Rasa

Latest version: v3.6.20

Safety actively analyzes 681881 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 30 of 49

2.4.1

Not secure
Bugfixes
- [8194](https://github.com/rasahq/rasa/issues/8194): Fix `TEDPolicy` training e2e entities when no entities are present in the stories
but there are entities in the domain.
- [8198](https://github.com/rasahq/rasa/issues/8198): Fixed missing model configuration file validation.
- [8223](https://github.com/rasahq/rasa/issues/8223): In Rasa 2.4.0, support for using `template` in `utter_message` when handling a custom action was wrongly deprecated. Both `template` and `response` are now supported, though note that `template` will be deprecated at Rasa 3.0.0.

2.4.0

Not secure
Deprecations and Removals
- [6484](https://github.com/rasahq/rasa/issues/6484): NLG Server
- Changed request format to send `response` as well as `template` as a field. The `template` field will be removed in Rasa Open Source 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 Open Source 3.0.0. Please see [here](nlg.mdx) 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 Open Source 3.0.0.

`rasa.shared.core.domain`
- The property `templates` is deprecated. Use `responses` instead. It will be removed in Rasa Open Source 3.0.0.
- `retrieval_intent_templates` will be removed in Rasa Open Source 3.0.0. Please use `retrieval_intent_responses` instead.
- `is_retrieval_intent_template` will be removed in Rasa Open Source 3.0.0. Please use `is_retrieval_intent_response` instead.
- `check_missing_templates` will be removed in Rasa Open Source 3.0.0. Please use `check_missing_responses` instead.

Response Selector
- The field `template_name` will be deprecated in Rasa Open Source 3.0.0. Please use `utter_action` instead. Please see [here](components.mdxselectors) for more details.
- The field `response_templates` will be deprecated in Rasa Open Source 3.0.0. Please use `responses` instead. Please see [here](components.mdxselectors) for more details.

Improvements
- [7022](https://github.com/rasahq/rasa/issues/7022): The following endpoints now require the existence of the conversation for the specified conversation ID, raising an exception and returning a 404 status code.

* `GET /conversations/<conversation_id:path>/story`

* `POST /conversations/<conversation_id:path>/execute`

* `POST /conversations/<conversation_id:path>/predict`
- [7438](https://github.com/rasahq/rasa/issues/7438): Simplify our training by overwriting `train_step` instead of `fit` for our custom models.

This allows us to use the build-in callbacks from Keras, such as the
[Tensorboard Callback](https://www.tensorflow.org/api_docs/python/tf/keras/callbacks/TensorBoard),
which offers more functionality compared to what we had before.

:::warning
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'.
- [7578](https://github.com/rasahq/rasa/issues/7578): When `TED` is configured to extract entities `rasa test` now evaluates them against the labels in the test stories. Results are saved in `/results` along with the results for the NLU components that extract entities.
- [7680](https://github.com/rasahq/rasa/issues/7680): We're now running integration tests for Rasa Open Source, with initial coverage for `SQLTrackerStore` (with PostgreSQL),
`RedisLockStore` (with Redis) and `PikaEventBroker` (with RabbitMQ). The integration tests are now part of our
CI, and can also be ran locally using `make test-integration`
(see [Rasa Open Source README](https://github.com/RasaHQ/rasa#running-the-integration-tests) for more information).
- [7763](https://github.com/rasahq/rasa/issues/7763): Allow tests to be located anywhere, not just in `tests` directory.
- [7893](https://github.com/rasahq/rasa/issues/7893): Model configuration files are now validated whether they match the expected schema.
- [7952](https://github.com/rasahq/rasa/issues/7952): Speed up `YAMLStoryReader.is_key_in_yaml` function by making it to check if key is in YAML without
actually parsing the text file.
- [7953](https://github.com/rasahq/rasa/issues/7953): Speed up YAML parsing by reusing parsers, making the process of environment variable interpolation optional,
and by not adding duplicating implicit resolvers and YAML constructors to `ruamel.yaml`
- [7955](https://github.com/rasahq/rasa/issues/7955): Drastically improved finger printing time for large story graphs
- [8000](https://github.com/rasahq/rasa/issues/8000): Remove console logging of conversation level F1-score and precision since these calculations were not meaningful.

Add conversation level accuracy to core policy results logged to file in `story_report.json` after running `rasa test core` or `rasa test`.
- [8100](https://github.com/rasahq/rasa/issues/8100): Improved the [lock store](lock-stores.mdx) debug log message when the process has to
queue because other messages have to be processed before this item.

Bugfixes
- [4612](https://github.com/rasahq/rasa/issues/4612): Fixed the bug that OR statements in stories would break the check whether a model needs to be retrained
- [7063](https://github.com/rasahq/rasa/issues/7063): Update the spec of `POST /model/test/intents` and add tests for cases when JSON is provided.

Fix the incorrect temporary file extension for the data that gets extracted from the payload provided
in the body of `POST /model/test/intents` request.
- [7113](https://github.com/rasahq/rasa/issues/7113): Fix for the cli command `rasa data convert config` when migrating Mapping Policy and no rules.

Making `rasa data convert config` migrate correctly the Mapping Policy when no rules are available. It updates the `config.yml` file by removing the `MappingPolicy` and adding the `RulePolicy` instead. Also, it creates the `data/rules.yml` file even if empty in the case of no available rules.
- [7470](https://github.com/rasahq/rasa/issues/7470): Allow to have slots with values that result to a dictionary under the key `slot_was_set` (in `stories.yml` file).

An example would be to have the following story step in `stories.yml`:
yaml
- slot_was_set:
- some_slot:
some_key: 'some_value'
other_key: 'other_value'

This would be allowed if the `some_slot` is also set accordingly in the `domain.yml` with type `any`.
- [7662](https://github.com/rasahq/rasa/issues/7662): Update the fingerprinting function to recognize changes in lookup files.
- [7932](https://github.com/rasahq/rasa/issues/7932): Fixed a bug when interpolating environment variables in YAML files which included `$` in their value.
This led to the following stack trace:


ValueError: Error when trying to expand the environment variables in '${PASSWORD}'. Please make sure to also set these environment variables: '['$qwerty']'.
(13 additional frame(s) were not displayed)
...
File "rasa/utils/endpoints.py", line 26, in read_endpoint_config
content = rasa.shared.utils.io.read_config_file(filename)
File "rasa/shared/utils/io.py", line 527, in read_config_file
content = read_yaml_file(filename)
File "rasa/shared/utils/io.py", line 368, in read_yaml_file
return read_yaml(read_file(filename, DEFAULT_ENCODING))
File "rasa/shared/utils/io.py", line 349, in read_yaml
return yaml_parser.load(content) or {}
File "rasa/shared/utils/io.py", line 314, in env_var_constructor
" variables: '{}'.".format(value, not_expanded)

- [7949](https://github.com/rasahq/rasa/issues/7949): The REQUESTED_SLOT always belongs to the currently active form.

Previously it was possible that after form switching, the REQUESTED_SLOT was for the previous form.
- [96](https://github.com/rasahq/rasa/issues/96): Update the `LanguageModelFeaturizer` tests to reflect new default model weights for `bert`, and skip all `bert` tests
with default model weights on CI, run `bert` tests with `bert-base-uncased` on CI instead.

Miscellaneous internal changes
- [6484](https://github.com/rasahq/rasa/issues/6484), [#7737](https://github.com/rasahq/rasa/issues/7737), [#7879](https://github.com/rasahq/rasa/issues/7879)

2.3.5

Not secure
Features
- [8860](https://github.com/rasahq/rasa/issues/8860): Added `sasl_mechanism` as an optional configurable parameters for the [Kafka Producer](event-brokers.mdx#kafka-event-broker).

Improvements
- [7955](https://github.com/rasahq/rasa/issues/7955): Drastically improved finger printing time for large story graphs
- [8100](https://github.com/rasahq/rasa/issues/8100): Improved the [lock store](lock-stores.mdx) debug log message when the process has to
queue because other messages have to be processed before this item.

Bugfixes
- [4612](https://github.com/rasahq/rasa/issues/4612): Fixed the bug that OR statements in stories would break the check whether a model needs to be retrained
- [8649](https://github.com/rasahq/rasa/issues/8649): Updated `python-engineio` dependency version for compatibility with `python-socketio`.

Improved Documentation
- [8080](https://github.com/rasahq/rasa/issues/8080): Update links to Sanic docs in the documentation.

2.3.4

Not secure
Bugfixes
- [8014](https://github.com/rasahq/rasa/issues/8014): Setting `model_confidence=cosine` in `DIETClassifier`, `ResponseSelector` and `TEDPolicy` is deprecated and will no longer be available. This was introduced in Rasa Open Source version `2.3.0` but post-release experiments suggest that using cosine similarity as model's confidences can change the ranking of predicted labels which is wrong.

`model_confidence=inner` is deprecated and is replaced by `model_confidence=linear_norm` as the former produced an unbounded range of confidences which broke 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:
yaml
- name: DIETClassifier
model_confidence: linear_norm
constrain_similarities: True

This should ease up [tuning fallback thresholds](./fallback-handoff.mdxfallbacks) as confidences for wrong predictions are better distributed across the range `[0, 1]`.

If you trained a model with `model_confidence=cosine` or `model_confidence=inner` setting using previous versions of Rasa Open Source, please re-train by either removing the `model_confidence` option from the configuration or setting it to `linear_norm`.

`model_confidence=cosine` is removed from the configuration generated by [auto-configuration](model-configuration.mdxsuggested-config).

2.3.3

Not secure
Bugfixes
- [8001](https://github.com/rasahq/rasa/issues/8001): Fixed bug where the conversation does not lock before handling a reminder event.

2.3.2

Not secure
Bugfixes
- [7972](https://github.com/rasahq/rasa/issues/7972): Fix a bug where, if a user injects an intent using the HTTP API, slot auto-filling is not performed on the entities provided.

Page 30 of 49

Links

Releases

Has known vulnerabilities

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.