# 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/1.9.1/core/policies/#ted-policy) replaced the [Keras Policy](https://legacy-docs-v1.rasa.com/1.9.1/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/1.9.1/core/policies/#ted-policy) add this to the `policies` section in your `config.yml` and remove potentially existing `KerasPolicy` entries:

```yaml
policies:
# - ... other policies
- name: TEDPolicy
  max_history: 5
  epochs: 100
```

- 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/1.9.1/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/1.9.1/core/policies/#embedding-policy) was renamed to [TED Policy](https://legacy-docs-v1.rasa.com/1.9.1/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/1.9.1/nlu/components/#embedding-intent-classifier) is now deprecated and will be replaced by [DIETClassifier](https://legacy-docs-v1.rasa.com/1.9.1/nlu/components/#diet-classifier) in the future. `DIETClassifier` performs intent classification as well as entity recognition. If you want to get the same model behaviour as the current `EmbeddingIntentClassifier`, you can use the following configuration of `DIETClassifier`:

```yaml
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/1.9.1/nlu/components/#diet-classifier) for more information about the new component. Specifying `EmbeddingIntentClassifier` in the configuration maps to the above component definition, the behaviour 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 behaviour as the current `CRFEntityExtractor`, you can use the following configuration:

```yaml
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. Thus, in order to obtain the same results as before, you need to add this featurizer to your pipeline before the `:ref:`diet-classifier`. Specifying `CRFEntityExtractor` in the configuration maps to the above component definition, the behaviour 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/1.9.1/nlu/components/#diet-classifier). You can use the following pipeline for that:

```yaml
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).

## Rasa 1.2 to Rasa 1.3

Warning

### General

- Default parameters of `EmbeddingIntentClassifier` are changed. Architecture implementation is changed as well, so **old trained models cannot be loaded**.

- `/` 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

Warning

### General

- 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.