Common interface for different mechanisms to load training data.
Retrieves the domain of the bot.
Retrieves the stories that should be used for training.
template_variables- Values of templates that should be replaced while reading the story files.
use_e2e- Specifies whether to parse end to end learning annotations.
exclusion_percentage- Amount of training data that should be excluded.
StoryGraph containing all loaded stories.
Retrieves the configuration that should be used for the training.
The configuration as dictionary.
Retrieves the NLU training data that should be used for training.
language- Can be used to only load training data for a certain language.
TrainingDataImporter instance from a configuration file.
Instance loaded from configuration file will only read Core training data.
Instance loaded from configuration file will only read NLU training data.
TrainingDataImporter instance from a dictionary.
Importer that skips any Core-related file reading.
Importer that skips any NLU related file reading.
TrainingDataImporter that combines multiple importers.
to load the data as if they were a single instance.
Importer that syncs
responses between Domain and NLU training data.
Synchronizes response templates between Domain and NLU and adds retrieval intent properties from the NLU training data back to the Domain.
Merge existing domain with properties of retrieval intents in NLU data.
Update NLU data with response templates for retrieval intents defined in the domain
- enhances the NLU training data with actions / user messages from the stories.
- adds potential end-to-end bot messages from stories as actions to the domain