Consider a custom form action from 1.x like this: Copy from typing import Text, List, Any, Dict, Union from rasa\_sdk import Tracker from rasa\_sdk.executor import CollectingDispatcher from rasa\_sdk.forms import FormAction classRestaurantForm(FormAction): defname(self)-> Text: return"restaurant\_form" @staticmethod defrequired\_slots(tracker: Tracker)-> List\[Text\]: return\["cuisine"\] defslot\_mappings(self)-> Dict\[Text, Union\[Dict, List\[Dict\]\]\]: return{ "cuisine": self.from\_entity(entity="cuisine", not\_intent="chitchat"), } @staticmethod defcuisine\_db()-> List\[Text\]: """Database of supported cuisines""" return\["caribbean","chinese","french"\] defvalidate\_cuisine( self, value: Text, dispatcher: CollectingDispatcher, tracker: Tracker, domain: Dict\[Text, Any\], )-> Dict\[Text, Any\]: """Validate cuisine value.""" if value.lower()in self.cuisine\_db(): \# validation succeeded, set the value of the "cuisine" slot to value return{"cuisine": value} else: dispatcher.utter\_message(template="utter\_wrong\_cuisine") \# validation failed, set this slot to None, meaning the \# user will be asked for the slot again return{"cuisine":None} defsubmit( self, dispatcher: CollectingDispatcher, tracker: Tracker, domain: Dict\[Text, Any\], )-> List\[Dict\]: """Define what the form has to do after all required slots are filled""" \# utter submit template dispatcher.utter\_message(template="utter\_submit") return\[\] Start the migration by removing the FormPolicy and adding the [RulePolicy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#rule-policy) (if not there already) to your model configuration: config.yml Copy policies: \# Other policies \# ... -name: RulePolicy Then you need to define the form, required slots and their slot mappings in the domain as described in the documentation on [forms](https://legacy-docs-oss.rasa.com/docs/rasa/forms#defining-a-form): domain.yml Copy forms: restaurant\_form: cuisine: -type: from\_entity entity: cuisine not\_intent: chitchat If you ran the command to [convert your stories](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide#training-data-Files), you will have a story that handles form activation and deactivation like this: stories.yml Copy stories: -story: cuisine form steps: -intent: request\_restaurant -action: restaurant\_form -active\_loop: restaurant\_form -active\_loop:null -action: utter\_submit This will work fine, but the best way to handle form behavior is to remove this story and instead define two separate rules for form activation and submission: rules.yml Copy rules: -rule: Activate form steps: -intent: request\_restaurant -action: restaurant\_form -active\_loop: restaurant\_form -rule: Submit form condition: \# Condition that form is active. -active\_loop: restaurant\_form steps: -action: restaurant\_form -active\_loop:null \# The action we want to run when the form is submitted. -action: utter\_submit The last step is to implement a custom action to validate the form slots. Start by adding the custom action to your domain: domain.yml Copy actions: \# Other actions \# ... - validate\_restaurant\_form Then add a custom action which validates the `cuisine` slot: Copy from typing import Text, List, Any, Dict, Union from rasa\_sdk import Tracker from rasa\_sdk.executor import CollectingDispatcher from rasa\_sdk import FormValidationAction from rasa\_sdk.types import DomainDict classRestaurantFormValidator(FormValidationAction): defname(self)-> Text: return"validate\_restaurant\_form" @staticmethod defcuisine\_db()-> List\[Text\]: """Database of supported cuisines""" return\["caribbean","chinese","french"\] defvalidate\_cuisine( self, slot\_value: Any, dispatcher: CollectingDispatcher, tracker: Tracker, domain: DomainDict, )-> Dict\[Text, Any\]: """Validate cuisine value.""" if slot\_value.lower()in self.cuisine\_db(): \# validation succeeded, set the value of the "cuisine" slot to value return{"cuisine": slot\_value} else: \# validation failed, set this slot to None, meaning the \# user will be asked for the slot again return{"cuisine":None} You can also migrate forms from Rasa SDK to Rasa 2 iteratively. You can for example migrate one form to the Rasa 2 implementation while continue using the deprecated Rasa SDK implementation for another form. To continue to use the deprecated Rasa SDK `FormAction`s, add a custom action with the name of your form to your domain. Note that you should complete the migration as soon as possible as the deprecated `FormAction` will be removed from the Rasa SDK in Rasa 3. domain.yml Copy actions: \# Adding a custom action for a form will \# instruct Rasa to use the \# deprecated Rasa SDK implementation of forms. - my\_form forms: my\_form: See the [forms](https://legacy-docs-oss.rasa.com/docs/rasa/forms) documentation for more details. ### Response Selectors [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#response-selectors "Direct link to heading") Response Selectors are a stable feature as of version 2.0. The [conversion command](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide#training-data-files) will automatically convert your `responses.md` file, stories and nlu training data to the new yaml format. It will also take care of adding the `utter_` prefix to your responses. Additionally you will need to rename the `respond_` actions in your stories files to use the `utter_` prefix instead. Run the following command to apply these changes: Copy rasa data convert responses --data {SOURCE\_DIR} --out={TARGET\_DIR} You can also apply these changes manually. For example: Copy stories: -story: chitchat steps: -intent: chitchat -action: respond\_chitchat becomes Copy stories: -story: chitchat steps: -intent: chitchat -action: utter\_chitchat and you will need to add the `utter_` prefix to the response names in your `responses.md` as well. For example: Copy responses: chitchat/ask\_name: -text: Oh yeah, I am called the retrieval bot. chitchat/ask\_weather: -text: Oh, it does look sunny right now in Berlin. becomes Copy responses: utter\_chitchat/ask\_name: -text: Oh yeah, I am called the retrieval bot. utter\_chitchat/ask\_weather: -text: Oh, it does look sunny right now in Berlin. Finally, you should remove any actions with the `respond_` prefix from the actions list in your domain. This behavior will work fine when defined as a story, but even better when defined as a rule. You should consider transferring your retrieval stories to rules. More information on what that looks like in the [chitchat and FAQs documentation](https://legacy-docs-oss.rasa.com/docs/rasa/chitchat-faqs). Response Selectors are now trained on retrieval intent labels by default instead of the actual response text. For most models, this should improve training time and accuracy of the `ResponseSelector`. If you want to revert to the pre-2.0 default behavior, add the `use_text_as_label: true` parameter to your `ResponseSelector` component: Copy pipeline: \# other components -name: ResponseSelector use\_text\_as\_label:true The output schema of `ResponseSelector` has changed. An example output looks like this: Copy { "response\_selector":{ "all\_retrieval\_intents":\[\ \ "faq"\ \ \], "default":{ "response":{ "id":1388783286124362000, "confidence":1, "intent\_response\_key":"faq/is\_legit", "response\_templates":\[\ \ {\ \ "text":"absolutely",\ \ "image":"https://i.imgur.com/nGF1K8f.jpg"\ \ },\ \ {\ \ "text":"I think so."\ \ }\ \ \] "template\_name":"utter\_faq/is\_legit" }, "ranking":\[\ \ {\ \ "id":1388783286124362000,\ \ "confidence":1,\ \ "intent\_response\_key":"faq/is\_legit"\ \ }\ \ \] } } } As a result of this, if you were previously querying for the key `full_retrieval_intent` as: Copy response\_selector\_output.get("default") .get("full\_retrieval\_intent") you should instead now do this: Copy response\_selector\_output.get("default") .get("response") .get("intent\_response\_key") ### Unfeaturized Slots [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#unfeaturized-slots "Direct link to heading") [Slots](https://legacy-docs-oss.rasa.com/docs/rasa/domain#slots) of type `unfeaturized` are deprecated and will be removed in version 3.0. To ignore slot values during a conversation, set the `influence_conversation` property of the slot to `false`. The following snippet is an example of the deprecated unfeaturized slot usage: Copy slots: username: type: unfeaturized To update this to the new format, you can specify the expected data type `text` and define that the slot should be ignored during the conversation. Copy slots: username: type: text \# Set \`influence\_conversation\` to \`false\` \# to ignore the slot value during the conversation. influence\_conversation:false If you don't require the slot to have a specific data type, you can use the new slot type [any](https://legacy-docs-oss.rasa.com/docs/rasa/domain#any-slot). This slot type is always ignored during a conversation and does not make any assumptions regarding the data type of the slot value. Copy slots: username: type: any Please see the updated [slots documentation](https://legacy-docs-oss.rasa.com/docs/rasa/domain#slots) for more information. ### Conversation sessions [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#conversation-sessions "Direct link to heading") [Conversation sessions](https://legacy-docs-oss.rasa.com/docs/rasa/domain#session-configuration) are now enabled by default if your [Domain](https://legacy-docs-oss.rasa.com/docs/rasa/domain) does not contain a session configuration. Previously a missing session configuration was treated as if conversation sessions were disabled. You can explicitly disable conversation sessions using the following snippet: domain.yml Copy session\_config: \# A session expiration time of \`0\` \# disables conversation sessions session\_expiration\_time:0 ### Dialogue Featurization [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#dialogue-featurization "Direct link to heading") This section is only relevant if you explicitly defined [featurizers](https://legacy-docs-oss.rasa.com/docs/rasa/policies#featurizers) in your policy configuration. LabelTokenizerSingleStateFeaturizer is deprecated and will be removed in the future. It should be replaced with SingleStateFeaturizer and some changes should be made to the NLU pipeline. Add a `Tokenizer` with the option `intent_tokenization_flag: True` and `CountVectorsFeaturizer` to the NLU pipeline. For example: Copy language: en pipeline: -name: WhitespaceTokenizer intent\_tokenization\_flag:True -name: CountVectorsFeaturizer \# other components policies: \# other policies -name: TEDPolicy featurizer: -name: SingleStateFeaturizer BinarySingleStateFeaturizer is deprecated and will be removed in the future. You should replace it with `SingleStateFeaturizer` and a NLU pipeline where `intent_tokenization_flag` of a Tokenizer is set to `False`. For example: Copy language: en pipeline: -name: WhitespaceTokenizer intent\_tokenization\_flag:False \# other components policies: \# other policies -name: TEDPolicy featurizer: -name: SingleStateFeaturizer ### Deprecations [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#deprecations-3 "Direct link to heading") The deprecated [event brokers](https://legacy-docs-oss.rasa.com/docs/rasa/event-brokers) FileProducer, KafkaProducer, PikaProducer and SQLProducer have been removed. If you used these brokers in your `endpoints.yml` make sure to use the renamed variants instead: - FileProducer became FileEventBroker - KafkaProducer became KafkaEventBroker - PikaProducer became PikaEventBroker - SQLProducer became SQLEventBroker The deprecated EmbeddingIntentClassifier has been removed. If you used this component in your pipeline configuration (`config.yml`) you can replace it with [DIETClassifier](https://legacy-docs-oss.rasa.com/docs/rasa/components#dietclassifier). It accepts the same configuration parameters. The deprecated KerasPolicy has been removed. If you used this component in your policies configuration (`config.yml`) you can replace it with [TEDPolicy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#ted-policy). It accepts the same configuration parameters. ## Rasa 1.7 to Rasa 1.8 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-17-to-rasa-18 "Direct link to heading") ##### caution This is a release **breaking backwards compatibility**. It is not possible to load previously trained models. Please make sure to retrain a model before trying to use it with this improved version. ### General [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#general-3 "Direct link to heading") - The [TED Policy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#ted-policy) replaced the `keras_policy` as recommended machine learning policy. New projects generated with `rasa init` will automatically use this policy. In case you want to change your existing model configuration to use the [TED Policy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#ted-policy) add this to the `policies` section in your `config.yml` and remove potentially existing `KerasPolicy` entries: Copy policies: \# - ... other policies -name: TEDPolicy max\_history:5 epochs:100 The given snippet specifies default values for the parameters `max_history` and `epochs`. `max_history` is particularly important and strongly depends on your stories. Please see the docs of the [TED Policy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#ted-policy) if you want to customize them. - All pre-defined pipeline templates are deprecated. **Any templates you use will be** **mapped to the new configuration, but the underlying architecture is the same**. Take a look at [Tuning Your Model](https://legacy-docs-oss.rasa.com/docs/rasa/tuning-your-model) to decide on what components you should use in your configuration file. - The Embedding Policy was renamed to [TED Policy](https://legacy-docs-oss.rasa.com/docs/rasa/policies#ted-policy). The functionality of the policy stayed the same. Please update your configuration files to use `TEDPolicy` instead of `EmbeddingPolicy`. - Most of the model options for `EmbeddingPolicy`, `EmbeddingIntentClassifier`, and `ResponseSelector` got renamed. Please update your configuration files using the following mapping: | Old model option | New model option | | --- | --- | | hidden\_layers\_sizes\_a | dictionary “hidden\_layers\_sizes” with key “text” | | hidden\_layers\_sizes\_b | dictionary “hidden\_layers\_sizes” with key “label” | | hidden\_layers\_sizes\_pre\_dial | dictionary “hidden\_layers\_sizes” with key “dialogue” | | hidden\_layers\_sizes\_bot | dictionary “hidden\_layers\_sizes” with key “label” | | num\_transformer\_layers | number\_of\_transformer\_layers | | num\_heads | number\_of\_attention\_heads | | max\_seq\_length | maximum\_sequence\_length | | dense\_dim | dense\_dimension | | embed\_dim | embedding\_dimension | | num\_neg | number\_of\_negative\_examples | | mu\_pos | maximum\_positive\_similarity | | mu\_neg | maximum\_negative\_similarity | | use\_max\_sim\_neg | use\_maximum\_negative\_similarity | | C2 | regularization\_constant | | C\_emb | negative\_margin\_scale | | droprate\_a | droprate\_dialogue | | droprate\_b | droprate\_label | | evaluate\_every\_num\_epochs | evaluate\_every\_number\_of\_epochs | | evaluate\_on\_num\_examples | evaluate\_on\_number\_of\_examples | Old configuration options will be mapped to the new names, and a warning will be thrown. However, these will be deprecated in a future release. - The Embedding Intent Classifier is now deprecated and will be replaced by [DIETClassifier](https://legacy-docs-oss.rasa.com/docs/rasa/components#dietclassifier) in the future. `DIETClassfier` performs intent classification as well as entity recognition. If you want to get the same model behavior as the current `EmbeddingIntentClassifier`, you can use the following configuration of `DIETClassifier`: Copy pipeline: \# - ... other components -name: DIETClassifier hidden\_layers\_sizes: text:\[256,128\] number\_of\_transformer\_layers:0 weight\_sparsity:0 intent\_classification:True entity\_recognition:False use\_masked\_language\_model:False BILOU\_flag:False scale\_loss:True use\_sparse\_input\_dropout:False use\_dense\_input\_dropout:False \# ... any other parameters See [DIETClassifier](https://legacy-docs-oss.rasa.com/docs/rasa/components#dietclassifier) for more information about the new component. Specifying `EmbeddingIntentClassifier` in the configuration maps to the above component definition, and results in the same behaviour within the same Rasa version. - `CRFEntityExtractor` is now deprecated and will be replaced by `DIETClassifier` in the future. If you want to get the same model behavior as the current `CRFEntityExtractor`, you can use the following configuration: Copy pipeline: \# - ... other components -name: LexicalSyntacticFeaturizer features:\[\ \ \ \ \["low","title","upper"\],\ \ \ \ \[\ \ \ \ "BOS",\ \ \ \ "EOS",\ \ \ \ "low",\ \ \ \ "prefix5",\ \ \ \ "prefix2",\ \ \ \ "suffix5",\ \ \ \ "suffix3",\ \ \ \ "suffix2",\ \ \ \ "upper",\ \ \ \ "title",\ \ \ \ "digit",\ \ \ \ \],\ \ \ \ \["low","title","upper"\],\ \ \ \ \] -name: DIETClassifier intent\_classification:False entity\_recognition:True use\_masked\_language\_model:False number\_of\_transformer\_layers:0 \# ... any other parameters `CRFEntityExtractor` featurizes user messages on its own, it does not depend on any featurizer. We extracted the featurization from the component into the new featurizer [LexicalSyntacticFeaturizer](https://legacy-docs-oss.rasa.com/docs/rasa/components#lexicalsyntacticfeaturizer). Thus, in order to obtain the same results as before, you need to add this featurizer to your pipeline before the [DIETClassifier](https://legacy-docs-oss.rasa.com/docs/rasa/components#dietclassifier). Specifying `CRFEntityExtractor` in the configuration maps to the above component definition, the behavior is unchanged from previous versions. - If your pipeline contains `CRFEntityExtractor` and `EmbeddingIntentClassifier` you can substitute both components with [DIETClassifier](https://legacy-docs-oss.rasa.com/docs/rasa/components#dietclassifier). You can use the following pipeline for that: Copy pipeline: \# - ... other components -name: LexicalSyntacticFeaturizer -name: DIETClassifier number\_of\_transformer\_layers:0 \# ... any other parameters ## Rasa 1.6 to Rasa 1.7 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-16-to-rasa-17 "Direct link to heading") ### General [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#general-4 "Direct link to heading") - By default, the `EmbeddingIntentClassifier`, `EmbeddingPolicy`, and `ResponseSelector` will now normalize the top 10 confidence results if the `loss_type` is `"softmax"` (which has been default since 1.3, see [Rasa 1.2 to Rasa 1.3](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide#rasa-12-to-rasa-13)). This is configurable via the `ranking_length` configuration parameter; to turn off normalization to match the previous behavior, set `ranking_length: 0`. ## Rasa 1.2 to Rasa 1.3 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-12-to-rasa-13 "Direct link to heading") ##### caution ### General [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#general-5 "Direct link to heading") - Default parameters of `EmbeddingIntentClassifier` are changed. See the Components page for details. Architecture implementation is changed as well, so **old trained models cannot be loaded**. Default parameters and architecture for `EmbeddingPolicy` are changed. See [Policies](https://legacy-docs-oss.rasa.com/docs/rasa/policies) for details. It uses transformer instead of lstm. **Old trained models cannot be loaded**. They use `inner` similarity and `softmax` loss by default instead of `cosine` similarity and `margin` loss (can be set in config file). They use `balanced` batching strategy by default to counteract class imbalance problem. The meaning of `evaluate_on_num_examples` is changed. If it is non zero, random examples will be picked by stratified split and used as **hold out** validation set, so they will be excluded from training data. We suggest to set it to zero (default) if data set contains a lot of unique examples of dialogue turns. Removed `label_tokenization_flag` and `label_split_symbol` from component. Instead moved intent splitting to `Tokenizer` components via `intent_tokenization_flag` and `intent_split_symbol` flag. - Default `max_history` for `EmbeddingPolicy` is `None` which means it'll use the `FullDialogueTrackerFeaturizer`. We recommend to set `max_history` to some finite value in order to use `MaxHistoryTrackerFeaturizer` for **faster training**. See [Featurizers](https://legacy-docs-oss.rasa.com/docs/rasa/policies#featurizers) for details. We recommend to increase `batch_size` for `MaxHistoryTrackerFeaturizer` (e.g. `"batch_size": [32, 64]`) - **Compare** mode of `rasa train core` allows the whole core config comparison. Therefore, we changed the naming of trained models. They are named by config file name instead of policy name. Old naming style will not be read correctly when creating **compare** plots (`rasa test core`). Please remove old trained models in comparison folder and retrain. Normal core training is unaffected. - We updated the **evaluation metric** for our **NER**. We report the weighted precision and f1-score. So far we included `no-entity` in this report. However, as most of the tokens actually don't have an entity set, this will influence the weighted precision and f1-score quite a bit. From now on we exclude `no-entity` from the evaluation. The overall metrics now only include proper entities. You might see a drop in the performance scores when running the evaluation again. - `/` is reserved as a delimiter token to distinguish between retrieval intent and the corresponding response text identifier. Make sure you don't include `/` symbol in the name of your intents. ## Rasa NLU 0.14.x and Rasa Core 0.13.x to Rasa 1.0 [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#rasa-nlu-014x-and-rasa-core-013x-to-rasa-10 "Direct link to heading") ##### caution ### General [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#general-6 "Direct link to heading") - The scripts in `rasa.core` and `rasa.nlu` can no longer be executed. To train, test, run, … an NLU or Core model, you should now use the command line interface `rasa`. The functionality is, for the most part, the same as before. Some changes in commands reflect the combined training and running of NLU and Core models, but NLU and Core can still be trained and used individually. If you attempt to run one of the old scripts in `rasa.core` or `rasa.nlu`, an error is thrown that points you to the command you should use instead. See all the new commands at [Command Line Interface](https://legacy-docs-oss.rasa.com/docs/rasa/command-line-interface). - If you have written a custom output channel, all `send_` methods subclassed from the `OutputChannel` class need to take an additional `\*\*kwargs` argument. You can use these keyword args from your custom action code or the templates in your domain file to send any extra parameters used in your channel's send methods. - If you were previously importing the `Button` or `Element` classes from `rasa_core.dispatcher`, these are now to be imported from `rasa_sdk.utils`. - Rasa NLU and Core previously used [separate configuration files](https://legacy-docs.rasa.com/docs/nlu/0.15.1/migrations/?&_ga=2.218966814.608734414.1560704810-314462423.1543594887#id1). These two files should be merged into a single file either named `config.yml`, or passed via the `--config` parameter. ### Script parameters [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#script-parameters "Direct link to heading") - All script parameter names have been unified to follow the same schema. Any underscores (`_`) in arguments have been replaced with dashes (`-`). For example: `--max_history` has been changed to `--max-history`. You can see all of the script parameters in the `--help` output of the commands in the [Command Line Interface](https://legacy-docs-oss.rasa.com/docs/rasa/command-line-interface). - The `--num_threads` parameter was removed from the `run` command. The server will always run single-threaded, but will now run asynchronously. If you want to make use of multiple processes, feel free to check out the [Sanic server\\ documentation](https://sanicframework.org/en/guide/deployment/running.html#gunicorn). - To avoid conflicts in script parameter names, connectors in the `run` command now need to be specified with `--connector`, as `-c` is no longer supported. The maximum history in the `rasa visualize` command needs to be defined with `--max-history`. Output paths and log files cannot be specified with `-o` anymore; `--out` and `--log-file` should be used. NLU data has been standarized to be `--nlu` and the name of any kind of data files or directory to be `--data`. ### HTTP API [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/\#http-api "Direct link to heading") - There are numerous HTTP API endpoint changes which can be found [here](https://legacy-docs-oss.rasa.com/docs/rasa/http-api). We collect and process your personal information for the following purposes: **Visitor Statistics, Browsing Behavior**. [Learn more...](https://legacy-docs-oss.rasa.com/docs/rasa/migration-guide/#) OKDecline