Migration Guide

These docs are for version 1.x of Rasa Open Source.

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 replaced the Keras Policy as the recommended machine learning policy.
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.
The Embedding Policy has been renamed to TED Policy.

Configuration Snippet

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

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

EmbeddingIntentClassifier is now deprecated and will be replaced by DIETClassifier in the future.

pipeline:
  # - ... other components
  - name: DIETClassifier
    hidden_layers_sizes:
      text: [256, 128]
    number_of_transformer_layers: 0
    # ... any other parameters

See DIETClassifier for more information.

If your pipeline contains CRFEntityExtractor and EmbeddingIntentClassifier, you can substitute both components with DIETClassifier.

Rasa 1.6 to Rasa 1.7

General

By default, the EmbeddingIntentClassifier, EmbeddingPolicy, and ResponseSelector will normalize the top 10 confidence results if the loss_type is "softmax".

Rasa 1.2 to Rasa 1.3

Default parameters of EmbeddingIntentClassifier are changed. See Components for details.
The meaning of evaluate_on_num_examples has changed; if it is non-zero, random examples will be picked by stratified split and used as a hold-out validation set.
max_history for EmbeddingPolicy is set to None by default, which means it’ll use the FullDialogueTrackerFeaturizer. We recommend setting max_history to some finite value for faster training.

👋 I can help you get started with Rasa and answer your technical questions.