# Migration Guide This page contains information about changes between major versions and how you can migrate from one version to another. ## Rasa 1.7 to Rasa 1.8 **Warning**: 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 - The [TED Policy](https://legacy-docs-v1.rasa.com/1.10.15/core/policies/#ted-policy) replaced the [Keras Policy](https://legacy-docs-v1.rasa.com/1.10.15/core/policies/#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-v1.rasa.com/1.10.15/core/policies/#ted-policy) add this to the `policies` section in your `config.yml` and remove potentially existing `KerasPolicy` entries: ``` 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-v1.rasa.com/1.10.15/core/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 [Choosing a Pipeline](https://legacy-docs-v1.rasa.com/1.10.15/nlu/choosing-a-pipeline/#choosing-a-pipeline) to decide on what components you should use in your configuration file. - The [Embedding Policy](https://legacy-docs-v1.rasa.com/1.10.15/core/policies/#embedding-policy) was renamed to [TED Policy](https://legacy-docs-v1.rasa.com/1.10.15/core/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. - [EmbeddingIntentClassifier](https://legacy-docs-v1.rasa.com/1.10.15/nlu/components/#embedding-intent-classifier) is now deprecated and will be replaced by [DIETClassifier](https://legacy-docs-v1.rasa.com/1.10.15/nlu/components/#diet-classifier) in the future. `DIETClassifier` 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`: ``` 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 # ... any other parameters ``` See [DIETClassifier](https://legacy-docs-v1.rasa.com/1.10.15/nlu/components/#diet-classifier) for more information about the new component. Specifying `EmbeddingIntentClassifier` in the configuration maps to the above component definition, the behavior is unchanged from previous versions. - `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: ``` 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-v1.rasa.com/1.10.15/nlu/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-v1.rasa.com/1.10.15/nlu/components/#diet-classifier). 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-v1.rasa.com/1.10.15/nlu/components/#diet-classifier). You can use the following pipeline for that: ``` 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 number_of_transformer_layers: 0 # ... any other parameters ``` ## Rasa 1.6 to Rasa 1.7 ### General - 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-v1.rasa.com/1.10.15/migration-guide/#migration-to-rasa-1-3)). 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 ### General - Default parameters of `EmbeddingIntentClassifier` are changed. See [Components](https://legacy-docs-v1.rasa.com/1.10.15/nlu/components/#components) 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-v1.rasa.com/1.10.15/core/policies/#policies) for details. It uses transformer instead of lstm. **Old trained models cannot be loaded**.