File | Date | Author | Commit |
---|---|---|---|
.github | 2024-03-15 | David | [e2d556] Create FUNDING.yml |
datasets | 2024-02-21 | David | [31585d] Add files via upload |
.gitignore | 2024-02-21 | David | [3e41b6] Initial commit |
LICENSE | 2024-02-21 | David | [3e41b6] Initial commit |
README.md | 2024-04-06 | David | [6e3447] Updated README.md |
app_v5.py | 2024-02-21 | David | [31585d] Add files via upload |
requirements.txt | 2024-04-03 | David | [dc4c3d] Created requirements.txt |
app_v5.py
: The main application file containing Flask setup, route definitions, ChatterBot initialization, and Twilio API integration.datasets/
: A directory containing various categories for training the chatbot, including:feedback/
general_information/
order_delivery/
placing_orders/
returns/
Each folder contains a corpus.yml file tailored for its specific category, aiding in the chatbot's learning process.
git clone <repository-url>
pip install flask chatterbot twilio
python -m chatterbot --train datasets/
flask run
Once the application is running, it can interact with clients through the configured Twilio messaging service. The chatbot utilizes the trained datasets to respond to customer inquiries, feedback, and support requests effectively.
For detailed API usage and additional configurations, refer to the ChatterBot and Twilio documentation.
The training data (corpus) for this chatbot is primarily in Romanian, tailored for an online store context.
The datasets are structured to enable the bot to handle a wide range of customer inquiries autonomously.
In scenarios where the chatbot cannot provide sufficient assistance, it is designed to direct customers to real customer support agents for further help.
Contributions to enhance the chatbot's functionality, extend the datasets, or improve the application's efficiency are welcome.
This project is licensed under the MIT License - see the LICENSE file for details.