In this project, I create a simple conversational assistant using Rasa, an open-source framework for building AI assistants and chatbots.
data/
- Training data for NLU and dialogue management.
models/
- Stores trained models.
actions/
- Custom action definitions.
domain.yml
- Defines intents, entities, slots, responses, and actions.
config.yml
- Configuration for the training pipeline and policies.
endpoints.yml
- Configuration for bot endpoints.
Ensure I have the following installed:
- Python 3.7+
- Rasa Open Source
- A text editor or IDE
-
Clone the repository:
git clone https://github.com/yourusername/your-repo-name.git cd your-repo-name
-
Create and activate a virtual environment:
python -m venv env source env/bin/activate # On Windows use `env\Scripts\activate`
-
Install the required packages:
pip install -r requirements.txt
To train the NLU and dialogue management models, run:
rasa train
To start the Rasa server:
rasa shell
If there are custom actions, start the action server:
rasa run actions
Test the assistant in interactive mode:
rasa interactive