Build the Docker image
docker build -t chattybot .
Run the Docker container
docker run -p 5000:5000 chattybot
Sure! Here is the description formatted in Markdown:
ChattyBot is a conversational AI chatbot built with Flask and Rasa, designed to provide a simple yet powerful interface for interacting with users. This project demonstrates how to integrate a Flask web application with the Rasa conversational AI framework, allowing for robust natural language understanding and responses.
- Natural Language Understanding: Leveraging Rasa's advanced NLU capabilities for accurate intent recognition and response generation.
- Simple Web Interface: A clean and user-friendly web interface built with HTML and JavaScript.
- Dockerized Deployment: Easy to set up and run with Docker Compose, ensuring consistent environments and smooth deployments.
- Live File Updates: Automatically reflects changes in the source code, thanks to Docker volumes.
- Cross-Origin Resource Sharing (CORS): Configured to handle requests from different origins, facilitating integration with various frontend applications.
project/
├── Dockerfile
├── docker-compose.yml
├── requirements.txt
├── app.py
├── static/
│ └── index.html
└── rasa/
├── actions/
├── data/
├── models/
├── config.yml
├── credentials.yml
├── domain.yml
└── endpoints.yml
- Docker
- Docker Compose
-
Clone the repository:
git clone https://github.com/yourusername/chattybot.git cd chattybot
-
Build and run the Docker containers:
docker-compose up --build
-
Access the application:
Open your web browser and navigate to
http://localhost:5000
.
- Chat Interface: Type messages into the input box and interact with ChattyBot through the web interface.
- Custom Training Data: Update the Rasa training data in the
rasa/data
directory to customize the bot's responses.
Contributions are welcome! Please fork the repository and submit a pull request for any enhancements, bug fixes, or features.
This project is licensed under the MIT License - see the LICENSE file for details.
For questions or suggestions, please open an issue in the repository or contact [email protected].