End-to-End stories and UnexpecTED policy error

Rasa Open Source Feedback on Rasa Open Source
1

I have some story with e2e elements, and the UnexpecTED policy enters in conflict with both of the “user” and the “bot” tags. While adding the user sentences as intents in the domain file solves the problem, the bot sentences cause this problem:

Traceback (most recent call last):
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\runpy.py", line 192, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "C:\Users\a.porporato\Anaconda3\envs\rasatestenv\Scripts\rasa.exe\__main__.py", line 7, in <module>
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\__main__.py", line 117, in main
    cmdline_arguments.func(cmdline_arguments)
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\cli\train.py", line 59, in <lambda>
    train_parser.set_defaults(func=lambda args: run_training(args, can_exit=True))
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\cli\train.py", line 91, in run_training
    training_result = train_all(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\api.py", line 109, in train
    return rasa.utils.common.run_in_loop(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\utils\common.py", line 296, in run_in_loop
    result = loop.run_until_complete(f)
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\asyncio\base_events.py", line 608, in run_until_complete
    return future.result()
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\model_training.py", line 108, in train_async
    return await _train_async_internal(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\model_training.py", line 288, in _train_async_internal
    await _do_training(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\model_training.py", line 352, in _do_training
    await _train_core_with_validated_data(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\model_training.py", line 549, in _train_core_with_validated_data
    await rasa.core.train.train(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\train.py", line 70, in train
    agent.train(training_data, **additional_arguments)
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\agent.py", line 753, in train
    self.policy_ensemble.train(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\policies\ensemble.py", line 206, in train
    policy.train(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\policies\ted_policy.py", line 690, in train
    self.run_training(model_data, label_ids)
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\policies\unexpected_intent_policy.py", line 419, in run_training
    super().run_training(model_data, label_ids)
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\policies\ted_policy.py", line 613, in run_training
    self.model = self.model_class()(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\policies\ted_policy.py", line 1143, in __init__
    self._prepare_layers()
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\policies\ted_policy.py", line 1169, in _prepare_layers
    self._prepare_input_layers(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\core\policies\ted_policy.py", line 1224, in _prepare_input_layers
    ] = rasa_layers.RasaSequenceLayer(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\utils\tensorflow\rasa_layers.py", line 768, in __init__
    self.FEATURE_COMBINING: RasaFeatureCombiningLayer(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\utils\tensorflow\rasa_layers.py", line 413, in __init__
    self._prepare_sparse_dense_concat_layers(attribute, attribute_signature, config)
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\utils\tensorflow\rasa_layers.py", line 450, in _prepare_sparse_dense_concat_layers
    ] = ConcatenateSparseDenseFeatures(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\utils\tensorflow\rasa_layers.py", line 231, in __init__
    self.output_units = self._calculate_output_units(
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\utils\tensorflow\rasa_layers.py", line 291, in _calculate_output_units
    [
  File "c:\users\a.porporato\anaconda3\envs\rasatestenv\lib\site-packages\rasa\utils\tensorflow\rasa_layers.py", line 292, in <listcomp>
    config[DENSE_DIMENSION][attribute]
KeyError: 'action_text'

Adding action_text as ana action in the domain doesn’t solve the issue. Is this a known problem?

2

The error persist after the upgrade to Rasa 2.8.2. It seems that the error persist for stories with the ‘bot’ tag in them.