Rasa: 2.2.0 Release

Deprecations and Removals

• #6410: Domain.random_template_for is deprecated and will be removed in Rasa Open Source 3.0.0. You can alternatively use the TemplatedNaturalLanguageGenerator.

Domain.action_names is deprecated and will be removed in Rasa Open Source 3.0.0. Please use Domain.action_names_or_texts instead. - #7458: Interfaces for Policy.__init__ and Policy.load have changed. See [migration guide](./migration-guide.mdx#rasa-21-to-rasa-22) for details. - #7495: Deprecate training and test data in Markdown format. 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 Open Source 3.0.0.

Please convert your existing Markdown data by using the commands from the [migration guide](./migration-guide.mdx#rasa-21-to-rasa-22):

  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}

• #7529: Domain.add_categorical_slot_default_value, Domain.add_requested_slot and Domain.add_knowledge_base_slots are deprecated and will be removed in Rasa Open Source 3.0.0. Their internal versions are now called during the Domain creation. Calling them manually is no longer required.

Features

• #6971: Incremental training of models in a pipeline is now supported.

If you have added new NLU training examples or new stories/rules for
dialogue manager, you don't need to train the pipeline from scratch. Instead, you can initialize the pipeline with a previously trained model and continue finetuning the model on the complete dataset consisting of new training examples. To do so, use rasa train --finetune. For more detailed explanation of the command, check out the docs on [incremental
training](./command-line-interface.mdx#incremental-training).

Added a configuration parameter additional_vocabulary_size to
[CountVectorsFeaturizer](./components.mdx#countvectorsfeaturizer)
and number_additional_patterns to [RegexFeaturizer](./components.mdx#regexfeaturizer). These parameters are useful to configure when using incremental training for your pipelines. - #7408: Add the option to use cross-validation to the POST /model/test/intents endpoint. To use cross-validation specify the query parameter cross_validation_folds in addition to the training data in YAML format.

Add option to run NLU evaluation (POST /model/test/intents) and model training (POST /model/train) asynchronously. To trigger asynchronous processing specify a callback URL in the query parameter callback_url which Rasa Open Source should send the results to. This URL will also be called in case of errors. - #7496: Make [TED Policy](./policies.mdx#ted-policy) an end-to-end policy. Namely, make it possible to train TED on stories that contain intent and entities or user text and bot actions or bot text. If you don't have text in your stories, TED will behave the same way as before. Add possibility to predict entities using TED.

Here's an example of a dialogue in the Rasa story format:

  stories:
  - story: collect restaurant booking info  # name of the story - just for debugging
    steps:
    - intent: greet                          # user message with no entities
    - action: utter_ask_howcanhelp           # action that the bot should execute
    - intent: inform                         # user message with entities
      entities:
      - location: "rome"
      - price: "cheap"
    - bot: On it                             # actual text that bot can output
    - action: utter_ask_cuisine
    - user: I would like [spanish](cuisine). # actual text that user input
    - action: utter_ask_num_people

Some model options for TEDPolicy got renamed. Please update your configuration files using the following mapping:

| Old model option | New model option | |-----------------------------|--------------------------------------------------------| |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” |

Improvements

• #3998: Added a message showing the location where the failed stories file was saved.
• #7232: Add support for the top-level response keys quick_replies, attachment and elements refered to in rasa.core.channels.OutputChannel.send_reponse, as well as metadata.
• #7257: Changed the format of the histogram of confidence values for both correct and incorrect predictions produced by running rasa test.
• #7284: Run bandit checks on pull requests. Introduce make static-checks command to run all static checks locally.
• #7397: Add rasa train --dry-run command that allows to check if training needs to be performed and what exactly needs to be retrained.
• #7408: POST /model/test/intents now returns the report field for intent_evaluation, entity_evaluation and response_selection_evaluation as machine-readable JSON payload instead of string.
• #7436: Make rasa data validate stories work for end-to-end.

The rasa data validate stories function now considers the tokenized user text instead of the plain text that is part of a state. This is closer to what Rasa Core actually uses to distinguish states and thus captures more story structure problems.

Bugfixes

• #6804: Rename language_list to supported_language_list for JiebaTokenizer.
• #7244: A float slot returns unambiguous values - [1.0, <value>] if successfully converted, [0.0, 0.0] if not. This makes it possible to distinguish an empty float slot from a slot set to 0.0. :::caution This change is model-breaking. Please retrain your models. :::
• #7306: Fix an erroneous attribute for Redis key prefix in rasa.core.tracker_store.RedisTrackerStore: 'RedisTrackerStore' object has no attribute 'prefix'.
• #7407: Remove token when its text (for example, whitespace) can't be tokenized by LM tokenizer (from LanguageModelFeaturizer).
• #7408: Temporary directories which were created during requests to the [HTTP API](http-api.mdx) are now cleaned up correctly once the request was processed.
• #7422: Add option use_word_boundaries for RegexFeaturizer and RegexEntityExtractor. To correctly process languages such as Chinese that don't use whitespace for word separation, the user needs to add the use_word_boundaries: False option to those two components.
• #7529: Correctly fingerprint the default domain slots. Previously this led to the issue that rasa train core would always retrain the model even if the training data hasn't changed.

Improved Documentation

• #7313: Return the "Migrate from" entry to the docs sidebar.

Miscellaneous internal changes

• #7167